feat(installer): Add selective install filters and new skill

Add installer filters for risk, category, and tags so maintainers and users can ship smaller skill surfaces to context-sensitive runtimes. Document the reduced-install flow for OpenCode-style hosts, add the humanize-chinese community skill, and sync the generated catalog and plugin-safe artifacts that now reflect the release batch. Refs #437 Refs #440 Refs #443
2026-04-03 17:08:33 +02:00
parent db36188c78
commit bb2304a34f
36 changed files with 4076 additions and 158 deletions
--- a/.claude-plugin/plugin.json
+++ b/.claude-plugin/plugin.json
@@ -1,7 +1,7 @@
 {
  "name": "antigravity-awesome-skills",
  "version": "9.4.0",
-  "description": "Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,327 supported skills.",
+  "description": "Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,330 supported skills.",
  "author": {
    "name": "sickn33 and contributors",
    "url": "https://github.com/sickn33/antigravity-awesome-skills"
--- a/CATALOG.md
+++ b/CATALOG.md
@@ -2,7 +2,7 @@

 Generated at: 2026-02-08T00:00:00.000Z

-Total skills: 1341
+Total skills: 1344

 ## architecture (88)

@@ -37,11 +37,11 @@ Total skills: 1341
 | `context-degradation` | Language models exhibit predictable degradation patterns as context length increases. Understanding these patterns is essential for diagnosing failures and d... | degradation | degradation, context, language, models, exhibit, predictable, length, increases, understanding, these, essential, diagnosing |
 | `core-components` | Core component library and design system patterns. Use when building UI, using design tokens, or working with the component library. | core, components | core, components, component, library, building, ui, tokens, working |
 | `cqrs-implementation` | Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or bu... | cqrs | cqrs, command, query, responsibility, segregation, scalable, architectures, separating, read, write, models, optimizing |
-| `ddd-context-mapping` | Map relationships between bounded contexts and define integration contracts using DDD context mapping patterns. | [ddd, context-map, anti-corruption-layer, integration] | [ddd, context-map, anti-corruption-layer, integration], ddd, context, mapping, map, relationships, between, bounded, contexts |
-| `ddd-strategic-design` | Design DDD strategic artifacts including subdomains, bounded contexts, and ubiquitous language for complex business domains. | [ddd, strategic-design, bounded-context, ubiquitous-language] | [ddd, strategic-design, bounded-context, ubiquitous-language], ddd, strategic, artifacts, including, subdomains, bounded, contexts, ubiquitous |
-| `ddd-tactical-patterns` | Apply DDD tactical patterns in code using entities, value objects, aggregates, repositories, and domain events with explicit invariants. | [ddd, tactical, aggregates, value-objects, domain-events] | [ddd, tactical, aggregates, value-objects, domain-events], ddd, apply, code, entities, value, objects, repositories |
+| `ddd-context-mapping` | Map relationships between bounded contexts and define integration contracts using DDD context mapping patterns. | ddd, context-map, anti-corruption-layer, integration | ddd, context-map, anti-corruption-layer, integration, context, mapping, map, relationships, between, bounded, contexts, define |
+| `ddd-strategic-design` | Design DDD strategic artifacts including subdomains, bounded contexts, and ubiquitous language for complex business domains. | ddd, strategic-design, bounded-context, ubiquitous-language | ddd, strategic-design, bounded-context, ubiquitous-language, strategic, artifacts, including, subdomains, bounded, contexts, ubiquitous, language |
+| `ddd-tactical-patterns` | Apply DDD tactical patterns in code using entities, value objects, aggregates, repositories, and domain events with explicit invariants. | ddd, tactical, aggregates, value-objects, domain-events | ddd, tactical, aggregates, value-objects, domain-events, apply, code, entities, value, objects, repositories, domain |
 | `docs-architect` | Creates comprehensive technical documentation from existing codebases. Analyzes architecture, design patterns, and implementation details to produce long-for... | docs | docs, architect, creates, technical, documentation, existing, codebases, analyzes, architecture, details, produce, long |
-| `domain-driven-design` | Plan and route Domain-Driven Design work from strategic modeling to tactical implementation and evented architecture patterns. | [ddd, domain, bounded-context, architecture] | [ddd, domain, bounded-context, architecture], driven, plan, route, work, strategic, modeling, tactical, evented |
+| `domain-driven-design` | Plan and route Domain-Driven Design work from strategic modeling to tactical implementation and evented architecture patterns. | ddd, domain, bounded-context, architecture | ddd, domain, bounded-context, architecture, driven, plan, route, work, strategic, modeling, tactical, evented |
 | `e2e-testing-patterns` | Build reliable, fast, and maintainable end-to-end test suites that provide confidence to ship code quickly and catch regressions before users do. | e2e | e2e, testing, reliable, fast, maintainable, test, suites, provide, confidence, ship, code, quickly |
 | `electron-development` | Master Electron desktop app development with secure IPC, contextIsolation, preload scripts, multi-process architecture, electron-builder packaging, code sign... | electron | electron, development, desktop, app, secure, ipc, contextisolation, preload, scripts, multi, process, architecture |
 | `elixir-pro` | Write idiomatic Elixir code with OTP patterns, supervision trees, and Phoenix LiveView. Masters concurrency, fault tolerance, and distributed systems. | elixir | elixir, pro, write, idiomatic, code, otp, supervision, trees, phoenix, liveview, masters, concurrency |
@@ -171,7 +171,7 @@ Total skills: 1341
 | `warren-buffett` | Agente que simula Warren Buffett — o maior investidor do seculo XX e XXI, CEO da Berkshire Hathaway, discipulo de Benjamin Graham e socio intelectual de Char... | persona, investing, value-investing, business | persona, investing, value-investing, business, warren, buffett, agente, que, simula, maior, investidor, do |
 | `whatsapp-automation` | Automate WhatsApp Business tasks via Rube MCP (Composio): send messages, manage templates, upload media, and handle contacts. Always search tools first for c... | whatsapp | whatsapp, automation, automate, business, tasks, via, rube, mcp, composio, send, messages, upload |

-## data-ai (252)
+## data-ai (255)

 | Skill | Description | Tags | Triggers |
 | --- | --- | --- | --- |
@@ -183,6 +183,7 @@ Total skills: 1341
 | `agent-memory-mcp` | A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions). | agent, memory, mcp | agent, memory, mcp, hybrid, provides, persistent, searchable, knowledge, ai, agents, architecture, decisions |
 | `agentfolio` | Skill for discovering and researching autonomous AI agents, tools, and ecosystems using the AgentFolio directory. | agentfolio | agentfolio, skill, discovering, researching, autonomous, ai, agents, ecosystems, directory |
 | `agentmail` | Email infrastructure for AI agents. Create accounts, send/receive emails, manage webhooks, and check karma balance via the AgentMail API. | agentmail | agentmail, email, infrastructure, ai, agents, accounts, send, receive, emails, webhooks, check, karma |
+| `agentphone` | Build AI phone agents with AgentPhone API. Use when the user wants to make phone calls, send/receive SMS, manage phone numbers, create voice agents, set up w... | agentphone | agentphone, ai, phone, agents, api, user, wants, calls, send, receive, sms, numbers |
 | `agents-v2-py` | Build container-based Foundry Agents with Azure AI Projects SDK (ImageBasedHostedAgentDefinition). Use when creating hosted agents with custom container imag... | agents, v2, py | agents, v2, py, container, foundry, azure, ai, sdk, imagebasedhostedagentdefinition, creating, hosted, custom |
 | `ai-agent-development` | AI agent development workflow for building autonomous agents, multi-agent systems, and agent orchestration with CrewAI, LangGraph, and custom agents. | ai, agent | ai, agent, development, building, autonomous, agents, multi, orchestration, crewai, langgraph, custom |
 | `ai-agents-architect` | I build AI systems that can act autonomously while remaining controllable. I understand that agents fail in unexpected ways - I design for graceful degradati... | ai, agents | ai, agents, architect, act, autonomously, while, remaining, controllable, understand, fail, unexpected, ways |
@@ -206,7 +207,7 @@ Total skills: 1341
 | `apify-ultimate-scraper` | AI-driven data extraction from 55+ Actors across all major platforms. This skill automatically selects the best Actor for your task. | apify, ultimate, scraper | apify, ultimate, scraper, ai, driven, data, extraction, 55, actors, all, major, platforms |
 | `appdeploy` | Deploy web apps with backend APIs, database, and file storage. Use when the user asks to deploy or publish a website or web app and wants a public URL. Uses ... | appdeploy | appdeploy, deploy, web, apps, backend, apis, database, file, storage, user, asks, publish |
 | `astropy` | Astropy is the core Python package for astronomy, providing essential functionality for astronomical research and data analysis. | astropy | astropy, core, python, package, astronomy, providing, essential, functionality, astronomical, research, data, analysis |
-| `audio-transcriber` | Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration | [audio, transcription, whisper, meeting-minutes, speech-to-text] | [audio, transcription, whisper, meeting-minutes, speech-to-text], audio, transcriber, transform, recordings, professional, markdown, documentation |
+| `audio-transcriber` | Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration | audio, transcription, whisper, meeting-minutes, speech-to-text | audio, transcription, whisper, meeting-minutes, speech-to-text, transcriber, transform, recordings, professional, markdown, documentation, intelligent |
 | `autonomous-agents` | You are an agent architect who has learned the hard lessons of autonomous AI. You've seen the gap between impressive demos and production disasters. You know... | autonomous, agents | autonomous, agents, agent, architect, who, learned, hard, lessons, ai, ve, seen, gap |
 | `avoid-ai-writing` | Audit and rewrite content to remove 21 categories of AI writing patterns with a 43-entry replacement table | avoid, ai, writing | avoid, ai, writing, audit, rewrite, content, remove, 21, categories, 43, entry, replacement |
 | `awt-e2e-testing` | AI-powered E2E web testing — eyes and hands for AI coding tools. Declarative YAML scenarios, Playwright execution, visual matching (OpenCV + OCR), platform a... | awt, e2e | awt, e2e, testing, ai, powered, web, eyes, hands, coding, declarative, yaml, scenarios |
@@ -324,6 +325,7 @@ Total skills: 1341
 | `hosted-agents-v2-py` | Build hosted agents using Azure AI Projects SDK with ImageBasedHostedAgentDefinition. Use when creating container-based agents in Azure AI Foundry. | hosted, agents, v2, py | hosted, agents, v2, py, azure, ai, sdk, imagebasedhostedagentdefinition, creating, container, foundry |
 | `hugging-face-community-evals` | Run local evaluations for Hugging Face Hub models with inspect-ai or lighteval. | hugging, face, community, evals | hugging, face, community, evals, run, local, evaluations, hub, models, inspect, ai, lighteval |
 | `hugging-face-datasets` | Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset qu... | hugging, face, datasets | hugging, face, datasets, hub, supports, initializing, repos, defining, configs, prompts, streaming, row |
+| `humanize-chinese` | Detect and rewrite AI-like Chinese text with a practical workflow for scoring, humanization, academic AIGC reduction, and style conversion. Use when the user... | chinese, writing, editing, aigc, academic, style-transfer | chinese, writing, editing, aigc, academic, style-transfer, humanize, detect, rewrite, ai, like, text |
 | `hybrid-search-implementation` | Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides... | hybrid, search | hybrid, search, combine, vector, keyword, improved, retrieval, implementing, rag, building, engines, neither |
 | `iconsax-library` | Extensive icon library and AI-driven icon generation skill for premium UI/UX design. | iconsax, library | iconsax, library, extensive, icon, ai, driven, generation, skill, premium, ui, ux |
 | `image-studio` | Studio de geracao de imagens inteligente — roteamento automatico entre ai-studio-image (fotos humanizadas/influencer) e stability-ai (arte/ ilustracao/edicao... | image-generation, routing, ai-art, photography | image-generation, routing, ai-art, photography, image, studio, de, geracao, imagens, inteligente, roteamento, automatico |
@@ -409,12 +411,13 @@ Total skills: 1341
 | `travel-health-analyzer` | 分析旅行健康数据、评估目的地健康风险、提供疫苗接种建议、生成多语言紧急医疗信息卡片。支持WHO/CDC数据集成的专业级旅行健康风险评估。 | travel, health, analyzer | travel, health, analyzer, who, cdc |
 | `uniprot-database` | Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL. For Python workflows with multiple databases, prefer bio... | uniprot, database | uniprot, database, direct, rest, api, access, protein, searches, fasta, retrieval, id, mapping |
 | `unity-ecs-patterns` | Production patterns for Unity's Data-Oriented Technology Stack (DOTS) including Entity Component System, Job System, and Burst Compiler. | unity, ecs | unity, ecs, data, oriented, technology, stack, dots, including, entity, component, job, burst |
+| `uxui-principles` | Evaluate interfaces against 168 research-backed UX/UI principles, detect antipatterns, and inject UX context into AI coding sessions. | ux, ui, design, evaluation, principles, antipatterns, accessibility | ux, ui, design, evaluation, principles, antipatterns, accessibility, uxui, evaluate, interfaces, against, 168 |
 | `vector-database-engineer` | Expert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applic... | vector, database | vector, database, engineer, databases, embedding, semantic, search, masters, pinecone, weaviate, qdrant, milvus |
 | `vector-index-tuning` | Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector sear... | vector, index, tuning | vector, index, tuning, optimize, performance, latency, recall, memory, hnsw, parameters, selecting, quantization |
 | `vercel-ai-sdk-expert` | Expert in the Vercel AI SDK. Covers Core API (generateText, streamText), UI hooks (useChat, useCompletion), tool calling, and streaming UI components with Re... | vercel, ai, sdk | vercel, ai, sdk, covers, core, api, generatetext, streamtext, ui, hooks, usechat, usecompletion |
 | `vexor` | Vector-powered CLI for semantic file search with a Claude/Codex skill | vexor | vexor, vector, powered, cli, semantic, file, search, claude, codex, skill |
 | `vibe-code-auditor` | Audit rapidly generated or AI-produced code for structural flaws, fragility, and production risks. | vibe, code, auditor | vibe, code, auditor, audit, rapidly, generated, ai, produced, structural, flaws, fragility, risks |
-| `videodb-skills` | Upload, stream, search, edit, transcribe, and generate AI video and audio using the VideoDB SDK. | [video, editing, transcription, subtitles, search, streaming, ai-generation, media] | [video, editing, transcription, subtitles, search, streaming, ai-generation, media], videodb, skills, upload, stream |
+| `videodb-skills` | Upload, stream, search, edit, transcribe, and generate AI video and audio using the VideoDB SDK. | video, editing, transcription, subtitles, search, streaming, ai-generation, media | video, editing, transcription, subtitles, search, streaming, ai-generation, media, videodb, skills, upload, stream |
 | `vizcom` | AI-powered product design tool for transforming sketches into full-fidelity 3D renders. | vizcom | vizcom, ai, powered, product, transforming, sketches, full, fidelity, 3d, renders |
 | `voice-agents` | You are a voice AI architect who has shipped production voice agents handling millions of calls. You understand the physics of latency - every component adds... | voice, agents | voice, agents, ai, architect, who, shipped, handling, millions, calls, understand, physics, latency |
 | `voice-ai-development` | You are an expert in building real-time voice applications. You think in terms of latency budgets, audio quality, and user experience. You know that voice ap... | voice, ai | voice, ai, development, building, real, time, applications, think, terms, latency, budgets, audio |
@@ -618,7 +621,7 @@ Total skills: 1341
 | `zod-validation-expert` | Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js... | zod, validation | zod, validation, typescript, first, schema, covers, parsing, custom, errors, refinements, type, inference |
 | `zustand-store-ts` | Create Zustand stores following established patterns with proper TypeScript types and middleware. | zustand, store, ts | zustand, store, ts, stores, following, established, proper, typescript, types, middleware |

