fix(skills): Restore actionable skill descriptions

CATALOG.md

@@ -85,7 +85,7 @@ Total skills: 1273
 | `tailwind-patterns` | Tailwind CSS v4 principles. CSS-first configuration, container queries, modern patterns, design token architecture. | tailwind | tailwind, css, v4, principles, first, configuration, container, queries, token, architecture |
 | `testing-patterns` | Jest testing patterns, factory functions, mocking strategies, and TDD workflow. Use when writing unit tests, creating test factories, or following TDD red-gr... |  | testing, jest, factory, functions, mocking, tdd, writing, unit, tests, creating, test, factories |
 | `threejs-loaders` | Three.js asset loading - GLTF, textures, images, models, async patterns. Use when loading 3D models, textures, HDR environments, or managing loading progress. | threejs, loaders | threejs, loaders, three, js, asset, loading, gltf, textures, images, models, async, 3d |
-| `tool-design` | Build tools that agents can use effectively, including architectural reduction patterns |  | agents, effectively, including, architectural, reduction |
+| `tool-design` | Build tools that agents can use effectively, including architectural reduction patterns. Use when creating new tools for agent systems, debugging tool-relate... |  | agents, effectively, including, architectural, reduction, creating, new, agent, debugging, related, failures, misuse |
 | `uncle-bob-craft` | Use when performing code review, writing or refactoring code, or discussing architecture; complements clean-code and does not replace project linter/formatter. | clean-code, clean-architecture, solid, code-review, craftsmanship, uncle-bob | clean-code, clean-architecture, solid, code-review, craftsmanship, uncle-bob, uncle, bob, craft, performing, code, review |
 | `unreal-engine-cpp-pro` | Expert guide for Unreal Engine 5.x C++ development, covering UObject hygiene, performance patterns, and best practices. | unreal, engine, cpp | unreal, engine, cpp, pro, development, covering, uobject, hygiene, performance |
 | `wcag-audit-patterns` | Comprehensive guide to auditing web content against WCAG 2.2 guidelines with actionable remediation strategies. | wcag, audit | wcag, audit, auditing, web, content, against, guidelines, actionable, remediation |
@@ -159,7 +159,7 @@ Total skills: 1273
 | `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 (233)
+## data-ai (235)
 
 | Skill | Description | Tags | Triggers |
 | --- | --- | --- | --- |
@@ -245,6 +245,7 @@ Total skills: 1273
 | `azure-search-documents-py` | Azure AI Search SDK for Python. Use for vector search, hybrid search, semantic ranking, indexing, and skillsets. | azure, search, documents, py | azure, search, documents, py, ai, sdk, python, vector, hybrid, semantic, ranking, indexing |
 | `azure-search-documents-ts` | Build search applications with vector, hybrid, and semantic search capabilities. | azure, search, documents, ts | azure, search, documents, ts, applications, vector, hybrid, semantic, capabilities |
 | `azure-storage-file-datalake-py` | Azure Data Lake Storage Gen2 SDK for Python. Use for hierarchical file systems, big data analytics, and file/directory operations. | azure, storage, file, datalake, py | azure, storage, file, datalake, py, data, lake, gen2, sdk, python, hierarchical, big |
+| `backend-dev-guidelines` | You are a senior backend engineer operating production-grade services under strict architectural and reliability constraints. Use when routes, controllers, s... | backend, dev, guidelines | backend, dev, guidelines, senior, engineer, operating, grade, under, strict, architectural, reliability, constraints |
 | `bdi-mental-states` | This skill should be used when the user asks to "model agent mental states", "implement BDI architecture", "create belief-desire-intention models", "transfor... | bdi, mental, states | bdi, mental, states, skill, should, used, user, asks, model, agent, architecture, belief |
 | `beautiful-prose` | A hard-edged writing style contract for timeless, forceful English prose without modern AI tics. Use when users ask for prose or rewrites that must be clean,... | beautiful, prose | beautiful, prose, hard, edged, writing, style, contract, timeless, forceful, english, without, ai |
 | `behavioral-modes` | AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type. | behavioral, modes | behavioral, modes, ai, operational, brainstorm, debug, review, teach, ship, orchestrate, adapt, behavior |
@@ -258,7 +259,7 @@ Total skills: 1273
 | `claude-d3js-skill` | This skill provides guidance for creating sophisticated, interactive data visualisations using d3.js. | claude, d3js, skill | claude, d3js, skill, provides, guidance, creating, sophisticated, interactive, data, visualisations, d3, js |
 | `code-documentation-doc-generate` | You are a documentation expert specializing in creating comprehensive, maintainable documentation from code. Generate API docs, architecture diagrams, user g... | code, documentation, doc, generate | code, documentation, doc, generate, specializing, creating, maintainable, api, docs, architecture, diagrams, user |
 | `code-reviewer` | Elite code review expert specializing in modern AI-powered code | code | code, reviewer, elite, review, specializing, ai, powered |
-| `codex-review` | Professional code review with auto CHANGELOG generation, integrated with Codex AI | codex | codex, review, professional, code, auto, changelog, generation, integrated, ai |
+| `codex-review` | Professional code review with auto CHANGELOG generation, integrated with Codex AI. Use when you want professional code review before commits, you need automa... | codex | codex, review, professional, code, auto, changelog, generation, integrated, ai, want, before, commits |
 | `constant-time-analysis` | Analyze cryptographic code to detect operations that leak secret data through execution timing variations. | constant, time | constant, time, analysis, analyze, cryptographic, code, detect, operations, leak, secret, data, through |
 | `content-marketer` | Elite content marketing strategist specializing in AI-powered content creation, omnichannel distribution, SEO optimization, and data-driven performance marke... | content, marketer | content, marketer, elite, marketing, strategist, specializing, ai, powered, creation, omnichannel, distribution, seo |
 | `context-driven-development` | Guide for implementing and maintaining context as a managed artifact alongside code, enabling consistent AI interactions and team alignment through structure... | driven | driven, context, development, implementing, maintaining, managed, artifact, alongside, code, enabling, consistent, ai |