-## general (328)
+## general (327)

 | Skill | Description | Tags | Triggers |
 | --- | --- | --- | --- |
@@ -636,7 +639,6 @@ Total skills: 1341
 | `angular-best-practices` | Angular performance optimization and best practices guide. Use when writing, reviewing, or refactoring Angular code for optimal performance, bundle size, and... | angular, best, practices | angular, best, practices, performance, optimization, writing, reviewing, refactoring, code, optimal, bundle, size |
 | `angular-migration` | Master AngularJS to Angular migration, including hybrid apps, component conversion, dependency injection changes, and routing migration. | angular, migration | angular, migration, angularjs, including, hybrid, apps, component, conversion, dependency, injection, changes, routing |
 | `antigravity-design-expert` | Core UI/UX engineering skill for building highly interactive, spatial, weightless, and glassmorphism-based web interfaces using GSAP and 3D CSS. | antigravity | antigravity, core, ui, ux, engineering, skill, building, highly, interactive, spatial, weightless, glassmorphism |
-| `antigravity-skill-orchestrator` | A meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations using agent-memory-mcp, and pre... | [orchestration, meta-skill, agent-memory, task-evaluation] | [orchestration, meta-skill, agent-memory, task-evaluation], antigravity, skill, orchestrator, meta, understands, task, requirements, dynamically |
 | `apify-actorization` | Actorization converts existing software into reusable serverless applications compatible with the Apify platform. Actors are programs packaged as Docker imag... | apify, actorization | apify, actorization, converts, existing, software, reusable, serverless, applications, compatible, platform, actors, programs |
 | `apify-lead-generation` | Scrape leads from multiple platforms using Apify Actors. | apify, lead, generation | apify, lead, generation, scrape, leads, multiple, platforms, actors |
 | `apify-trend-analysis` | Discover and track emerging trends across Google Trends, Instagram, Facebook, YouTube, and TikTok to inform content strategy. | apify, trend | apify, trend, analysis, discover, track, emerging, trends, google, instagram, facebook, youtube, tiktok |
@@ -862,7 +864,7 @@ Total skills: 1341
 | `production-scheduling` | Codified expertise for production scheduling, job sequencing, line balancing, changeover optimisation, and bottleneck resolution in discrete and batch manufa... | production, scheduling | production, scheduling, codified, expertise, job, sequencing, line, balancing, changeover, optimisation, bottleneck, resolution |
 | `professional-proofreader` | Use when a user asks to "proofread", "review and correct", "fix grammar", "improve readability while keeping my voice", and to proofread a document file and ... | professional, proofreader | professional, proofreader, user, asks, proofread, review, correct, fix, grammar, improve, readability, while |
 | `project-skill-audit` | Audit a project and recommend the highest-value skills to add or update. | skill, audit | skill, audit, recommend, highest, value, skills, add, update |
-| `prompt-engineer` | Transforms user prompts into optimized prompts using frameworks (RTF, RISEN, Chain of Thought, RODES, Chain of Density, RACE, RISE, STAR, SOAP, CLEAR, GROW) | [prompt-engineering, optimization, frameworks, ai-enhancement] | [prompt-engineering, optimization, frameworks, ai-enhancement], prompt, engineer, transforms, user, prompts, optimized, rtf, risen |
+| `prompt-engineer` | Transforms user prompts into optimized prompts using frameworks (RTF, RISEN, Chain of Thought, RODES, Chain of Density, RACE, RISE, STAR, SOAP, CLEAR, GROW) | prompt-engineering, optimization, frameworks, ai-enhancement | prompt-engineering, optimization, frameworks, ai-enhancement, prompt, engineer, transforms, user, prompts, optimized, rtf, risen |
 | `prompt-library` | A comprehensive collection of battle-tested prompts inspired by [awesome-chatgpt-prompts](https://github.com/f/awesome-chatgpt-prompts) and community best pr... | prompt, library | prompt, library, collection, battle, tested, prompts, inspired, awesome, chatgpt, https, github, com |
 | `qiskit` | Qiskit is the world's most popular open-source quantum computing framework with 13M+ downloads. Build quantum circuits, optimize for hardware, execute on sim... | qiskit | qiskit, world, most, popular, open, source, quantum, computing, framework, 13m, downloads, circuits |
 | `quality-nonconformance` | Codified expertise for quality control, non-conformance investigation, root cause analysis, corrective action, and supplier quality management in regulated m... | quality, nonconformance | quality, nonconformance, codified, expertise, control, non, conformance, investigation, root, cause, analysis, corrective |
@@ -931,7 +933,7 @@ Total skills: 1341
 | `varlock` | Secure-by-default environment variable management for Claude Code sessions. | varlock | varlock, secure, default, environment, variable, claude, code, sessions |
 | `verification-before-completion` | Claiming work is complete without verification is dishonesty, not efficiency. Use when ANY variation of success/completion claims, ANY expression of satisfac... | verification, before, completion | verification, before, completion, claiming, work, complete, without, dishonesty, efficiency, any, variation, success |
 | `vexor-cli` | Semantic file discovery via `vexor`. Use whenever locating where something is implemented/loaded/defined in a medium or large repo, or when the file location... | vexor, cli | vexor, cli, semantic, file, discovery, via, whenever, locating, where, something, implemented, loaded |
-| `videodb` | Video and audio perception, indexing, and editing. Ingest files/URLs/live streams, build visual/spoken indexes, search with timestamps, edit timelines, add o... | [video, editing, transcription, subtitles, search, streaming, ai-generation, media, live-streams, desktop-capture] | [video, editing, transcription, subtitles, search, streaming, ai-generation, media, live-streams, desktop-capture], videodb, video |
+| `videodb` | Video and audio perception, indexing, and editing. Ingest files/URLs/live streams, build visual/spoken indexes, search with timestamps, edit timelines, add o... | video, editing, transcription, subtitles, search, streaming, ai-generation, media, live-streams, desktop-capture | video, editing, transcription, subtitles, search, streaming, ai-generation, media, live-streams, desktop-capture, videodb, audio |
 | `viral-generator-builder` | You understand why people share things. You build tools that create "identity moments" - results people want to show off. You know the difference between a t... | viral, generator, builder | viral, generator, builder, understand, why, people, share, things, identity, moments, results, want |
 | `web-performance-optimization` | Optimize website and web application performance including loading speed, Core Web Vitals, bundle size, caching strategies, and runtime performance | web, performance, optimization | web, performance, optimization, optimize, website, application, including, loading, speed, core, vitals, bundle |
 | `weightloss-analyzer` | 分析减肥数据、计算代谢率、追踪能量缺口、管理减肥阶段 | weightloss, analyzer | weightloss, analyzer |
@@ -949,7 +951,7 @@ Total skills: 1341
 | `yann-lecun-debate` | Sub-skill de debates e posições de Yann LeCun. Cobre críticas técnicas detalhadas aos LLMs, rivalidades intelectuais (LeCun vs Hinton, Sutskever, Russell, Yu... | persona, ai-debate, llm-criticism, open-source | persona, ai-debate, llm-criticism, open-source, yann, lecun, debate, sub, skill, de, debates, posi |
 | `yann-lecun-filosofia` | Sub-skill filosófica e pedagógica de Yann LeCun. | persona, ai-philosophy, open-source, education | persona, ai-philosophy, open-source, education, yann, lecun, filosofia, sub, skill, filos, fica, pedag |
 | `yann-lecun-tecnico` | Sub-skill técnica de Yann LeCun. Cobre CNNs, LeNet, backpropagation, JEPA (I-JEPA, V-JEPA, MC-JEPA), AMI (Advanced Machinery of Intelligence), Self-Supervise... | persona, cnn, jepa, self-supervised, pytorch | persona, cnn, jepa, self-supervised, pytorch, yann, lecun, tecnico, sub, skill, cnica, de |
-| `youtube-summarizer` | Extract transcripts from YouTube videos and generate comprehensive, detailed summaries using intelligent analysis frameworks | [video, summarization, transcription, youtube, content-analysis] | [video, summarization, transcription, youtube, content-analysis], summarizer, extract, transcripts, videos, generate, detailed, summaries |
+| `youtube-summarizer` | Extract transcripts from YouTube videos and generate comprehensive, detailed summaries using intelligent analysis frameworks | video, summarization, transcription, youtube, content-analysis | video, summarization, transcription, youtube, content-analysis, summarizer, extract, transcripts, videos, generate, detailed, summaries |

 ## infrastructure (120)

@@ -1074,7 +1076,7 @@ Total skills: 1341
 | `unity-developer` | Build Unity games with optimized C# scripts, efficient rendering, and proper asset management. Masters Unity 6 LTS, URP/HDRP pipelines, and cross-platform de... | unity | unity, developer, games, optimized, scripts, efficient, rendering, proper, asset, masters, lts, urp |
 | `vercel-deployment` | Expert knowledge for deploying to Vercel with Next.js Use when: vercel, deploy, deployment, hosting, production. | vercel, deployment | vercel, deployment, knowledge, deploying, next, js, deploy, hosting |
 | `whatsapp-cloud-api` | Integracao com WhatsApp Business Cloud API (Meta). Mensagens, templates, webhooks HMAC-SHA256, automacao de atendimento. Boilerplates Node.js e Python. | messaging, whatsapp, meta, webhooks | messaging, whatsapp, meta, webhooks, cloud, api, integracao, com, business, mensagens, hmac, sha256 |
-| `x-twitter-scraper` | X (Twitter) data platform skill — tweet search, user lookup, follower extraction, engagement metrics, giveaway draws, monitoring, webhooks, 19 extraction too... | [twitter, x-api, scraping, mcp, social-media, data-extraction, giveaway, monitoring, webhooks] | [twitter, x-api, scraping, mcp, social-media, data-extraction, giveaway, monitoring, webhooks], twitter, scraper, data |
+| `x-twitter-scraper` | X (Twitter) data platform skill — tweet search, user lookup, follower extraction, engagement metrics, giveaway draws, monitoring, webhooks, 19 extraction too... | twitter, x-api, scraping, mcp, social-media, data-extraction, giveaway, monitoring, webhooks | twitter, x-api, scraping, mcp, social-media, data-extraction, giveaway, monitoring, webhooks, scraper, data, platform |

 ## security (167)

@@ -1208,17 +1210,17 @@ Total skills: 1341
 | `security-scanning-security-dependencies` | You are a security expert specializing in dependency vulnerability analysis, SBOM generation, and supply chain security. Scan project dependencies across mul... | security, scanning, dependencies | security, scanning, dependencies, specializing, dependency, vulnerability, analysis, sbom, generation, supply, chain, scan |
 | `security-scanning-security-hardening` | Coordinate multi-layer security scanning and hardening across application, infrastructure, and compliance controls. | security, scanning, hardening | security, scanning, hardening, coordinate, multi, layer, application, infrastructure, compliance, controls |
 | `security-scanning-security-sast` | Static Application Security Testing (SAST) for code vulnerability analysis across multiple languages and frameworks | security, scanning, sast | security, scanning, sast, static, application, testing, code, vulnerability, analysis, multiple, languages, frameworks |
-| `security/aws-compliance-checker` | Automated compliance checking against CIS, PCI-DSS, HIPAA, and SOC 2 benchmarks | [aws, compliance, audit, cis, pci-dss, hipaa, kiro-cli] | [aws, compliance, audit, cis, pci-dss, hipaa, kiro-cli], aws, checker, automated, checking, against |
-| `security/aws-iam-best-practices` | IAM policy review, hardening, and least privilege implementation | [aws, iam, security, access-control, kiro-cli, least-privilege] | [aws, iam, security, access-control, kiro-cli, least-privilege], aws, policy, review, hardening, least, privilege |
-| `security/aws-secrets-rotation` | Automate AWS secrets rotation for RDS, API keys, and credentials | [aws, secrets-manager, security, automation, kiro-cli, credentials] | [aws, secrets-manager, security, automation, kiro-cli, credentials], aws, secrets, rotation, automate, rds, api |
-| `security/aws-security-audit` | Comprehensive AWS security posture assessment using AWS CLI and security best practices | [aws, security, audit, compliance, kiro-cli, security-assessment] | [aws, security, audit, compliance, kiro-cli, security-assessment], aws, posture, assessment, cli |
+| `security/aws-compliance-checker` | Automated compliance checking against CIS, PCI-DSS, HIPAA, and SOC 2 benchmarks | aws, compliance, audit, cis, pci-dss, hipaa, kiro-cli | aws, compliance, audit, cis, pci-dss, hipaa, kiro-cli, checker, automated, checking, against, pci |
+| `security/aws-iam-best-practices` | IAM policy review, hardening, and least privilege implementation | aws, iam, security, access-control, kiro-cli, least-privilege | aws, iam, security, access-control, kiro-cli, least-privilege, policy, review, hardening, least, privilege |
+| `security/aws-secrets-rotation` | Automate AWS secrets rotation for RDS, API keys, and credentials | aws, secrets-manager, security, automation, kiro-cli, credentials | aws, secrets-manager, security, automation, kiro-cli, credentials, secrets, rotation, automate, rds, api, keys |
+| `security/aws-security-audit` | Comprehensive AWS security posture assessment using AWS CLI and security best practices | aws, security, audit, compliance, kiro-cli, security-assessment | aws, security, audit, compliance, kiro-cli, security-assessment, posture, assessment, cli |
 | `semgrep-rule-creator` | Creates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns. Use when writing Semgrep rules or building custom stati... | semgrep, rule, creator | semgrep, rule, creator, creates, custom, rules, detecting, security, vulnerabilities, bug, code, writing |
 | `seo-authority-builder` | Analyzes content for E-E-A-T signals and suggests improvements to build authority and trust. Identifies missing credibility elements. Use PROACTIVELY for YMY... | seo, authority, builder | seo, authority, builder, analyzes, content, signals, suggests, improvements, trust, identifies, missing, credibility |
 | `seo-forensic-incident-response` | Investigate sudden drops in organic traffic or rankings and run a structured forensic SEO incident response with triage, root-cause analysis and recovery plan. | seo, forensic, incident, response | seo, forensic, incident, response, investigate, sudden, drops, organic, traffic, rankings, run, structured |
 | `seo-technical` | Audit technical SEO across crawlability, indexability, security, URLs, mobile, Core Web Vitals, structured data, JavaScript rendering, and related platform s... | seo, technical | seo, technical, audit, crawlability, indexability, security, urls, mobile, core, web, vitals, structured |
 | `service-mesh-expert` | Expert service mesh architect specializing in Istio, Linkerd, and cloud-native networking patterns. Masters traffic management, security policies, observabil... | service, mesh | service, mesh, architect, specializing, istio, linkerd, cloud, native, networking, masters, traffic, security |
 | `simplify-code` | Review a diff for clarity and safe simplifications, then optionally apply low-risk fixes. | simplify, code | simplify, code, review, diff, clarity, safe, simplifications, then, optionally, apply, low, risk |
-| `skill-creator` | To create new CLI skills following Anthropic's official best practices with zero manual configuration. This skill automates brainstorming, template applicati... | [automation, scaffolding, skill-creation, meta-skill] | [automation, scaffolding, skill-creation, meta-skill], skill, creator, new, cli, skills, following, anthropic, official |
+| `skill-creator` | To create new CLI skills following Anthropic's official best practices with zero manual configuration. This skill automates brainstorming, template applicati... | automation, scaffolding, skill-creation, meta-skill | automation, scaffolding, skill-creation, meta-skill, skill, creator, new, cli, skills, following, anthropic, official |
 | `skill-scanner` | Scan agent skills for security issues before adoption. Detects prompt injection, malicious code, excessive permissions, secret exposure, and supply chain risks. | skill, scanner | skill, scanner, scan, agent, skills, security, issues, before, adoption, detects, prompt, injection |
 | `smtp-penetration-testing` | Conduct comprehensive security assessments of SMTP (Simple Mail Transfer Protocol) servers to identify vulnerabilities including open relays, user enumeratio... | smtp, penetration | smtp, penetration, testing, conduct, security, assessments, simple, mail, transfer, protocol, servers, identify |
 | `snowflake-development` | Comprehensive Snowflake development assistant covering SQL best practices, data pipeline design (Dynamic Tables, Streams, Tasks, Snowpipe), Cortex AI functio... | snowflake | snowflake, development, assistant, covering, sql, data, pipeline, dynamic, tables, streams, tasks, snowpipe |
@@ -1284,7 +1286,7 @@ Total skills: 1341
 | `wiki-qa` | Answer repository questions grounded entirely in source code evidence. Use when user asks a question about the codebase, user wants to understand a specific ... | wiki, qa | wiki, qa, answer, repository, questions, grounded, entirely, source, code, evidence, user, asks |
 | `windows-privilege-escalation` | Provide systematic methodologies for discovering and exploiting privilege escalation vulnerabilities on Windows systems during penetration testing engagements. | windows, privilege, escalation | windows, privilege, escalation, provide, systematic, methodologies, discovering, exploiting, vulnerabilities, during, penetration, testing |

-## workflow (101)
+## workflow (102)

 | Skill | Description | Tags | Triggers |
 | --- | --- | --- | --- |
@@ -1294,6 +1296,7 @@ Total skills: 1341
 | `agent-orchestrator` | Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry m... | orchestration, multi-agent, workflow, automation | orchestration, multi-agent, workflow, automation, agent, orchestrator, meta, skill, que, orquestra, todos, os |
 | `airtable-automation` | Automate Airtable tasks via Rube MCP (Composio): records, bases, tables, fields, views. Always search tools first for current schemas. | airtable | airtable, automation, automate, tasks, via, rube, mcp, composio, records, bases, tables, fields |
 | `amplitude-automation` | Automate Amplitude tasks via Rube MCP (Composio): events, user activity, cohorts, user identification. Always search tools first for current schemas. | amplitude | amplitude, automation, automate, tasks, via, rube, mcp, composio, events, user, activity, cohorts |
+| `antigravity-skill-orchestrator` | A meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations using agent-memory-mcp, and pre... | orchestration, meta-skill, agent-memory, task-evaluation | orchestration, meta-skill, agent-memory, task-evaluation, antigravity, skill, orchestrator, meta, understands, task, requirements, dynamically |
 | `apify-influencer-discovery` | Find and evaluate influencers for brand partnerships, verify authenticity, and track collaboration performance across Instagram, Facebook, YouTube, and TikTok. | apify, influencer, discovery | apify, influencer, discovery, find, evaluate, influencers, brand, partnerships, verify, authenticity, track, collaboration |
 | `asana-automation` | Automate Asana tasks via Rube MCP (Composio): tasks, projects, sections, teams, workspaces. Always search tools first for current schemas. | asana | asana, automation, automate, tasks, via, rube, mcp, composio, sections, teams, workspaces, always |
 | `azure-functions` | Modern .NET execution model with process isolation | azure, functions | azure, functions, net, execution, model, process, isolation |
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -9,6 +9,51 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

 ## [Unreleased]

+## [9.5.0] - 2026-04-03 - "Selective Installs and 30K Stars"
+
+> Installable skill library update for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, OpenCode, and related AI coding assistants.
+
+Start here:
+
+- Install: `npx antigravity-awesome-skills`
+- Choose your tool: [README -> Choose Your Tool](https://github.com/sickn33/antigravity-awesome-skills#choose-your-tool)
+- Best skills by tool: [README -> Best Skills By Tool](https://github.com/sickn33/antigravity-awesome-skills#best-skills-by-tool)
+- Bundles: [docs/users/bundles.md](https://github.com/sickn33/antigravity-awesome-skills/blob/main/docs/users/bundles.md)
+- Workflows: [docs/users/workflows.md](https://github.com/sickn33/antigravity-awesome-skills/blob/main/docs/users/workflows.md)
+
+This release expands the library with four practical additions while making installs much more manageable for context-sensitive runtimes. It merges the current open PR batch, adds `humanize-chinese` directly on `main`, introduces first-class installer filtering by `risk`, `category`, and `tags`, and updates the docs so OpenCode-style `.agents/skills` setups start from a reduced install instead of overwhelming the runtime. It also marks a project milestone: the repository crossed **30K GitHub stars** on April 3, 2026. Thank you to every contributor, source project, issue reporter, and user who keeps this library useful.
+
+## New Skills
+
+- **agentflow** - merges PR #438 to add Kanban-style multi-worker orchestration guidance for Claude Code development pipelines.
+- **uxui-principles** - merges PR #441 to add research-backed UX/UI audit guidance sourced from the `uxuiprinciples/agent-skills` collection.
+- **agentphone** - merges PR #442 to add phone-agent workflows for voice calls, SMS operations, number management, and streaming telephony flows.
+- **humanize-chinese** - adds issue-driven coverage for Chinese AI-text detection, rewriting, academic AIGC reduction, and style-conversion workflows based on `voidborne-d/humanize-chinese`.
+
+## Improvements
+
+- **Selective installer filters** - the npm installer now supports `--risk <csv>`, `--category <csv>`, and `--tags <csv>` with comma-separated include values, trailing `-` exclusions, OR semantics within each flag, exclusion precedence, and AND semantics across dimensions.
+- **Tag-aware filtering** - installer filtering now reads skill frontmatter directly so `tags` can participate in install selection even though `skills_index.json` does not store them.
+- **Recursive install sync** - install manifests now track nested skill paths consistently, and filtered updates prune stale managed entries instead of leaving old skills behind.
+- **OpenCode guidance** - `README.md`, `docs/users/getting-started.md`, and `docs/users/faq.md` now explicitly recommend reduced installs for `.agents/skills` hosts and document the new filter grammar.
+- **Source and contributor credits** - post-merge README credit sync now includes the upstream repositories reflected in this release batch, including `UrRhb/agentflow`, `AgentPhone-AI/skills`, `uxuiprinciples/agent-skills`, and `voidborne-d/humanize-chinese`.
+
+## Who should care
+
+- **Claude Code, Cursor, Codex CLI, and Gemini CLI users** get four new skills covering workflow orchestration, UX/UI review, telephony agents, and Chinese text humanization.
+- **OpenCode and other `.agents/skills` users** now have a supported reduced-install path instead of needing the full library in a context-sensitive runtime.
+- **Maintainers and teams curating smaller agent surfaces** can now ship filtered installs by risk, category, and tag without manually pruning skill folders after each update.
+
+## Credits
+
+- **[@UrRhb](https://github.com/UrRhb)** for the new `agentflow` skill in PR #438
+- **[@modi2meet](https://github.com/modi2meet)** and **[AgentPhone-AI](https://github.com/AgentPhone-AI/skills)** for the new `agentphone` skill in PR #442
+- **[@joselhurtado](https://github.com/joselhurtado)** for the new `uxui-principles` skill in PR #441
+- **[voidborne-d](https://github.com/voidborne-d/humanize-chinese)** for the upstream `humanize-chinese` workflow adapted in issue #437
+- **30,262 GitHub stargazers as of 2026-04-03** for pushing the project past the 30K milestone
+
+Upgrade now: `git pull origin main` to fetch the latest skills.
+
 ## [9.4.0] - 2026-03-31 - "Release Hardening and Credit Sync"

 > Installable skill library update for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and related AI coding assistants.
--- a/README.md
+++ b/README.md
@@ -1,13 +1,13 @@
-<!-- registry-sync: version=9.4.0; skills=1341; stars=28867; updated_at=2026-03-31T16:30:41+00:00 -->
-# 🌌 Antigravity Awesome Skills: 1,341+ Agentic Skills for Claude Code, Gemini CLI, Cursor, Copilot & More
+<!-- registry-sync: version=9.4.0; skills=1344; stars=28867; updated_at=2026-03-31T16:30:41+00:00 -->
+# 🌌 Antigravity Awesome Skills: 1,344+ Agentic Skills for Claude Code, Gemini CLI, Cursor, Copilot & More

-> **Installable GitHub library of 1,341+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and other AI coding assistants.**
+> **Installable GitHub library of 1,344+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and other AI coding assistants.**

 Antigravity Awesome Skills is an installable GitHub library and npm installer for reusable `SKILL.md` playbooks. It is designed for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, Kiro, OpenCode, GitHub Copilot, and other AI coding assistants that benefit from structured operating instructions. Instead of collecting one-off prompt snippets, this repository gives you a searchable, installable catalog of skills, bundles, workflows, plugin-safe distributions, and practical docs that help agents perform recurring tasks with better context, stronger constraints, and clearer outputs.

 You can use this repo to install a broad multi-tool skill library, start from role-based bundles, or jump into workflow-driven execution for planning, coding, debugging, testing, security review, infrastructure, product work, and growth tasks. The root README is intentionally a high-signal landing page: understand what the project is, install it quickly, choose the right tool path, and then follow deeper docs only when you need them.

-**Start here:** [Star the repo](https://github.com/sickn33/antigravity-awesome-skills/stargazers) · [Install in 1 minute](#installation) · [Choose your tool](#choose-your-tool) · [Best skills by tool](#best-skills-by-tool) · [📚 Browse 1,341+ Skills](#browse-1341-skills) · [Bundles](docs/users/bundles.md) · [Workflows](docs/users/workflows.md) · [Plugins for Claude Code and Codex](docs/users/plugins.md)
+**Start here:** [Star the repo](https://github.com/sickn33/antigravity-awesome-skills/stargazers) · [Install in 1 minute](#installation) · [Choose your tool](#choose-your-tool) · [Best skills by tool](#best-skills-by-tool) · [📚 Browse 1,344+ Skills](#browse-1344-skills) · [Bundles](docs/users/bundles.md) · [Workflows](docs/users/workflows.md) · [Plugins for Claude Code and Codex](docs/users/plugins.md)

 [![GitHub stars](https://img.shields.io/badge/⭐%2029%2C000%2B%20Stars-gold?style=for-the-badge)](https://github.com/sickn33/antigravity-awesome-skills/stargazers)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
@@ -28,7 +28,7 @@ You can use this repo to install a broad multi-tool skill library, start from ro

 - **Installable, not just inspirational**: use `npx antigravity-awesome-skills` to put skills where your tool expects them.
 - **Built for major agent workflows**: Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, Kiro, OpenCode, Copilot, and more.
- **Broad coverage with real utility**: 1,341+ skills across development, testing, security, infrastructure, product, and marketing.
+- **Broad coverage with real utility**: 1,344+ skills across development, testing, security, infrastructure, product, and marketing.
 - **Faster onboarding**: bundles and workflows reduce the time from "I found this repo" to "I used my first skill".
 - **Useful whether you want breadth or curation**: browse the full catalog, start with top bundles, or compare alternatives before installing.

@@ -95,7 +95,7 @@ Use the same repository, but install or invoke it in the way your host expects.
 | Kiro CLI       | `npx antigravity-awesome-skills --kiro`                                | `Use brainstorming to plan a feature`                |
 | Kiro IDE       | `npx antigravity-awesome-skills --path ~/.kiro/skills`                 | `Use @brainstorming to plan a feature`               |
 | GitHub Copilot | _No installer — paste skills or rules manually_                       | `Ask Copilot to use brainstorming to plan a feature` |
-| OpenCode       | `npx antigravity-awesome-skills --path .agents/skills`                 | `opencode run @brainstorming help me plan a feature` |
+| OpenCode       | `npx antigravity-awesome-skills --path .agents/skills --category development,backend --risk safe,none` | `opencode run @brainstorming help me plan a feature` |
 | AdaL CLI       | `npx antigravity-awesome-skills --path .adal/skills`                   | `Use brainstorming to plan a feature`                |
 | Custom path    | `npx antigravity-awesome-skills --path ./my-skills`                    | Depends on your tool                                   |

@@ -127,7 +127,7 @@ Start with [Bundles](docs/users/bundles.md) for role-based recommendations, [Wor

 ## Best Skills By Tool

-If you want a faster answer than "browse all 1,341+ skills", start with a tool-specific guide:
+If you want a faster answer than "browse all 1,344+ skills", start with a tool-specific guide:

 - **[Claude Code skills](docs/users/claude-code-skills.md)**: install paths, starter skills, prompt examples, and plugin marketplace flow.
 - **[Cursor skills](docs/users/cursor-skills.md)**: best starter skills for `.cursor/skills/`, UI-heavy work, and pair-programming flows.
@@ -181,7 +181,9 @@ Bundles are curated groups of recommended skills for a role or goal such as `Web

 If Antigravity starts hitting context limits with too many active skills, the activation guidance in [docs/users/agent-overload-recovery.md](docs/users/agent-overload-recovery.md) can materialize only the bundles or skill ids you want in the live Antigravity directory.

-## Browse 1,341+ Skills
+If you use OpenCode or another `.agents/skills` host, prefer a reduced install up front instead of copying the full library into a context-sensitive runtime. The installer now supports `--risk`, `--category`, and `--tags` so you can keep the installed set narrow.
+
+## Browse 1,344+ Skills

 Use the root repo as a landing page, then jump into the deeper surface that matches your intent.

@@ -216,6 +218,7 @@ Keep the root README short; use the dedicated docs for recovery and platform-spe
 - If you are confused after installation, start with the [Usage Guide](docs/users/usage.md).
 - For Windows truncation or context crash loops, use [docs/users/windows-truncation-recovery.md](docs/users/windows-truncation-recovery.md).
 - For Linux/macOS overload or selective activation, use [docs/users/agent-overload-recovery.md](docs/users/agent-overload-recovery.md).
+- For OpenCode or other `.agents/skills` installs, prefer a reduced install such as `npx antigravity-awesome-skills --path .agents/skills --category development,backend --risk safe,none`.
 - For plugin install details, host compatibility, and marketplace-safe distribution, use [docs/users/plugins.md](docs/users/plugins.md).
 - For contributor expectations and guardrails, use [CONTRIBUTING.md](CONTRIBUTING.md), [`CODE_OF_CONDUCT.md`](CODE_OF_CONDUCT.md), and [`SECURITY.md`](SECURITY.md).