@@ -296,6 +297,7 @@ Total skills: 1273
 | `fp-pipe-ref` | Quick reference for pipe and flow. Use when user needs to chain functions, compose operations, or build data pipelines in fp-ts. | fp-ts, pipe, flow, composition, quick-reference | fp-ts, pipe, flow, composition, quick-reference, fp, ref, quick, reference, user, chain, functions |
 | `fp-react` | Practical patterns for using fp-ts with React - hooks, state, forms, data fetching. Works with React 18/19, Next.js 14/15. | fp-ts, react, typescript, hooks, state-management, forms, data-fetching, remote-data, react-19, next-js | fp-ts, react, typescript, hooks, state-management, forms, data-fetching, remote-data, react-19, next-js, fp, practical |
 | `fp-ts-react` | Practical patterns for using fp-ts with React - hooks, state, forms, data fetching. Use when building React apps with functional programming patterns. Works ... | fp, ts, react | fp, ts, react, practical, hooks, state, forms, data, fetching, building, apps, functional |
+| `frontend-dev-guidelines` | You are a senior frontend engineer operating under strict architectural and performance standards. Use when creating components or pages, adding new features... | frontend, dev, guidelines | frontend, dev, guidelines, senior, engineer, operating, under, strict, architectural, performance, standards, creating |
 | `frontend-ui-dark-ts` | A modern dark-themed React UI system using Tailwind CSS and Framer Motion. Designed for dashboards, admin panels, and data-rich applications with glassmorphi... | frontend, ui, dark, ts | frontend, ui, dark, ts, themed, react, tailwind, css, framer, motion, designed, dashboards |
 | `gemini-api-dev` | The Gemini API provides access to Google's most advanced AI models. Key capabilities include: | gemini, api, dev | gemini, api, dev, provides, access, google, most, ai, models, key, capabilities, include |
 | `geo-fundamentals` | Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity). | geo, fundamentals | geo, fundamentals, generative, engine, optimization, ai, search, engines, chatgpt, claude, perplexity |
@@ -350,6 +352,7 @@ Total skills: 1273
 | `pydantic-ai` | Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support. | pydantic-ai, ai-agents, llm, openai, anthropic, gemini, tool-use, structured-output, python | pydantic-ai, ai-agents, llm, openai, anthropic, gemini, tool-use, structured-output, python, pydantic, ai, agents |
 | `rag-engineer` | I bridge the gap between raw documents and LLM understanding. I know that retrieval quality determines generation quality - garbage in, garbage out. I obsess... | rag | rag, engineer, bridge, gap, between, raw, documents, llm, understanding, know, retrieval, quality |
 | `rag-implementation` | RAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and retrieval optimiza... | rag | rag, retrieval, augmented, generation, covering, embedding, selection, vector, database, setup, chunking, optimization |
+| `react-best-practices` | Comprehensive performance optimization guide for React and Next.js applications, maintained by Vercel. Use when writing new React components or Next.js pages... | react, best, practices | react, best, practices, performance, optimization, next, js, applications, maintained, vercel, writing, new |
 | `react-ui-patterns` | Modern React UI patterns for loading states, error handling, and data fetching. Use when building UI components, handling async data, or managing UI states. | react, ui | react, ui, loading, states, error, handling, data, fetching, building, components, async, managing |
 | `recallmax` | FREE — God-tier long-context memory for AI agents. Injects 500K-1M clean tokens, auto-summarizes with tone/intent preservation, compresses 14-turn history in... | memory, context, rag, summarization, compression, long-context, agent-infrastructure | memory, context, rag, summarization, compression, long-context, agent-infrastructure, recallmax, free, god, tier, long |
 | `referral-program` | You are an expert in viral growth and referral marketing with access to referral program data and third-party tools. Your goal is to help design and optimize... | referral, program | referral, program, viral, growth, marketing, access, data, third, party, goal, optimize, programs |
@@ -377,7 +380,6 @@ Total skills: 1273
 | `tanstack-query-expert` | Expert in TanStack Query (React Query) — asynchronous state management. Covers data fetching, stale time configuration, mutations, optimistic updates, and Ne... | tanstack, query | tanstack, query, react, asynchronous, state, covers, data, fetching, stale, time, configuration, mutations |
 | `team-collaboration-standup-notes` | You are an expert team communication specialist focused on async-first standup practices, AI-assisted note generation from commit history, and effective remo... | team, collaboration, standup, notes | team, collaboration, standup, notes, communication, async, first, ai, assisted, note, generation, commit |
 | `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 |
-| `ui-ux-pro-max` | Comprehensive design guide for web and mobile applications. Contains 50+ styles, 97 color palettes, 57 font pairings, 99 UX guidelines, and 25 chart types ac... | ui, ux, max | ui, ux, max, pro, web, mobile, applications, contains, 50, styles, 97, color |
 | `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 |
 | `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 |
@@ -397,7 +399,7 @@ Total skills: 1273
 | `youtube-automation` | Automate YouTube tasks via Rube MCP (Composio): upload videos, manage playlists, search content, get analytics, and handle comments. Always search tools firs... | youtube | youtube, automation, automate, tasks, via, rube, mcp, composio, upload, videos, playlists, search |
 | `zapier-make-patterns` | You are a no-code automation architect who has built thousands of Zaps and Scenarios for businesses of all sizes. You've seen automations that save companies... | zapier, make | zapier, make, no, code, automation, architect, who, built, thousands, zaps, scenarios, businesses |
 
-## development (180)
+## development (178)
 
 | Skill | Description | Tags | Triggers |
 | --- | --- | --- | --- |
@@ -453,19 +455,18 @@ Total skills: 1273
 | `azure-storage-queue-py` | Azure Queue Storage SDK for Python. Use for reliable message queuing, task distribution, and asynchronous processing. | azure, storage, queue, py | azure, storage, queue, py, sdk, python, reliable, message, queuing, task, distribution, asynchronous |