@@ -345,6 +348,7 @@ This collection would not be possible without the incredible work of the Claude
 - **[UrRhb/agentflow](https://github.com/UrRhb/agentflow)**: Kanban-driven AI development pipeline for orchestrating multi-worker Claude Code workflows with deterministic quality gates, adversarial review, cost tracking, and crash-proof execution (MIT).
 - **[AgentPhone-AI/skills](https://github.com/AgentPhone-AI/skills)**: AgentPhone plugin for Claude Code — API-first telephony workflows for AI agents, including phone calls, SMS, phone-number management, voice-agent setup, streaming webhooks, and tool-calling patterns.
 - **[uxuiprinciples/agent-skills](https://github.com/uxuiprinciples/agent-skills)**: Research-backed UX/UI agent skills for auditing interfaces against 168 principles, detecting antipatterns, and injecting UX context into AI coding sessions.
+- **[voidborne-d/humanize-chinese](https://github.com/voidborne-d/humanize-chinese)**: Chinese AI-text detection and humanization toolkit for scoring, rewriting, academic AIGC reduction, and style conversion workflows.

 ### Inspirations

--- a/data/bundles.json
+++ b/data/bundles.json
@@ -6,6 +6,7 @@
      "skills": [
        "agent-framework-azure-ai-py",
        "agentmail",
+        "agentphone",
        "algolia-search",
        "android-jetpack-compose-expert",
        "android_ui_verification",
@@ -747,6 +748,7 @@
        "3d-web-experience",
        "activecampaign-automation",
        "agent-orchestrator",
+        "agentphone",
        "ai-agent-development",
        "ai-ml",
        "airtable-automation",
@@ -824,6 +826,7 @@
        "hig-components-dialogs",
        "hubspot-automation",
        "hubspot-integration",
+        "humanize-chinese",
        "incident-response-smart-fix",
        "instagram-automation",
        "interactive-portfolio",
@@ -892,6 +895,7 @@
        "shopify-apps",
        "shopify-automation",
        "shopify-development",
+        "skill-creator",
        "slack-automation",
        "slack-bot-builder",
        "slack-gif-creator",
--- a/data/catalog.json
+++ b/data/catalog.json
@@ -1,6 +1,6 @@
 {
  "generatedAt": "2026-02-08T00:00:00.000Z",
-  "total": 1341,
+  "total": 1344,
  "skills": [
    {
      "id": "00-andruia-consultant",
@@ -761,6 +761,30 @@
      ],
      "path": "skills/agentmail/SKILL.md"
    },
+    {
+      "id": "agentphone",
+      "name": "agentphone",
+      "description": "Build AI phone agents with AgentPhone API. Use when the user wants to make phone calls, send/receive SMS, manage phone numbers, create voice agents, set up webhooks, or check usage — anything related to telephony, phone numbers, or voice AI.",
+      "category": "data-ai",
+      "tags": [
+        "agentphone"
+      ],
+      "triggers": [
+        "agentphone",
+        "ai",
+        "phone",
+        "agents",
+        "api",
+        "user",
+        "wants",
+        "calls",
+        "send",
+        "receive",
+        "sms",
+        "numbers"
+      ],
+      "path": "skills/agentphone/SKILL.md"
+    },
    {
      "id": "agents-md",
      "name": "agents-md",
@@ -1664,18 +1688,18 @@
      "id": "antigravity-skill-orchestrator",
      "name": "antigravity-skill-orchestrator",
      "description": "A meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations using agent-memory-mcp, and prevents skill overuse for simple tasks.",
-      "category": "general",
+      "category": "workflow",
      "tags": [
-        "[orchestration",
+        "orchestration",
        "meta-skill",
        "agent-memory",
-        "task-evaluation]"
+        "task-evaluation"
      ],
      "triggers": [
-        "[orchestration",
+        "orchestration",
        "meta-skill",
        "agent-memory",
-        "task-evaluation]",
+        "task-evaluation",
        "antigravity",
        "skill",
        "orchestrator",
@@ -2692,25 +2716,25 @@
      "description": "Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration",
      "category": "data-ai",
      "tags": [
-        "[audio",
+        "audio",
        "transcription",
        "whisper",
        "meeting-minutes",
-        "speech-to-text]"
+        "speech-to-text"
      ],
      "triggers": [
-        "[audio",
+        "audio",
        "transcription",
        "whisper",
        "meeting-minutes",
-        "speech-to-text]",
-        "audio",
+        "speech-to-text",
        "transcriber",
        "transform",
        "recordings",
        "professional",
        "markdown",
-        "documentation"
+        "documentation",
+        "intelligent"
      ],
      "path": "skills/audio-transcriber/SKILL.md"
    },
@@ -10785,24 +10809,24 @@
      "description": "Map relationships between bounded contexts and define integration contracts using DDD context mapping patterns.",
      "category": "architecture",
      "tags": [
-        "[ddd",
+        "ddd",
        "context-map",
        "anti-corruption-layer",
-        "integration]"
+        "integration"
      ],
      "triggers": [
-        "[ddd",
+        "ddd",
        "context-map",
        "anti-corruption-layer",
-        "integration]",
-        "ddd",
+        "integration",
        "context",
        "mapping",
        "map",
        "relationships",
        "between",
        "bounded",
-        "contexts"
+        "contexts",
+        "define"
      ],
      "path": "skills/ddd-context-mapping/SKILL.md"
    },
@@ -10812,24 +10836,24 @@
      "description": "Design DDD strategic artifacts including subdomains, bounded contexts, and ubiquitous language for complex business domains.",
      "category": "architecture",
      "tags": [
-        "[ddd",
+        "ddd",
        "strategic-design",
        "bounded-context",
-        "ubiquitous-language]"
+        "ubiquitous-language"
      ],
      "triggers": [
-        "[ddd",
+        "ddd",
        "strategic-design",
        "bounded-context",
-        "ubiquitous-language]",
-        "ddd",
+        "ubiquitous-language",
        "strategic",
        "artifacts",
        "including",
        "subdomains",
        "bounded",
        "contexts",
-        "ubiquitous"
+        "ubiquitous",
+        "language"
      ],
      "path": "skills/ddd-strategic-design/SKILL.md"
    },
@@ -10839,25 +10863,25 @@
      "description": "Apply DDD tactical patterns in code using entities, value objects, aggregates, repositories, and domain events with explicit invariants.",
      "category": "architecture",
      "tags": [
-        "[ddd",
+        "ddd",
        "tactical",
        "aggregates",
        "value-objects",
-        "domain-events]"
+        "domain-events"
      ],
      "triggers": [
-        "[ddd",
+        "ddd",
        "tactical",
        "aggregates",
        "value-objects",
-        "domain-events]",
-        "ddd",
+        "domain-events",
        "apply",
        "code",
        "entities",
        "value",
        "objects",
-        "repositories"
+        "repositories",
+        "domain"
      ],
      "path": "skills/ddd-tactical-patterns/SKILL.md"
    },
@@ -11754,16 +11778,16 @@
      "description": "Plan and route Domain-Driven Design work from strategic modeling to tactical implementation and evented architecture patterns.",
      "category": "architecture",
      "tags": [
-        "[ddd",
+        "ddd",
        "domain",
        "bounded-context",
-        "architecture]"
+        "architecture"
      ],
      "triggers": [
-        "[ddd",
+        "ddd",
        "domain",
        "bounded-context",
-        "architecture]",
+        "architecture",
        "driven",
        "plan",
        "route",
@@ -16638,6 +16662,35 @@
      ],
      "path": "skills/hugging-face-vision-trainer/SKILL.md"
    },
+    {
+      "id": "humanize-chinese",
+      "name": "humanize-chinese",
+      "description": "Detect and rewrite AI-like Chinese text with a practical workflow for scoring, humanization, academic AIGC reduction, and style conversion. Use when the user asks to 去AI味, 降AIGC, 去除AI痕迹, 论文降重, 知网检测, 维普检测, humanize chinese, detect AI text, or make Chinese text sound more natural.",
+      "category": "data-ai",
+      "tags": [
+        "chinese",
+        "writing",
+        "editing",
+        "aigc",
+        "academic",
+        "style-transfer"
+      ],
+      "triggers": [
+        "chinese",
+        "writing",
+        "editing",
+        "aigc",
+        "academic",
+        "style-transfer",
+        "humanize",
+        "detect",
+        "rewrite",
+        "ai",
+        "like",
+        "text"
+      ],
+      "path": "skills/humanize-chinese/SKILL.md"
+    },
    {
      "id": "hybrid-cloud-architect",
      "name": "hybrid-cloud-architect",
@@ -23933,16 +23986,16 @@
      "description": "Transforms user prompts into optimized prompts using frameworks (RTF, RISEN, Chain of Thought, RODES, Chain of Density, RACE, RISE, STAR, SOAP, CLEAR, GROW)",
      "category": "general",
      "tags": [
-        "[prompt-engineering",
+        "prompt-engineering",
        "optimization",
        "frameworks",
-        "ai-enhancement]"
+        "ai-enhancement"
      ],
      "triggers": [
-        "[prompt-engineering",
+        "prompt-engineering",
        "optimization",
        "frameworks",
-        "ai-enhancement]",
+        "ai-enhancement",
        "prompt",
        "engineer",
        "transforms",
@@ -26072,27 +26125,27 @@
      "description": "Automated compliance checking against CIS, PCI-DSS, HIPAA, and SOC 2 benchmarks",
      "category": "security",
      "tags": [
-        "[aws",
+        "aws",
        "compliance",
        "audit",
        "cis",
        "pci-dss",
        "hipaa",
-        "kiro-cli]"
+        "kiro-cli"
      ],
      "triggers": [
-        "[aws",
+        "aws",
        "compliance",
        "audit",
        "cis",
        "pci-dss",
        "hipaa",
-        "kiro-cli]",
-        "aws",
+        "kiro-cli",
        "checker",
        "automated",
        "checking",
-        "against"
+        "against",
+        "pci"
      ],
      "path": "skills/security/aws-compliance-checker/SKILL.md"
    },
@@ -26102,21 +26155,20 @@
      "description": "IAM policy review, hardening, and least privilege implementation",
      "category": "security",
      "tags": [
-        "[aws",
+        "aws",
        "iam",
        "security",
        "access-control",
        "kiro-cli",
-        "least-privilege]"
+        "least-privilege"
      ],
      "triggers": [
-        "[aws",
+        "aws",
        "iam",
        "security",
        "access-control",
        "kiro-cli",
-        "least-privilege]",
-        "aws",
+        "least-privilege",
        "policy",
        "review",
        "hardening",
@@ -26131,26 +26183,26 @@
      "description": "Automate AWS secrets rotation for RDS, API keys, and credentials",
      "category": "security",
      "tags": [
-        "[aws",
+        "aws",
        "secrets-manager",
        "security",
        "automation",
        "kiro-cli",
-        "credentials]"
+        "credentials"
      ],
      "triggers": [
-        "[aws",
+        "aws",
        "secrets-manager",
        "security",
        "automation",
        "kiro-cli",
-        "credentials]",
-        "aws",
+        "credentials",
        "secrets",
        "rotation",
        "automate",
        "rds",
-        "api"
+        "api",
+        "keys"
      ],
      "path": "skills/security/aws-secrets-rotation/SKILL.md"
    },
@@ -26160,21 +26212,20 @@
      "description": "Comprehensive AWS security posture assessment using AWS CLI and security best practices",
      "category": "security",
      "tags": [
-        "[aws",
+        "aws",
        "security",
        "audit",
        "compliance",
        "kiro-cli",
-        "security-assessment]"
+        "security-assessment"
      ],
      "triggers": [
-        "[aws",
+        "aws",
        "security",
        "audit",
        "compliance",
        "kiro-cli",
-        "security-assessment]",
-        "aws",
+        "security-assessment",
        "posture",
        "assessment",
        "cli"
@@ -27501,16 +27552,16 @@
      "description": "To create new CLI skills following Anthropic's official best practices with zero manual configuration. This skill automates brainstorming, template application, validation, and installation processes while maintaining progressive disclosure patterns and writing style standards.",
      "category": "security",
      "tags": [
-        "[automation",
+        "automation",
        "scaffolding",
        "skill-creation",
-        "meta-skill]"
+        "meta-skill"
      ],
      "triggers": [
-        "[automation",
+        "automation",
        "scaffolding",
        "skill-creation",
-        "meta-skill]",
+        "meta-skill",
        "skill",
        "creator",
        "new",
@@ -31023,6 +31074,36 @@
      ],
      "path": "skills/uv-package-manager/SKILL.md"
    },
+    {
+      "id": "uxui-principles",
+      "name": "uxui-principles",
+      "description": "Evaluate interfaces against 168 research-backed UX/UI principles, detect antipatterns, and inject UX context into AI coding sessions.",
+      "category": "data-ai",
+      "tags": [
+        "ux",
+        "ui",
+        "design",
+        "evaluation",
+        "principles",
+        "antipatterns",
+        "accessibility"
+      ],
+      "triggers": [
+        "ux",
+        "ui",
+        "design",
+        "evaluation",
+        "principles",
+        "antipatterns",
+        "accessibility",
+        "uxui",
+        "evaluate",
+        "interfaces",
+        "against",
+        "168"
+      ],
+      "path": "skills/uxui-principles/SKILL.md"
+    },
    {
      "id": "variant-analysis",
      "name": "variant-analysis",
@@ -31373,7 +31454,7 @@
      "description": "Video and audio perception, indexing, and editing. Ingest files/URLs/live streams, build visual/spoken indexes, search with timestamps, edit timelines, add overlays/subtitles, generate media, and create real-time alerts.",
      "category": "general",
      "tags": [
-        "[video",
+        "video",
        "editing",
        "transcription",
        "subtitles",
@@ -31382,10 +31463,10 @@
        "ai-generation",
        "media",
        "live-streams",
-        "desktop-capture]"
+        "desktop-capture"
      ],
      "triggers": [
-        "[video",
+        "video",
        "editing",
        "transcription",
        "subtitles",
@@ -31394,9 +31475,9 @@
        "ai-generation",
        "media",
        "live-streams",
-        "desktop-capture]",
+        "desktop-capture",
        "videodb",
-        "video"
+        "audio"
      ],
      "path": "skills/videodb/SKILL.md"
    },
@@ -31406,24 +31487,24 @@
      "description": "Upload, stream, search, edit, transcribe, and generate AI video and audio using the VideoDB SDK.",
      "category": "data-ai",
      "tags": [
-        "[video",
+        "video",
        "editing",
        "transcription",
        "subtitles",
        "search",
        "streaming",
        "ai-generation",
-        "media]"
+        "media"
      ],
      "triggers": [
-        "[video",
+        "video",
        "editing",
        "transcription",
        "subtitles",
        "search",
        "streaming",
        "ai-generation",
-        "media]",
+        "media",
        "videodb",
        "skills",
        "upload",
@@ -32431,7 +32512,7 @@
      "description": "X (Twitter) data platform skill — tweet search, user lookup, follower extraction, engagement metrics, giveaway draws, monitoring, webhooks, 19 extraction tools, MCP server.",
      "category": "infrastructure",
      "tags": [
-        "[twitter",
+        "twitter",
        "x-api",
        "scraping",
        "mcp",
@@ -32439,10 +32520,10 @@
        "data-extraction",
        "giveaway",
        "monitoring",
-        "webhooks]"
+        "webhooks"
      ],
      "triggers": [
-        "[twitter",
+        "twitter",
        "x-api",
        "scraping",
        "mcp",
@@ -32450,10 +32531,10 @@
        "data-extraction",
        "giveaway",
        "monitoring",
-        "webhooks]",
-        "twitter",
+        "webhooks",
        "scraper",
-        "data"
+        "data",
+        "platform"
      ],
      "path": "skills/x-twitter-scraper/SKILL.md"
    },
@@ -32694,18 +32775,18 @@
      "description": "Extract transcripts from YouTube videos and generate comprehensive, detailed summaries using intelligent analysis frameworks",
      "category": "general",
      "tags": [
-        "[video",
+        "video",
        "summarization",
        "transcription",
        "youtube",
-        "content-analysis]"
+        "content-analysis"
      ],
      "triggers": [
-        "[video",
+        "video",
        "summarization",
        "transcription",
        "youtube",
-        "content-analysis]",
+        "content-analysis",
        "summarizer",
        "extract",
        "transcripts",
--- a/data/plugin-compatibility.json
+++ b/data/plugin-compatibility.json
@@ -578,6 +578,25 @@
      },
      "runtime_files": []
    },
+    {
+      "id": "agentphone",
+      "path": "skills/agentphone",
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": [],
+      "blocked_reasons": {
+        "codex": [],
+        "claude": []
+      },
+      "runtime_files": []
+    },
    {
      "id": "agents-md",
      "path": "skills/agents-md",
@@ -12907,6 +12926,25 @@
      },
      "runtime_files": []
    },
+    {
+      "id": "humanize-chinese",
+      "path": "skills/humanize-chinese",
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": [],
+      "blocked_reasons": {
+        "codex": [],
+        "claude": []
+      },
+      "runtime_files": []
+    },
    {
      "id": "hybrid-cloud-architect",
      "path": "skills/hybrid-cloud-architect",
@@ -24195,6 +24233,25 @@
      },
      "runtime_files": []
    },
+    {
+      "id": "uxui-principles",
+      "path": "skills/uxui-principles",
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": [],
+      "blocked_reasons": {
+        "codex": [],
+        "claude": []
+      },
+      "runtime_files": []
+    },
    {
      "id": "variant-analysis",
      "path": "skills/variant-analysis",
@@ -25645,10 +25702,10 @@
    }
  ],
  "summary": {
-    "total_skills": 1341,
+    "total_skills": 1344,
    "supported": {
-      "codex": 1311,
-      "claude": 1327
+      "codex": 1314,
+      "claude": 1330
    },
    "blocked": {
      "codex": 30,
--- a/docs/integrations/jetski-cortex.md
+++ b/docs/integrations/jetski-cortex.md
@@ -1,9 +1,9 @@
 ---
 title: Jetski/Cortex + Gemini Integration Guide
-description: "Use antigravity-awesome-skills with Jetski/Cortex without hitting context-window overflow with 1.341+ skills."
+description: "Use antigravity-awesome-skills with Jetski/Cortex without hitting context-window overflow with 1.344+ skills."
 ---

-# Jetski/Cortex + Gemini: safe integration with 1,1.341+ skills
+# Jetski/Cortex + Gemini: safe integration with 1,1.344+ skills

 This guide shows how to integrate the `antigravity-awesome-skills` repository with an agent based on **Jetski/Cortex + Gemini** (or similar frameworks) **without exceeding the model context window**.

@@ -23,7 +23,7 @@ Never do:
 - concatenate all `SKILL.md` content into a single system prompt;
 - re-inject the entire library for **every** request.

-With over 1,1.341 skills, this approach fills the context window before user messages are even added, causing truncation.
+With over 1,1.344 skills, this approach fills the context window before user messages are even added, causing truncation.

 ---

--- a/docs/integrations/jetski-gemini-loader/README.md
+++ b/docs/integrations/jetski-gemini-loader/README.md
@@ -20,7 +20,7 @@ This example shows one way to integrate **antigravity-awesome-skills** with a Je
 - How to enforce a **maximum number of skills per turn** via `maxSkillsPerTurn`.
 - How to choose whether to **truncate or error** when too many skills are requested via `overflowBehavior`.

-This pattern avoids context overflow when you have 1,341+ skills installed.
+This pattern avoids context overflow when you have 1,344+ skills installed.

 ---

--- a/docs/maintainers/repo-growth-seo.md
+++ b/docs/maintainers/repo-growth-seo.md
@@ -6,7 +6,7 @@ This document keeps the repository's GitHub-facing discovery copy aligned with t

 Preferred positioning:

-> Installable GitHub library of 1,341+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and other AI coding assistants.
+> Installable GitHub library of 1,344+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and other AI coding assistants.

 Key framing:

@@ -20,7 +20,7 @@ Key framing:

 Preferred description:

-> Installable GitHub library of 1,341+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
+> Installable GitHub library of 1,344+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.

 Preferred homepage:

@@ -28,7 +28,7 @@ Preferred homepage:

 Preferred social preview:

- use a clean preview image that says `1,341+ Agentic Skills`;
+- use a clean preview image that says `1,344+ Agentic Skills`;
 - mention Claude Code, Cursor, Codex CLI, and Gemini CLI;
 - avoid dense text and tiny logos that disappear in social cards.

--- a/docs/maintainers/skills-update-guide.md
+++ b/docs/maintainers/skills-update-guide.md
@@ -69,7 +69,7 @@ For manual updates, you need:
 The update process refreshes:
 - Skills index (`skills_index.json`)
 - Web app skills data (`apps\web-app\public\skills.json`)
- All 1,341+ skills from the skills directory
+- All 1,344+ skills from the skills directory

 ## When to Update

--- a/docs/users/bundles.md
+++ b/docs/users/bundles.md
@@ -673,4 +673,4 @@ Found a skill that should be in a bundle? Or want to create a new bundle? [Open

 ---

-_Last updated: March 2026 | Total Skills: 1,341+ | Total Bundles: 37_
+_Last updated: March 2026 | Total Skills: 1,344+ | Total Bundles: 37_
--- a/docs/users/claude-code-skills.md
+++ b/docs/users/claude-code-skills.md
@@ -12,7 +12,7 @@ Install the library into Claude Code, then invoke focused skills directly in the

 ## Why use this repo for Claude Code

- It includes 1,341+ skills instead of a narrow single-domain starter pack.
+- It includes 1,344+ skills instead of a narrow single-domain starter pack.
 - It supports the standard `.claude/skills/` path and the Claude Code plugin marketplace flow.
 - It also ships generated bundle plugins so teams can install focused packs like `Essentials` or `Security Developer` from the marketplace metadata.
 - It includes onboarding docs, bundles, and workflows so new users do not need to guess where to begin.
--- a/docs/users/faq.md
+++ b/docs/users/faq.md
@@ -225,6 +225,28 @@ If Antigravity becomes unstable only when the full skills library is active, swi

 That guide shows how to run `scripts/activate-skills.sh` from a cloned copy of this repository so only the bundles or skill ids you need stay active in `~/.gemini/antigravity/skills`.

+### I use OpenCode with `.agents/skills`. Should I install the whole library?
+
+Usually no. For OpenCode and other hosts that read from `.agents/skills`, start with a reduced install instead of copying the full library:
+
+```bash
+npx antigravity-awesome-skills --path .agents/skills --category development,backend --risk safe,none
+```
+
+You can narrow further with `--tags` or exclude values with a trailing `-`:
+
+```bash
+npx antigravity-awesome-skills --path .agents/skills --tags debugging,typescript-
+```
+
+The filter rules are:
+
+- comma-separated values are ORed within one flag
+- exclusions use a trailing `-`, for example `legal-`
+- `--risk`, `--category`, and `--tags` combine with AND
+
+This keeps the installed skill set smaller and reduces the chance of context overload in OpenCode-style runtimes.
+
 ### Gemini CLI hangs after a few turns or says "This is taking a bit longer, we're still on it". What should I do?

 Start with a quick isolation check:
--- a/docs/users/gemini-cli-skills.md
+++ b/docs/users/gemini-cli-skills.md
@@ -12,7 +12,7 @@ Install into the Gemini skills path, then ask Gemini to apply one skill at a tim

 - It installs directly into the expected Gemini skills path.
 - It includes both core software engineering skills and deeper agent/LLM-oriented skills.
- It helps new users get started with bundles and workflows rather than forcing a cold start from 1,341+ files.
+- It helps new users get started with bundles and workflows rather than forcing a cold start from 1,344+ files.
 - It is useful whether you want a broad internal skill library or a single repo to test many workflows quickly.

 ## Install Gemini CLI Skills
--- a/docs/users/getting-started.md
+++ b/docs/users/getting-started.md
@@ -107,7 +107,7 @@ Once installed, just talk to your AI naturally.
 | **Kiro IDE**    | ✅ Full Support | Global: `~/.kiro/skills/` · Workspace: `.kiro/skills/`                |
 | **Antigravity** | ✅ Native       | Global: `~/.gemini/antigravity/skills/` · Workspace: `.agent/skills/` |
 | **Cursor**      | ✅ Native       | `.cursor/skills/`                                                     |
-| **OpenCode**    | ✅ Full Support | `.agents/skills/`                                                     |
+| **OpenCode**    | ✅ Full Support | `.agents/skills/` (prefer reduced installs with `--risk`, `--category`, or `--tags`) |
 | **AdaL CLI**    | ✅ Full Support | `.adal/skills/`                                                       |
 | **Copilot**     | ⚠️ Text Only    | Manual copy-paste                                                     |

@@ -154,6 +154,9 @@ A: Follow the recovery steps in [windows-truncation-recovery.md](windows-truncat
 **Q: What if Antigravity overloads on Linux or macOS when too many skills are active?**
 A: Use the activation flow in [agent-overload-recovery.md](agent-overload-recovery.md). It shows how to run `scripts/activate-skills.sh` from a cloned repo so you can keep the full library archived and activate only the bundles or skills you need in the live Antigravity directory.

+**Q: What if OpenCode or another `.agents/skills` host becomes unstable with a full install?**
+A: Start with a reduced install instead of copying the whole library. For example: `npx antigravity-awesome-skills --path .agents/skills --category development,backend --risk safe,none`. You can narrow further with `--tags` and use a trailing `-` to exclude values such as `typescript-`.
+
 **Q: Is this free?**
 A: Yes. Original code and tooling are MIT-licensed, and original documentation/non-code written content is CC BY 4.0. See [../../LICENSE](../../LICENSE) and [../../LICENSE-CONTENT](../../LICENSE-CONTENT).

--- a/docs/users/kiro-integration.md
+++ b/docs/users/kiro-integration.md
@@ -18,7 +18,7 @@ Kiro is AWS's agentic AI IDE that combines:

 Kiro's agentic capabilities are enhanced by skills that provide:

- **Domain expertise** across 1,341+ specialized areas
+- **Domain expertise** across 1,344+ specialized areas
 - **Best practices** from Anthropic, OpenAI, Google, Microsoft, and AWS
 - **Workflow automation** for common development tasks
 - **AWS-specific patterns** for serverless, infrastructure, and cloud architecture
--- a/docs/users/usage.md
+++ b/docs/users/usage.md
@@ -14,7 +14,7 @@ If you came in through a **Claude Code** or **Codex** plugin instead of a full l

 When you ran `npx antigravity-awesome-skills` or cloned the repository, you:

-✅ **Downloaded 1,341+ skill files** to your computer (default: `~/.gemini/antigravity/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`)  
+✅ **Downloaded 1,344+ skill files** to your computer (default: `~/.gemini/antigravity/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`)  
 ✅ **Made them available** to your AI assistant  
 ❌ **Did NOT enable them all automatically** (they're just sitting there, waiting)

@@ -34,7 +34,7 @@ Bundles are **curated groups** of skills organized by role. They help you decide

 **Analogy:**

- You installed a toolbox with 1,341+ tools (✅ done)
+- You installed a toolbox with 1,344+ tools (✅ done)
 - Bundles are like **labeled organizer trays** saying: "If you're a carpenter, start with these 10 tools"
 - You can either **pick skills from the tray** or install that tray as a focused marketplace bundle plugin

@@ -212,7 +212,7 @@ Let's actually use a skill right now. Follow these steps:

 ## Step 5: Picking Your First Skills (Practical Advice)

-Don't try to use all 1,341+ skills at once. Here's a sensible approach:
+Don't try to use all 1,344+ skills at once. Here's a sensible approach:

 If you want a tool-specific starting point before choosing skills, use:

@@ -343,7 +343,7 @@ Usually no, but if your AI doesn't recognize a skill:

 ### "Can I load all skills into the model at once?"

-No. Even though you have 1,341+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block.
+No. Even though you have 1,344+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block.

 The intended pattern is:

--- a/docs/users/visual-guide.md
+++ b/docs/users/visual-guide.md
@@ -34,7 +34,7 @@ antigravity-awesome-skills/
 ├── 📄 CONTRIBUTING.md                  ← Contributor workflow
 ├── 📄 CATALOG.md                       ← Full generated catalog
 │
-├── 📁 skills/                          ← 1,341+ skills live here
+├── 📁 skills/                          ← 1,344+ skills live here
 │   │
 │   ├── 📁 brainstorming/
 │   │   └── 📄 SKILL.md                 ← Skill definition
@@ -47,7 +47,7 @@ antigravity-awesome-skills/
 │   │   └── 📁 2d-games/
 │   │       └── 📄 SKILL.md             ← Nested skills also supported
 │   │
-│   └── ... (1,341+ total)
+│   └── ... (1,344+ total)
 │
 ├── 📁 apps/
 │   └── 📁 web-app/                     ← Interactive browser
@@ -100,7 +100,7 @@ antigravity-awesome-skills/

 ```
                    ┌─────────────────────────┐
-                    │  1,341+ SKILLS          │
+                    │  1,344+ SKILLS          │
                    └────────────┬────────────┘
                                 │
        ┌────────────────────────┼────────────────────────┐
@@ -201,7 +201,7 @@ If you want a workspace-style manual install instead, cloning into `.agent/skill
 │   ├── 📁 brainstorming/                 │
 │   ├── 📁 stripe-integration/            │
 │   ├── 📁 react-best-practices/          │
-│   └── ... (1,341+ total)                │
+│   └── ... (1,344+ total)                │
 └─────────────────────────────────────────┘
 ```