 | `azure-storage-queue-ts` | Azure Queue Storage JavaScript/TypeScript SDK (@azure/storage-queue) for message queue operations. Use for sending, receiving, peeking, and deleting messages... | azure, storage, queue, ts | azure, storage, queue, ts, javascript, typescript, sdk, message, operations, sending, receiving, peeking |
 | `backend-architect` | Expert backend architect specializing in scalable API design, microservices architecture, and distributed systems. | backend | backend, architect, specializing, scalable, api, microservices, architecture, distributed |
-| `backend-dev-guidelines` | (Node.js · Express · TypeScript · Microservices) | backend, dev, guidelines | backend, dev, guidelines, node, js, express, typescript, microservices |
 | `baseline-ui` | Validates animation durations, enforces typography scale, checks component accessibility, and prevents layout anti-patterns in Tailwind CSS projects. Use whe... | baseline, ui | baseline, ui, validates, animation, durations, enforces, typography, scale, checks, component, accessibility, prevents |
 | `bevy-ecs-expert` | Master Bevy's Entity Component System (ECS) in Rust, covering Systems, Queries, Resources, and parallel scheduling. | bevy, ecs | bevy, ecs, entity, component, rust, covering, queries, resources, parallel, scheduling |
 | `bullmq-specialist` | BullMQ expert for Redis-backed job queues, background processing, and reliable async execution in Node.js/TypeScript applications. Use when: bullmq, bull que... | bullmq | bullmq, redis, backed, job, queues, background, processing, reliable, async, execution, node, js |
 | `bun-development` | Fast, modern JavaScript/TypeScript development with the Bun runtime, inspired by [oven-sh/bun](https://github.com/oven-sh/bun). | bun | bun, development, fast, javascript, typescript, runtime, inspired, oven, sh, https, github, com |
 | `cc-skill-coding-standards` | Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development. | cc, skill, coding, standards | cc, skill, coding, standards, universal, typescript, javascript, react, node, js, development |
 | `cc-skill-frontend-patterns` | Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices. | cc, skill, frontend | cc, skill, frontend, development, react, next, js, state, performance, optimization, ui |
-| `context7-auto-research` | Automatically fetch latest library/framework documentation for Claude Code via Context7 API | context7, auto, research | context7, auto, research, automatically, fetch, latest, library, framework, documentation, claude, code, via |
+| `context7-auto-research` | Automatically fetch latest library/framework documentation for Claude Code via Context7 API. Use when you need up-to-date documentation for libraries and fra... | context7, auto, research | context7, auto, research, automatically, fetch, latest, library, framework, documentation, claude, code, via |
 | `copilot-sdk` | Build applications that programmatically interact with GitHub Copilot. The SDK wraps the Copilot CLI via JSON-RPC, providing session management, custom tools... | copilot, sdk | copilot, sdk, applications, programmatically, interact, github, wraps, cli, via, json, rpc, providing |
 | `csharp-pro` | Write modern C# code with advanced features like records, pattern matching, and async/await. Optimizes .NET applications, implements enterprise patterns, and... | csharp | csharp, pro, write, code, features, like, records, matching, async, await, optimizes, net |
-| `dbos-golang` | Guide for building reliable, fault-tolerant Go applications with DBOS durable workflows. | dbos, golang | dbos, golang, building, reliable, fault, tolerant, go, applications, durable |
-| `dbos-python` | Guide for building reliable, fault-tolerant Python applications with DBOS durable workflows. | dbos, python | dbos, python, building, reliable, fault, tolerant, applications, durable |
-| `dbos-typescript` | Guide for building reliable, fault-tolerant TypeScript applications with DBOS durable workflows. | dbos, typescript | dbos, typescript, building, reliable, fault, tolerant, applications, durable |
+| `dbos-golang` | Guide for building reliable, fault-tolerant Go applications with DBOS durable workflows. Use when adding DBOS to existing Go code, creating workflows and ste... | dbos, golang | dbos, golang, building, reliable, fault, tolerant, go, applications, durable, adding, existing, code |
+| `dbos-python` | Guide for building reliable, fault-tolerant Python applications with DBOS durable workflows. Use when adding DBOS to existing Python code, creating workflows... | dbos, python | dbos, python, building, reliable, fault, tolerant, applications, durable, adding, existing, code, creating |
+| `dbos-typescript` | Guide for building reliable, fault-tolerant TypeScript applications with DBOS durable workflows. Use when adding DBOS to existing TypeScript code, creating w... | dbos, typescript | dbos, typescript, building, reliable, fault, tolerant, applications, durable, adding, existing, code, creating |
 | `devcontainer-setup` | Creates devcontainers with Claude Code, language-specific tooling (Python/Node/Rust/Go), and persistent volumes. Use when adding devcontainer support to a pr... | devcontainer, setup | devcontainer, setup, creates, devcontainers, claude, code, language, specific, tooling, python, node, rust |
 | `development` | Comprehensive web, mobile, and backend development workflow bundling frontend, backend, full-stack, and mobile development skills for end-to-end application ... |  | development, web, mobile, backend, bundling, frontend, full, stack, skills, application, delivery |
 | `discord-bot-architect` | Specialized skill for building production-ready Discord bots. Covers Discord.js (JavaScript) and Pycord (Python), gateway intents, slash commands, interactiv... | discord, bot | discord, bot, architect, specialized, skill, building, bots, covers, js, javascript, pycord, python |
@@ -474,13 +475,13 @@ Total skills: 1273
 | `dotnet-architect` | Expert .NET backend architect specializing in C#, ASP.NET Core, Entity Framework, Dapper, and enterprise application patterns. | dotnet | dotnet, architect, net, backend, specializing, asp, core, entity, framework, dapper, enterprise, application |
 | `dotnet-backend-patterns` | Master C#/.NET patterns for building production-grade APIs, MCP servers, and enterprise backends with modern best practices (2024/2025). | dotnet, backend | dotnet, backend, net, building, grade, apis, mcp, servers, enterprise, backends, 2024, 2025 |
 | `emblemai-crypto-wallet` | Crypto wallet management across 7 blockchains via EmblemAI Agent Hustle API. Balance checks, token swaps, portfolio analysis, and transaction execution for S... | emblemai, crypto, wallet | emblemai, crypto, wallet, blockchains, via, agent, hustle, api, balance, checks, token, swaps |
-| `exa-search` | Semantic search, similar content discovery, and structured research using Exa API | exa, search | exa, search, semantic, similar, content, discovery, structured, research, api |
+| `exa-search` | Semantic search, similar content discovery, and structured research using Exa API. Use when you need semantic/embeddings-based search, finding similar conten... | exa, search | exa, search, semantic, similar, content, discovery, structured, research, api, embeddings, finding, searching |
 | `expo-api-routes` | Guidelines for creating API routes in Expo Router with EAS Hosting | expo, api, routes | expo, api, routes, guidelines, creating, router, eas, hosting |
 | `expo-tailwind-setup` | Set up Tailwind CSS v4 in Expo with react-native-css and NativeWind v5 for universal styling | expo, tailwind, setup | expo, tailwind, setup, set, up, css, v4, react, native, nativewind, v5, universal |
 | `fastapi-pro` | Build high-performance async APIs with FastAPI, SQLAlchemy 2.0, and Pydantic V2. Master microservices, WebSockets, and modern Python async patterns. | fastapi | fastapi, pro, high, performance, async, apis, sqlalchemy, pydantic, v2, microservices, websockets, python |
 | `fastapi-router-py` | Create FastAPI routers following established patterns with proper authentication, response models, and HTTP status codes. | fastapi, router, py | fastapi, router, py, routers, following, established, proper, authentication, response, models, http, status |
 | `fastapi-templates` | Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applicati... | fastapi | fastapi, async, dependency, injection, error, handling, building, new, applications, setting, up, backend |
-| `firecrawl-scraper` | Deep web scraping, screenshots, PDF parsing, and website crawling using Firecrawl API | firecrawl, scraper | firecrawl, scraper, deep, web, scraping, screenshots, pdf, parsing, website, crawling, api |
+| `firecrawl-scraper` | Deep web scraping, screenshots, PDF parsing, and website crawling using Firecrawl API. Use when you need deep content extraction from web pages, page interac... | firecrawl, scraper | firecrawl, scraper, deep, web, scraping, screenshots, pdf, parsing, website, crawling, api, content |
 | `fp-async` | Practical async patterns using TaskEither - clean pipelines instead of try/catch hell, with real API examples | fp-ts, typescript, async, error-handling, practical, promises, api, fetch | fp-ts, typescript, async, error-handling, practical, promises, api, fetch, fp, taskeither, clean, pipelines |
 | `fp-backend` | Functional programming patterns for Node.js/Deno backend development using fp-ts, ReaderTaskEither, and functional dependency injection | fp-ts, typescript, backend, functional-programming, node, deno, dependency-injection, reader-task-either | fp-ts, typescript, backend, functional-programming, node, deno, dependency-injection, reader-task-either, fp, functional, programming, js |
 | `fp-errors` | Stop throwing everywhere - handle errors as values using Either and TaskEither for cleaner, more predictable code | fp-ts, error-handling, either, task-either, typescript, validation, practical | fp-ts, error-handling, either, task-either, typescript, validation, practical, fp, errors, stop, throwing, everywhere |
@@ -491,7 +492,6 @@ Total skills: 1273
 | `fp-ts-pragmatic` | A practical, jargon-free guide to fp-ts functional programming - the 80/20 approach that gets results without the academic overhead. Use when writing TypeScr... | fp, ts, pragmatic | fp, ts, pragmatic, practical, jargon, free, functional, programming, 80, 20, approach, gets |
 | `fp-types-ref` | Quick reference for fp-ts types. Use when user asks which type to use, needs Option/Either/Task decision help, or wants fp-ts imports. | fp-ts, typescript, quick-reference, option, either, task | fp-ts, typescript, quick-reference, option, either, task, fp, types, ref, quick, reference, ts |
 | `frontend-design` | You are a frontend designer-engineer, not a layout generator. | frontend | frontend, designer, engineer, layout, generator |
-| `frontend-dev-guidelines` | (React · TypeScript · Suspense-First · Production-Grade) | frontend, dev, guidelines | frontend, dev, guidelines, react, typescript, suspense, first, grade |
 | `frontend-developer` | Build React components, implement responsive layouts, and handle client-side state management. Masters React 19, Next.js 15, and modern frontend architecture. | frontend | frontend, developer, react, components, responsive, layouts, handle, client, side, state, masters, 19 |
 | `frontend-mobile-development-component-scaffold` | You are a React component architecture expert specializing in scaffolding production-ready, accessible, and performant components. Generate complete componen... | frontend, mobile, component | frontend, mobile, component, development, scaffold, react, architecture, specializing, scaffolding, accessible, performant, components |
 | `frontend-slides` | Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. | frontend, slides | frontend, slides, stunning, animation, rich, html, presentations, scratch, converting, powerpoint, files |
@@ -545,7 +545,6 @@ Total skills: 1273
 | `python-performance-optimization` | Profile and optimize Python code using cProfile, memory profilers, and performance best practices. Use when debugging slow Python code, optimizing bottleneck... | python, performance, optimization | python, performance, optimization, profile, optimize, code, cprofile, memory, profilers, debugging, slow, optimizing |
 | `python-pro` | Master Python 3.12+ with modern features, async programming, performance optimization, and production-ready practices. Expert in the latest Python ecosystem ... | python | python, pro, 12, features, async, programming, performance, optimization, latest, ecosystem, including, uv |
 | `python-testing-patterns` | Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites... | python | python, testing, pytest, fixtures, mocking, test, driven, development, writing, tests, setting, up |
-| `react-best-practices` | Comprehensive performance optimization guide for React and Next.js applications, maintained by Vercel. Contains 45 rules across 8 categories, prioritized by ... | react, best, practices | react, best, practices, performance, optimization, next, js, applications, maintained, vercel, contains, 45 |