--- a/package.json
+++ b/package.json
@@ -1,7 +1,7 @@
 {
  "name": "antigravity-awesome-skills",
  "version": "9.4.0",
-  "description": "1,341+ agentic skills for Claude Code, Gemini CLI, Cursor, Antigravity & more. Installer CLI.",
+  "description": "1,344+ agentic skills for Claude Code, Gemini CLI, Cursor, Antigravity & more. Installer CLI.",
  "license": "MIT",
  "scripts": {
    "validate": "node tools/scripts/run-python.js tools/scripts/validate_skills.py",
--- a/plugins/antigravity-awesome-skills-claude/.claude-plugin/plugin.json
+++ b/plugins/antigravity-awesome-skills-claude/.claude-plugin/plugin.json
@@ -1,7 +1,7 @@
 {
  "name": "antigravity-awesome-skills",
  "version": "9.4.0",
-  "description": "Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,327 supported skills.",
+  "description": "Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,330 supported skills.",
  "author": {
    "name": "sickn33 and contributors",
    "url": "https://github.com/sickn33/antigravity-awesome-skills"
--- a/plugins/antigravity-awesome-skills-claude/skills/agentphone/SKILL.md
+++ b/plugins/antigravity-awesome-skills-claude/skills/agentphone/SKILL.md
--- a/plugins/antigravity-awesome-skills-claude/skills/humanize-chinese/SKILL.md
+++ b/plugins/antigravity-awesome-skills-claude/skills/humanize-chinese/SKILL.md
@@ -0,0 +1,146 @@
+---
+name: humanize-chinese
+description: Detect and rewrite AI-like Chinese text with a practical workflow for scoring, humanization, academic AIGC reduction, and style conversion. Use when the user asks to 去AI味, 降AIGC, 去除AI痕迹, 论文降重, 知网检测, 维普检测, humanize chinese, detect AI text, or make Chinese text sound more natural.
+category: content
+risk: safe
+source: community
+tags:
+  - chinese
+  - writing
+  - editing
+  - aigc
+  - academic
+  - style-transfer
+date_added: "2026-04-03"
+---
+
+# Humanize Chinese
+
+Use this skill when you need to detect AI-like Chinese writing, rewrite it to feel less synthetic, reduce AIGC signals in academic prose, or convert the text into a more specific Chinese writing style.
+
+## When to Use
+
+- Use when the user says `去AI味`, `降AIGC`, `去除AI痕迹`, `让文字更自然`, `改成人话`, or `降低AI率`
+- Use when the user wants a Chinese text checked for AI-writing patterns or suspicious phrasing
+- Use when the user wants academic-paper-specific AIGC reduction for CNKI, VIP, or Wanfang-style checks
+- Use when the user wants Chinese text rewritten into a different style such as `zhihu`, `xiaohongshu`, `wechat`, `weibo`, `literary`, or `academic`
+
+## Core Workflow
+
+### 1. Detect Before Rewriting
+
+Start by identifying the most obvious AI markers instead of rewriting blindly:
+
+- rigid `first/second/finally` structures
+- mechanical connectors such as `综上所述`, `值得注意的是`, `由此可见`
+- abstract grandiose wording with low information density
+- repeated sentence rhythm and paragraph length
+- academic prose that sounds too complete, too certain, or too template-driven
+
+If the user provides a short sample, call out the suspicious phrases directly before rewriting.
+
+### 2. Rewrite in the Smallest Useful Pass
+
+Prefer targeted rewrites over total regeneration:
+
+- remove formulaic connectors rather than paraphrasing every sentence
+- vary sentence length and paragraph rhythm
+- replace repeated verbs and noun phrases
+- swap abstract summaries for concrete observations where possible
+- keep the original claims, facts, citations, and terminology intact
+
+### 3. Validate the Result
+
+After rewriting, verify that the text:
+
+- still says the same thing
+- sounds less templated
+- uses more natural rhythm
+- does not introduce factual drift
+- stays in the correct register for the target audience
+
+For academic text, preserve a scholarly tone. Do not over-casualize.
+
+## Optional CLI Flow
+
+If the user has a local clone of the source toolkit, these examples are useful:
+
+```bash
+python3 scripts/detect_cn.py text.txt -v
+python3 scripts/compare_cn.py text.txt -a -o clean.txt
+python3 scripts/academic_cn.py paper.txt -o clean.txt --compare
+python3 scripts/style_cn.py text.txt --style xiaohongshu -o out.txt
+```
+
+Use this CLI sequence when available:
+
+1. detect and inspect suspicious sentences
+2. rewrite or compare
+3. rerun detection on the cleaned file
+4. optionally convert into a target style
+
+## Manual Rewrite Playbook
+
+If the scripts are unavailable, use this manual process.
+
+### Common AI Markers
+
+- numbered or mirrored structures that feel too symmetrical
+- filler transitions that add no meaning
+- repeated stock phrases
+- overly even sentence length
+- conclusions that sound final, polished, and risk-free
+
+### Rewrite Moves
+
+- delete weak transitions first
+- collapse repetitive phrases into one stronger sentence
+- split sentences at natural turns instead of forcing long balanced structures
+- merge choppy sentences when they feel robotic
+- replace generic abstractions with concrete wording
+- introduce light variation in cadence so the prose does not march at a constant tempo
+
+## Academic AIGC Reduction
+
+For papers, reports, or theses:
+
+- keep discipline-specific terminology unchanged
+- replace AI-academic stock phrases with more grounded scholarly phrasing
+- reduce absolute certainty with measured hedging where appropriate
+- vary paragraph structure so each section does not read like the same template
+- add limitations or uncertainty if the conclusion feels unnaturally complete
+
+Examples of safer direction changes:
+
+- `本文旨在` -> `本文尝试` or `本研究关注`
+- `具有重要意义` -> `值得关注` or `有一定参考价值`
+- `研究表明` -> `前人研究发现` or `已有文献显示`
+
+Do not invent citations, evidence, or data.
+
+## Style Conversion
+
+Use style conversion only after the base text is readable and natural.
+
+Supported style directions from the source workflow:
+
+- `casual`
+- `zhihu`
+- `xiaohongshu`
+- `wechat`
+- `academic`
+- `literary`
+- `weibo`
+
+When switching style, keep the user's meaning stable and change only tone, structure, and surface wording.
+
+## Output Rules
+
+- Show the main AI-like patterns you found
+- Explain the rewrite strategy in 1-3 short bullets
+- Return the rewritten Chinese text
+- If helpful, include a short note on remaining weak spots
+
+## Source
+
+Adapted from the `voidborne-d/humanize-chinese` project and its CLI/script workflow for Chinese AI-text detection and rewriting.
--- a/plugins/antigravity-awesome-skills-claude/skills/uxui-principles/SKILL.md
+++ b/plugins/antigravity-awesome-skills-claude/skills/uxui-principles/SKILL.md
@@ -0,0 +1,48 @@
+---
+name: uxui-principles
+description: "Evaluate interfaces against 168 research-backed UX/UI principles, detect antipatterns, and inject UX context into AI coding sessions."
+category: design
+risk: safe
+source: community
+date_added: "2026-04-03"
+author: uxuiprinciples
+tags: [ux, ui, design, evaluation, principles, antipatterns, accessibility]
+tools: [claude, cursor, windsurf]
+---
+
+# UX/UI Principles
+
+A collection of 5 agent skills for evaluating interfaces against 168 research-backed UX/UI principles, detecting antipatterns, and injecting UX context into AI-assisted design and coding sessions.
+
+**Source:** https://github.com/uxuiprinciples/agent-skills
+
+## Skills
+
+| Skill | Purpose |
+|-------|---------|
+| `uxui-evaluator` | Evaluate interface descriptions against 168 research-backed principles |
+| `interface-auditor` | Detect UX antipatterns using the uxuiprinciples smell taxonomy |
+| `ai-interface-reviewer` | Audit AI-powered interfaces against 44 AI-era UX principles |
+| `flow-checker` | Check user flows against decision, error, and feedback principles |
+| `vibe-coding-advisor` | Inject UX context into vibe coding sessions before implementation |
+
+## When to Use
+
+- Auditing an existing interface for UX issues
+- Checking if a UI follows research-backed best practices
+- Detecting antipatterns and UX smells in designs
+- Reviewing AI-powered interfaces for trust, transparency, and safety
+- Getting UX guidance before or during implementation
+
+## How It Works
+
+1. Install any skill from the collection
+2. Describe the interface, screen, or flow you want to evaluate
+3. The skill evaluates against the relevant principles and returns structured findings with severity levels and remediation steps
+4. Optionally connect to the uxuiprinciples.com API for enriched output with full citations
+
+## Install
+
+```
+npx skills add uxuiprinciples/agent-skills
+```
--- a/plugins/antigravity-awesome-skills/.codex-plugin/plugin.json
+++ b/plugins/antigravity-awesome-skills/.codex-plugin/plugin.json
@@ -19,7 +19,7 @@
  "skills": "./skills/",
  "interface": {
    "displayName": "Antigravity Awesome Skills",
-    "shortDescription": "1,311 plugin-safe skills for coding, security, product, and ops workflows.",
+    "shortDescription": "1,314 plugin-safe skills for coding, security, product, and ops workflows.",
    "longDescription": "Install a plugin-safe Codex distribution of Antigravity Awesome Skills. Skills that still need hardening or target-specific setup remain available in the repo but are excluded from this plugin.",
    "developerName": "sickn33 and contributors",
    "category": "Productivity",
--- a/plugins/antigravity-awesome-skills/skills/agentphone/SKILL.md
+++ b/plugins/antigravity-awesome-skills/skills/agentphone/SKILL.md
--- a/plugins/antigravity-awesome-skills/skills/humanize-chinese/SKILL.md
+++ b/plugins/antigravity-awesome-skills/skills/humanize-chinese/SKILL.md
@@ -0,0 +1,146 @@
+---
+name: humanize-chinese
+description: Detect and rewrite AI-like Chinese text with a practical workflow for scoring, humanization, academic AIGC reduction, and style conversion. Use when the user asks to 去AI味, 降AIGC, 去除AI痕迹, 论文降重, 知网检测, 维普检测, humanize chinese, detect AI text, or make Chinese text sound more natural.
+category: content
+risk: safe
+source: community
+tags:
+  - chinese
+  - writing
+  - editing
+  - aigc
+  - academic
+  - style-transfer
+date_added: "2026-04-03"
+---
+
+# Humanize Chinese
+
+Use this skill when you need to detect AI-like Chinese writing, rewrite it to feel less synthetic, reduce AIGC signals in academic prose, or convert the text into a more specific Chinese writing style.
+
+## When to Use
+
+- Use when the user says `去AI味`, `降AIGC`, `去除AI痕迹`, `让文字更自然`, `改成人话`, or `降低AI率`
+- Use when the user wants a Chinese text checked for AI-writing patterns or suspicious phrasing
+- Use when the user wants academic-paper-specific AIGC reduction for CNKI, VIP, or Wanfang-style checks
+- Use when the user wants Chinese text rewritten into a different style such as `zhihu`, `xiaohongshu`, `wechat`, `weibo`, `literary`, or `academic`
+
+## Core Workflow
+
+### 1. Detect Before Rewriting
+
+Start by identifying the most obvious AI markers instead of rewriting blindly:
+
+- rigid `first/second/finally` structures
+- mechanical connectors such as `综上所述`, `值得注意的是`, `由此可见`
+- abstract grandiose wording with low information density
+- repeated sentence rhythm and paragraph length
+- academic prose that sounds too complete, too certain, or too template-driven
+
+If the user provides a short sample, call out the suspicious phrases directly before rewriting.
+
+### 2. Rewrite in the Smallest Useful Pass
+
+Prefer targeted rewrites over total regeneration:
+
+- remove formulaic connectors rather than paraphrasing every sentence
+- vary sentence length and paragraph rhythm
+- replace repeated verbs and noun phrases
+- swap abstract summaries for concrete observations where possible
+- keep the original claims, facts, citations, and terminology intact
+
+### 3. Validate the Result
+
+After rewriting, verify that the text:
+
+- still says the same thing
+- sounds less templated
+- uses more natural rhythm
+- does not introduce factual drift
+- stays in the correct register for the target audience
+
+For academic text, preserve a scholarly tone. Do not over-casualize.
+
+## Optional CLI Flow
+
+If the user has a local clone of the source toolkit, these examples are useful:
+
+```bash
+python3 scripts/detect_cn.py text.txt -v
+python3 scripts/compare_cn.py text.txt -a -o clean.txt
+python3 scripts/academic_cn.py paper.txt -o clean.txt --compare
+python3 scripts/style_cn.py text.txt --style xiaohongshu -o out.txt
+```
+
+Use this CLI sequence when available:
+
+1. detect and inspect suspicious sentences
+2. rewrite or compare
+3. rerun detection on the cleaned file
+4. optionally convert into a target style
+
+## Manual Rewrite Playbook
+
+If the scripts are unavailable, use this manual process.
+
+### Common AI Markers
+
+- numbered or mirrored structures that feel too symmetrical
+- filler transitions that add no meaning
+- repeated stock phrases
+- overly even sentence length
+- conclusions that sound final, polished, and risk-free
+
+### Rewrite Moves
+
+- delete weak transitions first
+- collapse repetitive phrases into one stronger sentence
+- split sentences at natural turns instead of forcing long balanced structures
+- merge choppy sentences when they feel robotic
+- replace generic abstractions with concrete wording
+- introduce light variation in cadence so the prose does not march at a constant tempo
+
+## Academic AIGC Reduction
+
+For papers, reports, or theses:
+
+- keep discipline-specific terminology unchanged
+- replace AI-academic stock phrases with more grounded scholarly phrasing
+- reduce absolute certainty with measured hedging where appropriate
+- vary paragraph structure so each section does not read like the same template
+- add limitations or uncertainty if the conclusion feels unnaturally complete
+
+Examples of safer direction changes:
+
+- `本文旨在` -> `本文尝试` or `本研究关注`
+- `具有重要意义` -> `值得关注` or `有一定参考价值`
+- `研究表明` -> `前人研究发现` or `已有文献显示`
+
+Do not invent citations, evidence, or data.
+
+## Style Conversion
+
+Use style conversion only after the base text is readable and natural.
+
+Supported style directions from the source workflow:
+
+- `casual`
+- `zhihu`
+- `xiaohongshu`
+- `wechat`
+- `academic`
+- `literary`
+- `weibo`
+
+When switching style, keep the user's meaning stable and change only tone, structure, and surface wording.
+
+## Output Rules
+
+- Show the main AI-like patterns you found
+- Explain the rewrite strategy in 1-3 short bullets
+- Return the rewritten Chinese text
+- If helpful, include a short note on remaining weak spots
+
+## Source
+
+Adapted from the `voidborne-d/humanize-chinese` project and its CLI/script workflow for Chinese AI-text detection and rewriting.
--- a/plugins/antigravity-awesome-skills/skills/uxui-principles/SKILL.md
+++ b/plugins/antigravity-awesome-skills/skills/uxui-principles/SKILL.md
@@ -0,0 +1,48 @@
+---
+name: uxui-principles
+description: "Evaluate interfaces against 168 research-backed UX/UI principles, detect antipatterns, and inject UX context into AI coding sessions."
+category: design
+risk: safe
+source: community
+date_added: "2026-04-03"
+author: uxuiprinciples
+tags: [ux, ui, design, evaluation, principles, antipatterns, accessibility]
+tools: [claude, cursor, windsurf]
+---
+
+# UX/UI Principles
+
+A collection of 5 agent skills for evaluating interfaces against 168 research-backed UX/UI principles, detecting antipatterns, and injecting UX context into AI-assisted design and coding sessions.
+
+**Source:** https://github.com/uxuiprinciples/agent-skills
+
+## Skills
+
+| Skill | Purpose |
+|-------|---------|
+| `uxui-evaluator` | Evaluate interface descriptions against 168 research-backed principles |
+| `interface-auditor` | Detect UX antipatterns using the uxuiprinciples smell taxonomy |
+| `ai-interface-reviewer` | Audit AI-powered interfaces against 44 AI-era UX principles |
+| `flow-checker` | Check user flows against decision, error, and feedback principles |
+| `vibe-coding-advisor` | Inject UX context into vibe coding sessions before implementation |
+
+## When to Use
+
+- Auditing an existing interface for UX issues
+- Checking if a UI follows research-backed best practices
+- Detecting antipatterns and UX smells in designs
+- Reviewing AI-powered interfaces for trust, transparency, and safety
+- Getting UX guidance before or during implementation
+
+## How It Works
+
+1. Install any skill from the collection
+2. Describe the interface, screen, or flow you want to evaluate
+3. The skill evaluates against the relevant principles and returns structured findings with severity levels and remediation steps
+4. Optionally connect to the uxuiprinciples.com API for enriched output with full citations
+
+## Install
+
+```
+npx skills add uxuiprinciples/agent-skills
+```
--- a/skills/humanize-chinese/SKILL.md
+++ b/skills/humanize-chinese/SKILL.md
@@ -0,0 +1,146 @@
+---
+name: humanize-chinese
+description: Detect and rewrite AI-like Chinese text with a practical workflow for scoring, humanization, academic AIGC reduction, and style conversion. Use when the user asks to 去AI味, 降AIGC, 去除AI痕迹, 论文降重, 知网检测, 维普检测, humanize chinese, detect AI text, or make Chinese text sound more natural.
+category: content
+risk: safe
+source: community
+tags:
+  - chinese
+  - writing
+  - editing
+  - aigc
+  - academic
+  - style-transfer
+date_added: "2026-04-03"
+---
+
+# Humanize Chinese
+
+Use this skill when you need to detect AI-like Chinese writing, rewrite it to feel less synthetic, reduce AIGC signals in academic prose, or convert the text into a more specific Chinese writing style.
+
+## When to Use
+
+- Use when the user says `去AI味`, `降AIGC`, `去除AI痕迹`, `让文字更自然`, `改成人话`, or `降低AI率`
+- Use when the user wants a Chinese text checked for AI-writing patterns or suspicious phrasing
+- Use when the user wants academic-paper-specific AIGC reduction for CNKI, VIP, or Wanfang-style checks
+- Use when the user wants Chinese text rewritten into a different style such as `zhihu`, `xiaohongshu`, `wechat`, `weibo`, `literary`, or `academic`
+
+## Core Workflow
+
+### 1. Detect Before Rewriting
+
+Start by identifying the most obvious AI markers instead of rewriting blindly:
+
+- rigid `first/second/finally` structures
+- mechanical connectors such as `综上所述`, `值得注意的是`, `由此可见`
+- abstract grandiose wording with low information density
+- repeated sentence rhythm and paragraph length
+- academic prose that sounds too complete, too certain, or too template-driven
+
+If the user provides a short sample, call out the suspicious phrases directly before rewriting.
+
+### 2. Rewrite in the Smallest Useful Pass
+
+Prefer targeted rewrites over total regeneration:
+
+- remove formulaic connectors rather than paraphrasing every sentence
+- vary sentence length and paragraph rhythm
+- replace repeated verbs and noun phrases
+- swap abstract summaries for concrete observations where possible
+- keep the original claims, facts, citations, and terminology intact
+
+### 3. Validate the Result
+
+After rewriting, verify that the text:
+
+- still says the same thing
+- sounds less templated
+- uses more natural rhythm
+- does not introduce factual drift
+- stays in the correct register for the target audience
+
+For academic text, preserve a scholarly tone. Do not over-casualize.
+
+## Optional CLI Flow
+
+If the user has a local clone of the source toolkit, these examples are useful:
+
+```bash
+python3 scripts/detect_cn.py text.txt -v
+python3 scripts/compare_cn.py text.txt -a -o clean.txt
+python3 scripts/academic_cn.py paper.txt -o clean.txt --compare
+python3 scripts/style_cn.py text.txt --style xiaohongshu -o out.txt
+```
+
+Use this CLI sequence when available:
+
+1. detect and inspect suspicious sentences
+2. rewrite or compare
+3. rerun detection on the cleaned file
+4. optionally convert into a target style
+
+## Manual Rewrite Playbook
+
+If the scripts are unavailable, use this manual process.
+
+### Common AI Markers
+
+- numbered or mirrored structures that feel too symmetrical
+- filler transitions that add no meaning
+- repeated stock phrases
+- overly even sentence length
+- conclusions that sound final, polished, and risk-free
+
+### Rewrite Moves
+
+- delete weak transitions first
+- collapse repetitive phrases into one stronger sentence
+- split sentences at natural turns instead of forcing long balanced structures
+- merge choppy sentences when they feel robotic
+- replace generic abstractions with concrete wording
+- introduce light variation in cadence so the prose does not march at a constant tempo
+
+## Academic AIGC Reduction
+
+For papers, reports, or theses:
+
+- keep discipline-specific terminology unchanged
+- replace AI-academic stock phrases with more grounded scholarly phrasing
+- reduce absolute certainty with measured hedging where appropriate
+- vary paragraph structure so each section does not read like the same template
+- add limitations or uncertainty if the conclusion feels unnaturally complete
+
+Examples of safer direction changes:
+
+- `本文旨在` -> `本文尝试` or `本研究关注`
+- `具有重要意义` -> `值得关注` or `有一定参考价值`
+- `研究表明` -> `前人研究发现` or `已有文献显示`
+
+Do not invent citations, evidence, or data.
+
+## Style Conversion
+
+Use style conversion only after the base text is readable and natural.
+
+Supported style directions from the source workflow:
+
+- `casual`
+- `zhihu`
+- `xiaohongshu`
+- `wechat`
+- `academic`
+- `literary`
+- `weibo`
+
+When switching style, keep the user's meaning stable and change only tone, structure, and surface wording.
+
+## Output Rules
+
+- Show the main AI-like patterns you found
+- Explain the rewrite strategy in 1-3 short bullets
+- Return the rewritten Chinese text
+- If helpful, include a short note on remaining weak spots
+
+## Source
+
+Adapted from the `voidborne-d/humanize-chinese` project and its CLI/script workflow for Chinese AI-text detection and rewriting.
--- a/skills_index.json
+++ b/skills_index.json
@@ -707,6 +707,28 @@
      "reasons": []
    }
  },
+  {
+    "id": "agentphone",
+    "path": "skills/agentphone",
+    "category": "ai-ml",
+    "name": "agentphone",
+    "description": "Build AI phone agents with AgentPhone API. Use when the user wants to make phone calls, send/receive SMS, manage phone numbers, create voice agents, set up webhooks, or check usage \u2014 anything related to telephony, phone numbers, or voice AI.",
+    "risk": "unknown",
+    "source": "unknown",
+    "date_added": null,
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    }
+  },
  {
    "id": "agents-md",
    "path": "skills/agents-md",
@@ -14903,6 +14925,28 @@
      "reasons": []
    }
  },
+  {
+    "id": "humanize-chinese",
+    "path": "skills/humanize-chinese",
+    "category": "content",
+    "name": "humanize-chinese",
+    "description": "Detect and rewrite AI-like Chinese text with a practical workflow for scoring, humanization, academic AIGC reduction, and style conversion. Use when the user asks to \u53bbAI\u5473, \u964dAIGC, \u53bb\u9664AI\u75d5\u8ff9, \u8bba\u6587\u964d\u91cd, \u77e5\u7f51\u68c0\u6d4b, \u7ef4\u666e\u68c0\u6d4b, humanize chinese, detect AI text, or make Chinese text sound more natural.",
+    "risk": "safe",
+    "source": "community",
+    "date_added": "2026-04-03",
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    }
+  },
  {
    "id": "hybrid-cloud-architect",
    "path": "skills/hybrid-cloud-architect",
@@ -27825,6 +27869,28 @@
      "reasons": []
    }
  },
+  {
+    "id": "uxui-principles",
+    "path": "skills/uxui-principles",
+    "category": "design",
+    "name": "uxui-principles",
+    "description": "Evaluate interfaces against 168 research-backed UX/UI principles, detect antipatterns, and inject UX context into AI coding sessions.",
+    "risk": "safe",
+    "source": "community",
+    "date_added": "2026-04-03",
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    }
+  },
  {
    "id": "variant-analysis",
    "path": "skills/variant-analysis",
--- a/tools/bin/install.js
+++ b/tools/bin/install.js
@@ -5,6 +5,7 @@ const path = require("path");
 const fs = require("fs");
 const os = require("os");
 const { resolveSafeRealPath } = require("../lib/symlink-safety");
+const { listSkillIdsRecursive, readSkill } = require("../lib/skill-utils");