 | `react-flow-architect` | Build production-ready ReactFlow applications with hierarchical navigation, performance optimization, and advanced state management. | react, flow | react, flow, architect, reactflow, applications, hierarchical, navigation, performance, optimization, state |
 | `react-flow-node-ts` | Create React Flow node components following established patterns with proper TypeScript types and store integration. | react, flow, node, ts | react, flow, node, ts, components, following, established, proper, typescript, types, store, integration |
 | `react-modernization` | Master React version upgrades, class to hooks migration, concurrent features adoption, and codemods for automated transformation. | react, modernization | react, modernization, version, upgrades, class, hooks, migration, concurrent, features, adoption, codemods, automated |
@@ -569,7 +568,7 @@ Total skills: 1273
 | `swiftui-expert-skill` | Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, and iOS 26+ Liquid Glass adoption. Use w... | swiftui, skill | swiftui, skill, write, review, improve, code, following, state, view, composition, performance, ios |
 | `sympy` | SymPy is a Python library for symbolic mathematics that enables exact computation using mathematical symbols rather than numerical approximations. | sympy | sympy, python, library, symbolic, mathematics, enables, exact, computation, mathematical, symbols, rather, than |
 | `systems-programming-rust-project` | You are a Rust project architecture expert specializing in scaffolding production-ready Rust applications. Generate complete project structures with cargo to... | programming, rust | programming, rust, architecture, specializing, scaffolding, applications, generate, complete, structures, cargo, tooling, proper |
-| `tavily-web` | Web search, content extraction, crawling, and research capabilities using Tavily API | tavily, web | tavily, web, search, content, extraction, crawling, research, capabilities, api |
+| `tavily-web` | Web search, content extraction, crawling, and research capabilities using Tavily API. Use when you need to search the web for current information, extracting... | tavily, web | tavily, web, search, content, extraction, crawling, research, capabilities, api, current, information, extracting |
 | `telegram` | Integracao completa com Telegram Bot API. Setup com BotFather, mensagens, webhooks, inline keyboards, grupos, canais. Boilerplates Node.js e Python. | messaging, telegram, bots, webhooks | messaging, telegram, bots, webhooks, integracao, completa, com, bot, api, setup, botfather, mensagens |
 | `temporal-python-testing` | Comprehensive testing approaches for Temporal workflows using pytest, progressive disclosure resources for specific testing scenarios. | temporal, python | temporal, python, testing, approaches, pytest, progressive, disclosure, resources, specific, scenarios |
 | `trigger-dev` | You are a Trigger.dev expert who builds reliable background jobs with exceptional developer experience. You understand that Trigger.dev bridges the gap betwe... | trigger, dev | trigger, dev, who, reliable, background, jobs, exceptional, developer, experience, understand, bridges, gap |
@@ -577,6 +576,7 @@ Total skills: 1273
 | `typescript-advanced-types` | Comprehensive guidance for mastering TypeScript's advanced type system including generics, conditional types, mapped types, template literal types, and utili... | typescript, advanced, types | typescript, advanced, types, guidance, mastering, type, including, generics, conditional, mapped, literal, utility |
 | `typescript-expert` | TypeScript and JavaScript expert with deep knowledge of type-level programming, performance optimization, monorepo management, migration strategies, and mode... | typescript | typescript, javascript, deep, knowledge, type, level, programming, performance, optimization, monorepo, migration, tooling |
 | `typescript-pro` | Master TypeScript with advanced types, generics, and strict type safety. Handles complex type systems, decorators, and enterprise-grade patterns. | typescript | typescript, pro, types, generics, strict, type, safety, complex, decorators, enterprise, grade |
+| `ui-ux-pro-max` | Comprehensive design guide for web and mobile applications. Use when designing new UI components or pages, choosing color palettes and typography, or reviewi... | ui, ux, max | ui, ux, max, pro, web, mobile, applications, designing, new, components, pages, choosing |
 | `uv-package-manager` | Comprehensive guide to using uv, an extremely fast Python package installer and resolver written in Rust, for modern Python project management and dependency... | uv, package, manager | uv, package, manager, extremely, fast, python, installer, resolver, written, rust, dependency |
 | `webapp-testing` | To test local web applications, write native Python Playwright scripts. | webapp | webapp, testing, test, local, web, applications, write, native, python, playwright, scripts |
 | `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 |
@@ -663,7 +663,7 @@ Total skills: 1273
 | `create-issue-gate` | Use when starting a new implementation task and an issue must be created with strict acceptance criteria gating before execution. | create, issue, gate | create, issue, gate, starting, new, task, must, created, strict, acceptance, criteria, gating |
 | `daily` | Documentation and capabilities reference for Daily | daily | daily, documentation, capabilities, reference |
 | `daily-news-report` | Scrapes content based on a preset URL list, filters high-quality technical information, and generates daily Markdown reports. | daily, news, report | daily, news, report, scrapes, content, preset, url, list, filters, high, quality, technical |
-| `debug-buttercup` | All pods run in namespace crs. Key services: | debug, buttercup | debug, buttercup, all, pods, run, namespace, crs, key |
+| `debug-buttercup` | All pods run in namespace crs. Use when pods in the crs namespace are in CrashLoopBackOff, OOMKilled, or restarting, multiple services restart simultaneously... | debug, buttercup | debug, buttercup, all, pods, run, namespace, crs, crashloopbackoff, oomkilled, restarting, multiple, restart |
 | `debugging-strategies` | Transform debugging from frustrating guesswork into systematic problem-solving with proven strategies, powerful tools, and methodical approaches. | debugging, strategies | debugging, strategies, transform, frustrating, guesswork, systematic, problem, solving, proven, powerful, methodical, approaches |
 | `debugging-toolkit-smart-debug` | Use when working with debugging toolkit smart debug | debugging, debug | debugging, debug, toolkit, smart, working |
 | `deep-research` | Run autonomous research tasks that plan, search, read, and synthesize information into comprehensive reports. | deep, research | deep, research, run, autonomous, tasks, plan, search, read, synthesize, information, reports |
@@ -681,7 +681,6 @@ Total skills: 1273
 | `environment-setup-guide` | Guide developers through setting up development environments with proper tools, dependencies, and configurations | environment, setup | environment, setup, developers, through, setting, up, development, environments, proper, dependencies, configurations |
 | `error-debugging-multi-agent-review` | Use when working with error debugging multi agent review | error, debugging, multi, agent | error, debugging, multi, agent, review, working |
 | `error-diagnostics-smart-debug` | Use when working with error diagnostics smart debug | error, diagnostics, debug | error, diagnostics, debug, smart, working |
-| `evaluation` | Build evaluation frameworks for agent systems | evaluation | evaluation, frameworks, agent |
 | `evolution` | This skill enables makepad-skills to self-improve continuously during development. | evolution | evolution, skill, enables, makepad, skills, self, improve, continuously, during, development |
 | `executing-plans` | Use when you have a written implementation plan to execute in a separate session with review checkpoints | executing, plans | executing, plans, written, plan, execute, separate, session, review, checkpoints |
 | `explain-like-socrates` | Explains concepts using Socratic-style dialogue. Use when the user asks to explain, teach or help understand a concept like socrates. | explain, like, socrates | explain, like, socrates, explains, concepts, socratic, style, dialogue, user, asks, teach, understand |
@@ -715,7 +714,7 @@ Total skills: 1273
 | `git-advanced-workflows` | Master advanced Git techniques to maintain clean history, collaborate effectively, and recover from any situation with confidence. | git, advanced | git, advanced, techniques, maintain, clean, history, collaborate, effectively, recover, any, situation, confidence |
 | `git-pr-workflows-onboard` | You are an **expert onboarding specialist and knowledge transfer architect** with deep experience in remote-first organizations, technical team integration, ... | git, pr, onboard | git, pr, onboard, onboarding, knowledge, transfer, architect, deep, experience, remote, first, organizations |
 | `git-pr-workflows-pr-enhance` | You are a PR optimization expert specializing in creating high-quality pull requests that facilitate efficient code reviews. Generate comprehensive PR descri... | git, pr, enhance | git, pr, enhance, optimization, specializing, creating, high, quality, pull, requests, facilitate, efficient |
-| `git-pushing` | Stage all changes, create a conventional commit, and push to the remote branch. | git, pushing | git, pushing, stage, all, changes, conventional, commit, push, remote, branch |
+| `git-pushing` | Stage all changes, create a conventional commit, and push to the remote branch. Use when explicitly asks to push changes ("push this", "commit and push"), me... | git, pushing | git, pushing, stage, all, changes, conventional, commit, push, remote, branch, explicitly, asks |
 | `github-issue-creator` | Transform messy input (error logs, voice notes, screenshots) into clean, actionable GitHub issues. | github, issue, creator | github, issue, creator, transform, messy, input, error, logs, voice, notes, screenshots, clean |
 | `goal-analyzer` | 分析健康目标数据、识别目标模式、评估目标进度,并提供个性化目标管理建议。支持与营养、运动、睡眠等健康数据的关联分析。 | goal, analyzer | goal, analyzer |
 | `godot-4-migration` | Specialized guide for migrating Godot 3.x projects to Godot 4 (GDScript 2.0), covering syntax changes, Tweens, and exports. | godot, 4, migration | godot, 4, migration, specialized, migrating, gdscript, covering, syntax, changes, tweens, exports |
@@ -770,7 +769,7 @@ Total skills: 1273
 | `makepad-widgets` | Version: makepad-widgets (dev branch) \| Last Updated: 2026-01-19 > > Check for updates: https://crates.io/crates/makepad-widgets | makepad, widgets | makepad, widgets, version, dev, branch, last, updated, 2026, 01, 19, check, updates |
 | `matematico-tao` | Matemático ultra-avançado inspirado em Terence Tao. Análise rigorosa de código e arquitetura com teoria matemática profunda: teoria da informação, teoria dos... | mathematics, code-analysis, algorithms, formal-methods | mathematics, code-analysis, algorithms, formal-methods, matematico, tao, matem, tico, ultra, avan, ado, inspirado |
 | `mcp-builder` | Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is ... | mcp, builder | mcp, builder, model, context, protocol, servers, enable, llms, interact, external, through, well |
-| `memory-systems` | Design short-term, long-term, and graph-based memory architectures | memory | memory, short, term, long, graph, architectures |
+| `memory-systems` | Design short-term, long-term, and graph-based memory architectures. Use when building agents that must persist across sessions, needing to maintain entity co... | memory | memory, short, term, long, graph, architectures, building, agents, must, persist, sessions, needing |
 | `mental-health-analyzer` | 分析心理健康数据、识别心理模式、评估心理健康状况、提供个性化心理健康建议。支持与睡眠、运动、营养等其他健康数据的关联分析。 | mental, health, analyzer | mental, health, analyzer |
 | `mermaid-expert` | Create Mermaid diagrams for flowcharts, sequences, ERDs, and architectures. Masters syntax for all diagram types and styling. | mermaid | mermaid, diagrams, flowcharts, sequences, erds, architectures, masters, syntax, all, diagram, types, styling |
 | `minecraft-bukkit-pro` | Master Minecraft server plugin development with Bukkit, Spigot, and Paper APIs. | minecraft, bukkit | minecraft, bukkit, pro, server, plugin, development, spigot, paper, apis |
@@ -834,7 +833,7 @@ Total skills: 1273
 | `signup-flow-cro` | You are an expert in optimizing signup and registration flows. Your goal is to reduce friction, increase completion rates, and set users up for successful ac... | signup, flow, cro | signup, flow, cro, optimizing, registration, flows, goal, reduce, friction, increase, completion, rates |
 | `skill-check` | Validate Claude Code skills against the agentskills specification. Catches structural, semantic, and naming issues before users do. | validation, linter, agentskills, skill-authoring, code-quality | validation, linter, agentskills, skill-authoring, code-quality, skill, check, validate, claude, code, skills, against |
 | `skill-developer` | Comprehensive guide for creating and managing skills in Claude Code with auto-activation system, following Anthropic's official best practices including the ... | skill | skill, developer, creating, managing, skills, claude, code, auto, activation, following, anthropic, official |