 const REPO = "https://github.com/sickn33/antigravity-awesome-skills.git";
 const HOME = process.env.HOME || process.env.USERPROFILE || "";
@@ -21,6 +22,9 @@ function parseArgs() {
  let pathArg = null;
  let versionArg = null;
  let tagArg = null;
+  let riskArg = null;
+  let categoryArg = null;
+  let tagsArg = null;
  let cursor = false,
    claude = false,
    gemini = false,
@@ -42,6 +46,18 @@ function parseArgs() {
      tagArg = a[++i];
      continue;
    }
+    if (a[i] === "--risk" && a[i + 1]) {
+      riskArg = a[++i];
+      continue;
+    }
+    if (a[i] === "--category" && a[i + 1]) {
+      categoryArg = a[++i];
+      continue;
+    }
+    if (a[i] === "--tags" && a[i + 1]) {
+      tagsArg = a[++i];
+      continue;
+    }
    if (a[i] === "--cursor") {
      cursor = true;
      continue;
@@ -73,6 +89,9 @@ function parseArgs() {
    pathArg,
    versionArg,
    tagArg,
+    riskArg,
+    categoryArg,
+    tagsArg,
    cursor,
    claude,
    gemini,
@@ -131,6 +150,9 @@ Options:
  --kiro         Install to ~/.kiro/skills (Kiro CLI)
  --antigravity  Install to ~/.gemini/antigravity/skills (Antigravity)
  --path <dir>   Install to <dir> (default: ~/.gemini/antigravity/skills)
+  --risk <csv>     Install only skills matching these risk labels
+  --category <csv> Install only skills matching these categories
+  --tags <csv>     Install only skills matching these tags
  --version <ver>  Clone tag v<ver> (e.g. 4.6.0 -> v4.6.0)
  --tag <tag>      Clone this tag or branch (e.g. v4.6.0)

@@ -139,12 +161,99 @@ Examples:
  npx antigravity-awesome-skills --cursor
  npx antigravity-awesome-skills --kiro
  npx antigravity-awesome-skills --antigravity
+  npx antigravity-awesome-skills --path .agents/skills --category development,backend --risk safe,none
+  npx antigravity-awesome-skills --path .agents/skills --tags debugging,typescript-legacy-
  npx antigravity-awesome-skills --version 4.6.0
  npx antigravity-awesome-skills --path ./my-skills
  npx antigravity-awesome-skills --claude --codex    Install to multiple targets
 `);
 }

+function normalizeFilterValue(value) {
+  return typeof value === "string" ? value.trim().toLowerCase() : "";
+}
+
+function uniqueValues(values) {
+  return [...new Set(values.filter(Boolean))];
+}
+
+function parseSelectorArg(raw) {
+  const include = [];
+  const exclude = [];
+
+  if (typeof raw !== "string" || !raw.trim()) {
+    return { include, exclude };
+  }
+
+  for (const token of raw.split(",")) {
+    const normalized = normalizeFilterValue(token);
+    if (!normalized) continue;
+    if (normalized.endsWith("-") && normalized.length > 1) {
+      exclude.push(normalized.slice(0, -1));
+      continue;
+    }
+    include.push(normalized);
+  }
+
+  const excludeValues = uniqueValues(exclude);
+  return {
+    include: uniqueValues(include).filter((value) => !excludeValues.includes(value)),
+    exclude: excludeValues,
+  };
+}
+
+function hasActiveSelector(selector) {
+  return selector.include.length > 0 || selector.exclude.length > 0;
+}
+
+function buildInstallSelectors(opts) {
+  return {
+    risk: parseSelectorArg(opts.riskArg),
+    category: parseSelectorArg(opts.categoryArg),
+    tags: parseSelectorArg(opts.tagsArg),
+  };
+}
+
+function hasInstallSelectors(selectors) {
+  return Object.values(selectors).some(hasActiveSelector);
+}
+
+function matchesScalarSelector(value, selector) {
+  const normalized = normalizeFilterValue(value);
+  if (normalized && selector.exclude.includes(normalized)) {
+    return false;
+  }
+  if (selector.include.length === 0) {
+    return true;
+  }
+  if (!normalized) {
+    return false;
+  }
+  return selector.include.includes(normalized);
+}
+
+function matchesArraySelector(values, selector) {
+  const normalizedValues = uniqueValues(
+    (Array.isArray(values) ? values : []).map((value) => normalizeFilterValue(value)),
+  );
+
+  if (normalizedValues.some((value) => selector.exclude.includes(value))) {
+    return false;
+  }
+  if (selector.include.length === 0) {
+    return true;
+  }
+  return normalizedValues.some((value) => selector.include.includes(value));
+}
+
+function matchesInstallSelectors(skill, selectors) {
+  return (
+    matchesScalarSelector(skill.risk, selectors.risk) &&
+    matchesScalarSelector(skill.category, selectors.category) &&
+    matchesArraySelector(skill.tags, selectors.tags)
+  );
+}
+
 function copyRecursiveSync(src, dest, rootDir = src, skipGit = true) {
  const stats = fs.lstatSync(src);
  const resolvedSource = stats.isSymbolicLink()
@@ -171,13 +280,24 @@ function copyRecursiveSync(src, dest, rootDir = src, skipGit = true) {
 }

 /** Copy contents of repo's skills/ into target so each skill is target/skill-name/ (for Claude Code etc.). */
-function getInstallEntries(tempDir) {
+function getInstallEntries(tempDir, selectors = buildInstallSelectors({})) {
  const repoSkills = path.join(tempDir, "skills");
  if (!fs.existsSync(repoSkills)) {
    console.error("Cloned repo has no skills/ directory.");
    process.exit(1);
  }
-  const entries = fs.readdirSync(repoSkills);
+
+  const skillEntries = listSkillIdsRecursive(repoSkills);
+  const filteredEntries = hasInstallSelectors(selectors)
+    ? skillEntries.filter((skillId) => matchesInstallSelectors(readSkill(repoSkills, skillId), selectors))
+    : skillEntries;
+
+  if (hasInstallSelectors(selectors) && filteredEntries.length === 0) {
+    console.error("No skills matched the requested --risk/--category/--tags filters.");
+    process.exit(1);
+  }
+
+  const entries = [...filteredEntries];
  if (fs.existsSync(path.join(tempDir, "docs"))) {
    entries.push("docs");
  }
@@ -295,7 +415,7 @@ function buildCloneArgs(repo, tempDir, ref = null) {
  return args;
 }

-function installForTarget(tempDir, target) {
+function installForTarget(tempDir, target, selectors = buildInstallSelectors({})) {
  if (fs.existsSync(target.path)) {
    ensureTargetIsDirectory(target.path);
    const gitDir = path.join(target.path, ".git");
@@ -334,7 +454,7 @@ function installForTarget(tempDir, target) {
    fs.mkdirSync(target.path, { recursive: true });
  }

-  const installEntries = getInstallEntries(tempDir);
+  const installEntries = getInstallEntries(tempDir, selectors);
  const previousEntries = readInstallManifest(target.path);
  pruneRemovedEntries(target.path, previousEntries, installEntries);
  installSkillsIntoTarget(tempDir, target.path, installEntries);
@@ -342,7 +462,12 @@ function installForTarget(tempDir, target) {
  console.log(`  ✓ Installed to ${target.path}`);
 }

-function getPostInstallMessages(targets) {
+function isOpenCodeStylePath(targetPath) {
+  const normalizedPath = path.normalize(targetPath);
+  return normalizedPath.endsWith(path.join(".agents", "skills"));
+}
+
+function getPostInstallMessages(targets, selectors = buildInstallSelectors({})) {
  const messages = [
    "Pick a bundle in docs/users/bundles.md and use @skill-name in your AI assistant.",
  ];
@@ -356,12 +481,24 @@ function getPostInstallMessages(targets) {
    );
  }

+  if (targets.some((target) => isOpenCodeStylePath(target.path))) {
+    const baseMessage =
+      "For OpenCode or other .agents/skills installs, prefer a reduced install with --risk, --category, or --tags to avoid context overload.";
+    messages.push(baseMessage);
+    if (!hasInstallSelectors(selectors)) {
+      messages.push(
+        "Example: npx antigravity-awesome-skills --path .agents/skills --category development,backend --risk safe,none",
+      );
+    }
+  }
+
  return messages;
 }

 function main() {
  const opts = parseArgs();
  const { tagArg, versionArg } = opts;
+  const selectors = buildInstallSelectors(opts);
  const ref =
    tagArg ||
    (versionArg
@@ -396,10 +533,10 @@ function main() {
    console.log(`\nInstalling for ${targets.length} target(s):`);
    for (const target of targets) {
      console.log(`\n${target.name}:`);
-      installForTarget(tempDir, target);
+      installForTarget(tempDir, target, selectors);
    }

-    for (const message of getPostInstallMessages(targets)) {
+    for (const message of getPostInstallMessages(targets, selectors)) {
      console.log(`\n${message}`);
    }
  } finally {
@@ -425,10 +562,14 @@ module.exports = {
  copyRecursiveSync,
  getPostInstallMessages,
  buildCloneArgs,
+  buildInstallSelectors,
  getInstallEntries,
  installSkillsIntoTarget,
  installForTarget,
+  isOpenCodeStylePath,
  main,
+  matchesInstallSelectors,
+  parseSelectorArg,
  pruneRemovedEntries,
  readInstallManifest,
  writeInstallManifest,
--- a/tools/lib/skill-utils.js
+++ b/tools/lib/skill-utils.js
@@ -137,28 +137,34 @@ function readSkill(skillDir, skillId) {
  if (Array.isArray(data.tags)) {
    tags = data.tags.map(tag => String(tag).trim());
  } else if (typeof data.tags === 'string' && data.tags.trim()) {
-    const parts = data.tags.includes(',')
-      ? data.tags.split(',')
-      : data.tags.split(/\s+/);
+    const inlineTags = parseInlineList(data.tags);
+    const parts = inlineTags.length > 0
+      ? inlineTags
+      : (data.tags.includes(',') ? data.tags.split(',') : data.tags.split(/\s+/));
    tags = parts.map(tag => tag.trim());
  } else if (isPlainObject(data.metadata) && data.metadata.tags) {
    const rawTags = data.metadata.tags;
    if (Array.isArray(rawTags)) {
      tags = rawTags.map(tag => String(tag).trim());
    } else if (typeof rawTags === 'string' && rawTags.trim()) {
-      const parts = rawTags.includes(',')
-        ? rawTags.split(',')
-        : rawTags.split(/\s+/);
+      const inlineTags = parseInlineList(rawTags);
+      const parts = inlineTags.length > 0
+        ? inlineTags
+        : (rawTags.includes(',') ? rawTags.split(',') : rawTags.split(/\s+/));
      tags = parts.map(tag => tag.trim());
    }
  }

  tags = tags.filter(Boolean);
+  const category = typeof data.category === 'string' ? data.category.trim() : '';
+  const risk = typeof data.risk === 'string' ? data.risk.trim() : '';

  return {
    id: skillId,
    name,
    description,
+    category,
+    risk,
    tags,
    path: skillPath,
    content,
--- a/tools/scripts/tests/installer_filters.test.js
+++ b/tools/scripts/tests/installer_filters.test.js
@@ -0,0 +1,146 @@
+const assert = require("assert");
+const fs = require("fs");
+const os = require("os");
+const path = require("path");
+
+const installer = require(path.resolve(__dirname, "..", "..", "bin", "install.js"));
+
+function withTempDir(fn) {
+  const dir = fs.mkdtempSync(path.join(os.tmpdir(), "installer-filters-"));
+  try {
+    fn(dir);
+  } finally {
+    fs.rmSync(dir, { recursive: true, force: true });
+  }
+}
+
+function writeSkill(repoRoot, skillPath, frontmatter) {
+  const skillDir = path.join(repoRoot, "skills", skillPath);
+  fs.mkdirSync(skillDir, { recursive: true });
+  fs.writeFileSync(
+    path.join(skillDir, "SKILL.md"),
+    `---\n${frontmatter}\n---\n\n# ${skillPath}\n`,
+    "utf8",
+  );
+}
+
+assert.deepStrictEqual(
+  installer.parseSelectorArg("safe,critical,offensive-"),
+  { include: ["safe", "critical"], exclude: ["offensive"] },
+  "parseSelectorArg should split CSV values and treat suffix - as exclude",
+);
+
+assert.deepStrictEqual(
+  installer.parseSelectorArg("safe,safe-,none"),
+  { include: ["none"], exclude: ["safe"] },
+  "parseSelectorArg should let excludes win over duplicate includes",
+);
+
+assert.strictEqual(
+  installer.isOpenCodeStylePath(path.join("/tmp", ".agents", "skills")),
+  true,
+  "OpenCode-style paths should be detected from .agents/skills",
+);
+
+assert.strictEqual(
+  installer.isOpenCodeStylePath(path.join("/tmp", ".codex", "skills")),
+  false,
+  "non-OpenCode paths should not trigger the .agents/skills guidance",
+);
+
+withTempDir((root) => {
+  const repoRoot = path.join(root, "repo");
+  fs.mkdirSync(path.join(repoRoot, "skills"), { recursive: true });
+  fs.mkdirSync(path.join(repoRoot, "docs"), { recursive: true });
+
+  writeSkill(
+    repoRoot,
+    "safe-debugger",
+    'name: safe-debugger\ncategory: development\nrisk: safe\ntags: [debugging, typescript]',
+  );
+  writeSkill(
+    repoRoot,
+    "offensive-tool",
+    'name: offensive-tool\ncategory: security\nrisk: offensive\ntags: [pentest, red-team]',
+  );
+  writeSkill(
+    repoRoot,
+    path.join("nested", "metadata-tags"),
+    'name: metadata-tags\ncategory: backend\nrisk: none\nmetadata:\n  tags: "api,saas"',
+  );
+
+  assert.deepStrictEqual(
+    installer.getInstallEntries(repoRoot, installer.buildInstallSelectors({})),
+    ["nested/metadata-tags", "offensive-tool", "safe-debugger", "docs"],
+    "full installs should return recursive skill paths plus docs",
+  );
+
+  assert.deepStrictEqual(
+    installer.getInstallEntries(
+      repoRoot,
+      installer.buildInstallSelectors({
+        riskArg: "safe,none",
+        categoryArg: "development,backend",
+        tagsArg: "typescript,saas",
+      }),
+    ),
+    ["nested/metadata-tags", "safe-debugger", "docs"],
+    "filters should AND across flags and keep docs when skills match",
+  );
+
+  assert.deepStrictEqual(
+    installer.getInstallEntries(
+      repoRoot,
+      installer.buildInstallSelectors({
+        tagsArg: "pentest-",
+      }),
+    ),
+    ["nested/metadata-tags", "safe-debugger", "docs"],
+    "exclude-only tag filters should remove matching skills",
+  );
+
+  assert.strictEqual(
+    installer.matchesInstallSelectors(
+      { risk: "safe", category: "development", tags: ["debugging", "typescript"] },
+      installer.buildInstallSelectors({
+        riskArg: "safe",
+        categoryArg: "development",
+        tagsArg: "typescript",
+      }),
+    ),
+    true,
+    "skills should match when all selector dimensions pass",
+  );
+
+  assert.strictEqual(
+    installer.matchesInstallSelectors(
+      { risk: "", category: "development", tags: ["debugging"] },
+      installer.buildInstallSelectors({
+        riskArg: "safe",
+      }),
+    ),
+    false,
+    "missing scalar metadata should not satisfy positive selectors",
+  );
+
+  const openCodeMessages = installer.getPostInstallMessages(
+    [{ name: "Custom", path: path.join(root, ".agents", "skills") }],
+    installer.buildInstallSelectors({}),
+  );
+
+  assert.ok(
+    openCodeMessages.some((message) => message.includes("reduced install")),
+    "OpenCode-style paths should get reduced-install guidance",
+  );
+
+  const filteredOpenCodeMessages = installer.getPostInstallMessages(
+    [{ name: "Custom", path: path.join(root, ".agents", "skills") }],
+    installer.buildInstallSelectors({ categoryArg: "development" }),
+  );
+
+  assert.strictEqual(
+    filteredOpenCodeMessages.some((message) => message.includes("Example:")),
+    false,
+    "OpenCode guidance should skip the example once selectors are already active",
+  );
+});
--- a/tools/scripts/tests/installer_update_sync.test.js
+++ b/tools/scripts/tests/installer_update_sync.test.js
@@ -14,6 +14,8 @@ function writeSkill(repoRoot, skillName, content = "# Skill\n") {

 function createFakeRepo(rootDir, skills) {
  fs.mkdirSync(path.join(rootDir, "skills"), { recursive: true });
+  fs.mkdirSync(path.join(rootDir, "docs"), { recursive: true });
+  fs.writeFileSync(path.join(rootDir, "docs", "README.md"), "# Docs\n", "utf8");
  for (const skillName of skills) {
    writeSkill(rootDir, skillName, `# ${skillName}\n`);
  }
@@ -35,22 +37,47 @@ try {

  createFakeRepo(repoV1, ["skill-a", "skill-b"]);
  createFakeRepo(repoV2, ["skill-a"]);
+  writeSkill(
+    repoV1,
+    path.join("nested", "skill-c"),
+    "---\nname: nested-skill-c\ncategory: backend\nrisk: safe\ntags: [api]\n---\n",
+  );
+  writeSkill(
+    repoV2,
+    "skill-a",
+    "---\nname: skill-a\ncategory: development\nrisk: safe\ntags: [debugging]\n---\n",
+  );
+  writeSkill(
+    repoV2,
+    path.join("nested", "skill-c"),
+    "---\nname: nested-skill-c\ncategory: backend\nrisk: safe\ntags: [api]\n---\n",
+  );

  installer.installForTarget(repoV1, { name: "Test", path: targetDir });
  assert.ok(fs.existsSync(path.join(targetDir, "skill-a", "SKILL.md")));
  assert.ok(fs.existsSync(path.join(targetDir, "skill-b", "SKILL.md")));
+  assert.ok(fs.existsSync(path.join(targetDir, "nested", "skill-c", "SKILL.md")));

-  installer.installForTarget(repoV2, { name: "Test", path: targetDir });
-  assert.ok(fs.existsSync(path.join(targetDir, "skill-a", "SKILL.md")));
+  installer.installForTarget(
+    repoV2,
+    { name: "Test", path: targetDir },
+    installer.buildInstallSelectors({ categoryArg: "backend" }),
+  );
+  assert.strictEqual(
+    fs.existsSync(path.join(targetDir, "skill-a")),
+    false,
+    "non-matching top-level skills should be pruned during filtered updates",
+  );
  assert.strictEqual(
    fs.existsSync(path.join(targetDir, "skill-b")),
    false,
-    "stale managed skill should be pruned during updates",
+    "stale managed top-level skills should be pruned during updates",
  );
+  assert.ok(fs.existsSync(path.join(targetDir, "nested", "skill-c", "SKILL.md")));
  assert.deepStrictEqual(
    readManifestEntries(targetDir),
-    ["skill-a"],
-    "install manifest should mirror the latest installed entries",
+    ["docs", "nested/skill-c"],
+    "install manifest should mirror the latest filtered install entries",
  );

  const badTargetPath = path.join(tmpRoot, "bad-target");
--- a/tools/scripts/tests/run-test-suite.js
+++ b/tools/scripts/tests/run-test-suite.js
@@ -19,6 +19,7 @@ const LOCAL_TEST_COMMANDS = [
    [path.join(TOOL_SCRIPTS, "run-python.js"), path.join(TOOL_TESTS, "test_editorial_bundles.py")],
    [path.join(TOOL_SCRIPTS, "run-python.js"), path.join(TOOL_TESTS, "test_plugin_compatibility.py")],
    [path.join(TOOL_TESTS, "installer_antigravity_guidance.test.js")],
+    [path.join(TOOL_TESTS, "installer_filters.test.js")],
    [path.join(TOOL_TESTS, "installer_update_sync.test.js")],
    [path.join(TOOL_TESTS, "jetski_gemini_loader.test.cjs")],
    [path.join(TOOL_TESTS, "npm_package_contents.test.js")],
--- a/tools/scripts/tests/skill_utils_security.test.js
+++ b/tools/scripts/tests/skill_utils_security.test.js
@@ -3,7 +3,7 @@ const fs = require("fs");
 const os = require("os");
 const path = require("path");

-const { listSkillIds, listSkillIdsRecursive } = require("../../lib/skill-utils");
+const { listSkillIds, listSkillIdsRecursive, readSkill } = require("../../lib/skill-utils");

 function withTempDir(fn) {
  const dir = fs.mkdtempSync(path.join(os.tmpdir(), "skill-utils-security-"));
@@ -110,3 +110,33 @@ withTempDir((root) => {
    fs.lstatSync = originalLstatSync;
  }
 });
+
+withTempDir((root) => {
+  const skillsDir = path.join(root, "skills");
+  const skillDir = path.join(skillsDir, "metadata-skill");
+  fs.mkdirSync(skillDir, { recursive: true });
+  fs.writeFileSync(
+    path.join(skillDir, "SKILL.md"),
+    `---
+name: metadata-skill
+category: backend
+risk: safe
+metadata:
+  tags: "[api, saas]"
+---
+
+# metadata-skill
+`,
+    "utf8",
+  );
+
+  const skill = readSkill(skillsDir, "metadata-skill");
+
+  assert.strictEqual(skill.category, "backend", "readSkill should expose category metadata");
+  assert.strictEqual(skill.risk, "safe", "readSkill should expose risk metadata");
+  assert.deepStrictEqual(
+    skill.tags,
+    ["api", "saas"],
+    "readSkill should normalize inline tag lists from metadata.tags",
+  );
+});