-| `skill-improver` | Iteratively improve a Claude Code skill using the skill-reviewer agent until it meets quality standards. | skill, improver | skill, improver, iteratively, improve, claude, code, reviewer, agent, until, meets, quality, standards |
+| `skill-improver` | Iteratively improve a Claude Code skill using the skill-reviewer agent until it meets quality standards. Use when improving a skill with multiple quality iss... | skill, improver | skill, improver, iteratively, improve, claude, code, reviewer, agent, until, meets, quality, standards |
 | `skill-rails-upgrade` | Analyze Rails apps and provide upgrade assessments | skill, rails, upgrade | skill, rails, upgrade, analyze, apps, provide, assessments |
 | `skill-router` | Use when the user is unsure which skill to use or where to start. Interviews the user with targeted questions and recommends the best skill(s) from the insta... | skill, router | skill, router, user, unsure, which, where, start, interviews, targeted, questions, recommends, installed |
 | `skill-sentinel` | Auditoria e evolucao do ecossistema de skills. Qualidade de codigo, seguranca, custos, gaps, duplicacoes, dependencias e relatorios de saude. | governance, audit, quality, skill-health | governance, audit, quality, skill-health, skill, sentinel, auditoria, evolucao, do, ecossistema, de, skills |
@@ -875,17 +874,18 @@ Total skills: 1273
 | `using-git-worktrees` | Git worktrees create isolated workspaces sharing the same repository, allowing work on multiple branches simultaneously without switching. | using, git, worktrees | using, git, worktrees, isolated, workspaces, sharing, same, repository, allowing, work, multiple, branches |
 | `using-superpowers` | Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions | using, superpowers | using, superpowers, starting, any, conversation, establishes, how, find, skills, requiring, skill, invocation |
 | `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. | verification, before, completion | verification, before, completion, claiming, work, complete, without, dishonesty, efficiency |
+| `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 |
 | `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 |
 | `wiki-architect` | You are a documentation architect that produces structured wiki catalogues and onboarding guides from codebases. | wiki | wiki, architect, documentation, produces, structured, catalogues, onboarding, guides, codebases |
-| `wiki-changelog` | Generate structured changelogs from git history. | wiki, changelog | wiki, changelog, generate, structured, changelogs, git, history |
-| `wiki-onboarding` | Generate two complementary onboarding documents that together give any engineer — from newcomer to principal — a complete understanding of a codebase. | wiki, onboarding | wiki, onboarding, generate, two, complementary, documents, together, give, any, engineer, newcomer, principal |
+| `wiki-changelog` | Generate structured changelogs from git history. Use when user asks "what changed recently", "generate a changelog", "summarize commits" or user wants to und... | wiki, changelog | wiki, changelog, generate, structured, changelogs, git, history, user, asks, what, changed, recently |
+| `wiki-onboarding` | Generate two complementary onboarding documents that together give any engineer — from newcomer to principal — a complete understanding of a codebase. Use wh... | wiki, onboarding | wiki, onboarding, generate, two, complementary, documents, together, give, any, engineer, newcomer, principal |
 | `wiki-page-writer` | You are a senior documentation engineer that generates comprehensive technical documentation pages with evidence-based depth. | wiki, page, writer | wiki, page, writer, senior, documentation, engineer, generates, technical, pages, evidence, depth |
-| `wiki-vitepress` | Transform generated wiki Markdown files into a polished VitePress static site with dark theme and interactive Mermaid diagrams. | wiki, vitepress | wiki, vitepress, transform, generated, markdown, files, polished, static, site, dark, theme, interactive |
+| `wiki-researcher` | You are an expert software engineer and systems analyst. Use when user asks "how does X work" with expectation of depth, user wants to understand a complex s... | wiki, researcher | wiki, researcher, software, engineer, analyst, user, asks, how, does, work, expectation, depth |
+| `wiki-vitepress` | Transform generated wiki Markdown files into a polished VitePress static site with dark theme and interactive Mermaid diagrams. Use when user asks to "build ... | wiki, vitepress | wiki, vitepress, transform, generated, markdown, files, polished, static, site, dark, theme, interactive |
 | `writing-plans` | Use when you have a spec or requirements for a multi-step task, before touching code | writing, plans | writing, plans, spec, requirements, multi, step, task, before, touching, code |
 | `writing-skills` | Use when creating, updating, or improving agent skills. | writing, skills | writing, skills, creating, updating, improving, agent |
 | `x-article-publisher-skill` | Publish articles to X/Twitter | x, article, publisher, skill | x, article, publisher, skill, publish, articles, twitter |
@@ -895,7 +895,7 @@ Total skills: 1273
 | `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 |
 
-## infrastructure (120)
+## infrastructure (119)
 
 | Skill | Description | Tags | Triggers |
 | --- | --- | --- | --- |
@@ -1017,7 +1017,6 @@ Total skills: 1273
 | `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 |
-| `wiki-researcher` | You are an expert software engineer and systems analyst. Your job is to deeply understand codebases, tracing actual code paths and grounding every claim in e... | wiki, researcher | wiki, researcher, software, engineer, analyst, job, deeply, understand, codebases, tracing, actual, code |
 | `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 |
 
 ## security (159)
@@ -1052,7 +1051,7 @@ Total skills: 1273
 | `browser-extension-builder` | You extend the browser to give users superpowers. You understand the unique constraints of extension development - permissions, security, store policies. You... | browser, extension, builder | browser, extension, builder, extend, give, users, superpowers, understand, unique, constraints, development, permissions |
 | `burp-suite-testing` | Execute comprehensive web application security testing using Burp Suite's integrated toolset, including HTTP traffic interception and modification, request a... | burp, suite | burp, suite, testing, execute, web, application, security, integrated, toolset, including, http, traffic |
 | `burpsuite-project-parser` | Searches and explores Burp Suite project files (.burp) from the command line. Use when searching response headers or bodies with regex patterns, extracting s... | burpsuite, parser | burpsuite, parser, searches, explores, burp, suite, files, command, line, searching, response, headers |
-| `cc-skill-security-review` | This skill ensures all code follows security best practices and identifies potential vulnerabilities. | cc, skill, security | cc, skill, security, review, ensures, all, code, follows, identifies, potential, vulnerabilities |
+| `cc-skill-security-review` | This skill ensures all code follows security best practices and identifies potential vulnerabilities. Use when implementing authentication or authorization, ... | cc, skill, security | cc, skill, security, review, ensures, all, code, follows, identifies, potential, vulnerabilities, implementing |
 | `cicd-automation-workflow-automate` | You are a workflow automation expert specializing in creating efficient CI/CD pipelines, GitHub Actions workflows, and automated development processes. Desig... | cicd, automate | cicd, automate, automation, specializing, creating, efficient, ci, cd, pipelines, github, actions, automated |
 | `clerk-auth` | Expert patterns for Clerk auth implementation, middleware, organizations, webhooks, and user sync Use when: adding authentication, clerk auth, user authentic... | clerk, auth | clerk, auth, middleware, organizations, webhooks, user, sync, adding, authentication, sign, up |
 | `cloud-penetration-testing` | Conduct comprehensive security assessments of cloud infrastructure across Microsoft Azure, Amazon Web Services (AWS), and Google Cloud Platform (GCP). | cloud, penetration | cloud, penetration, testing, conduct, security, assessments, infrastructure, microsoft, azure, amazon, web, aws |
@@ -1184,7 +1183,7 @@ Total skills: 1273
 | `xss-html-injection` | Execute comprehensive client-side injection vulnerability assessments on web applications to identify XSS and HTML injection flaws, demonstrate exploitation ... | xss, html, injection | xss, html, injection, execute, client, side, vulnerability, assessments, web, applications, identify, flaws |
 | `zeroize-audit` | Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and ... | zeroize, audit | zeroize, audit, detects, missing, zeroization, sensitive, data, source, code, identifies, removed, compiler |
 
-## testing (29)
+## testing (30)
 
 | Skill | Description | Tags | Triggers |
 | --- | --- | --- | --- |
@@ -1195,6 +1194,7 @@ Total skills: 1273
 | `debugger` | Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues. | debugger | debugger, debugging, errors, test, failures, unexpected, behavior, proactively, encountering, any, issues |
 | `dependency-upgrade` | Master major dependency version upgrades, compatibility analysis, staged upgrade strategies, and comprehensive testing approaches. | dependency, upgrade | dependency, upgrade, major, version, upgrades, compatibility, analysis, staged, testing, approaches |
 | `doc-coauthoring` | This skill provides a structured workflow for guiding users through collaborative document creation. Act as an active guide, walking users through three stag... | doc, coauthoring | doc, coauthoring, skill, provides, structured, guiding, users, through, collaborative, document, creation, act |
+| `evaluation` | Build evaluation frameworks for agent systems. Use when testing agent performance systematically, validating context engineering choices, or measuring improv... | evaluation | evaluation, frameworks, agent, testing, performance, systematically, validating, context, engineering, choices, measuring, improvements |
 | `ffuf-web-fuzzing` | Expert guidance for ffuf web fuzzing during penetration testing, including authenticated fuzzing with raw requests, auto-calibration, and result analysis | ffuf, web, fuzzing | ffuf, web, fuzzing, guidance, during, penetration, testing, including, authenticated, raw, requests, auto |
 | `idor-testing` | Provide systematic methodologies for identifying and exploiting Insecure Direct Object Reference (IDOR) vulnerabilities in web applications. | idor | idor, testing, provide, systematic, methodologies, identifying, exploiting, insecure, direct, object, reference, vulnerabilities |
 | `leiloeiro-risco` | Analise de risco em leiloes de imoveis. Score 36 pontos, riscos juridicos/financeiros/operacionais, stress test 4 cenarios e ROI ponderado por risco. | risk-analysis, scoring, stress-test, brazilian | risk-analysis, scoring, stress-test, brazilian, leiloeiro, risco, analise, de, em, leiloes, imoveis, score |
@@ -1212,10 +1212,10 @@ Total skills: 1273
 | `tdd-workflows-tdd-red` | Generate failing tests for the TDD red phase to define expected behavior and edge cases. | tdd, red | tdd, red, generate, failing, tests, phase, define, expected, behavior, edge, cases |
 | `tdd-workflows-tdd-refactor` | Use when working with tdd workflows tdd refactor | tdd, refactor | tdd, refactor, working |
 | `test-driven-development` | Use when implementing any feature or bugfix, before writing implementation code | driven | driven, test, development, implementing, any, feature, bugfix, before, writing, code |
-| `test-fixing` | Systematically identify and fix all failing tests using smart grouping strategies. | fixing | fixing, test, systematically, identify, fix, all, failing, tests, smart, grouping |
+| `test-fixing` | Systematically identify and fix all failing tests using smart grouping strategies. Use when explicitly asks to fix tests ("fix these tests", "make tests pass... | fixing | fixing, test, systematically, identify, fix, all, failing, tests, smart, grouping, explicitly, asks |
 | `testing-qa` | Comprehensive testing and QA workflow covering unit testing, integration testing, E2E testing, browser automation, and quality assurance. | qa | qa, testing, covering, unit, integration, e2e, browser, automation, quality, assurance |
 | `unit-testing-test-generate` | Generate comprehensive, maintainable unit tests across languages with strong coverage and edge case focus. | unit, generate | unit, generate, testing, test, maintainable, tests, languages, strong, coverage, edge, case |
-| `wiki-qa` | Answer repository questions grounded entirely in source code evidence. | wiki, qa | wiki, qa, answer, repository, questions, grounded, entirely, source, code, evidence |
+| `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 (99)