firefrost-gaming/claude-skills-reference
3
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
644 Commits 1 Branch 0 Tags
ed2419b8e176cda724b2c5e0b8620768638924bb
Commit Graph

80 Commits

Author SHA1 Message Date
Reza Rezvani
7533d34978 chore: post-merge sync — statistical-analyst plugin, spec-to-repo skill, docs update 
New:
- feat(product-team): add spec-to-repo skill — natural-language spec to runnable repo
  1 Python tool (validate_project.py), 2 references, 3 concrete examples
- feat(engineering): add statistical-analyst plugin.json + marketplace entry (32 total)

Sync:
- Update all counts to 233 skills, 305 tools, 424 refs, 25 agents, 22 commands
- Fix engineering-advanced plugin description: 42 → 43 skills
- Sync Codex (194 skills), Gemini (282 items), MkDocs (281 pages → 313 HTML)
- Update CLAUDE.md, README.md, docs/index.md, docs/getting-started.md, mkdocs.yml
- Expand product-analytics SKILL.md + add JSON output to metrics_calculator.py

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-07 12:09:55 +02:00
Reza Rezvani
7c2564845a refactor(engineering): move statistical-analyst to engineering/, fix cross-refs 
- Move from data-analysis/ to engineering/
- Fix 5 cross-references to use correct domain paths
- Fix Python 3.9 compat in sample_size_calculator.py

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-07 11:18:12 +02:00
Reza Rezvani
5710a7b763 chore: post-merge sync — plugins, audits, docs, cross-platform indexes 
New skills integrated:
- engineering/behuman, code-tour, demo-video, data-quality-auditor

Plugins & marketplace:
- Add plugin.json for code-tour, demo-video, data-quality-auditor
- Add all 3 to marketplace.json (31 total plugins)
- Update marketplace counts to 248 skills, 332 tools, 460 refs

Skill fixes:
- Move data-quality-auditor from data-analysis/ to engineering/
- Fix cross-refs: code-tour, demo-video, data-quality-auditor
- Add evals.json for code-tour (5 scenarios) and demo-video (4 scenarios)
- demo-video: add output artifacts, prereqs check, references extraction
- code-tour: add default persona, parallel discovery, trivial repo guidance
- Fix Python 3.9 compat (from __future__ import annotations)

product-analytics audit fixes:
- Expand SKILL.md from 82 to 147 lines (anti-patterns, cross-refs, examples)
- Add --format json to all metrics_calculator.py subcommands
- Add error handling (FileNotFoundError, KeyError)

Docs & indexes:
- Update CLAUDE.md, README.md, docs/index.md, docs/getting-started.md counts
- Sync Codex (192 skills) and Gemini (280 items) indexes
- Regenerate MkDocs pages (279 pages, 311 HTML)
- Add 3 new nav entries to mkdocs.yml
- Update mkdocs.yml site_description

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-04 02:05:19 +02:00
Alireza Rezvani
6c89d8f591 Merge pull request #475 from vaddisrinivas/add-framecraft 
feat(engineering): add demo-video skill
 2026-04-04 01:18:10 +02:00
Srinivas Vaddi
8be3cd56e8 feat(engineering): add code-tour skill 
Add a skill for creating CodeTour .tour files — persona-targeted,
step-by-step walkthroughs that link to real files and line numbers.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-03 02:43:59 -04:00
Srinivas Vaddi
01ab7433ac feat(engineering): add demo-video skill 
Add a skill for creating polished demo videos from screenshots and scene
descriptions. Orchestrates playwright, ffmpeg, and edge-tts MCPs.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-03 02:43:44 -04:00
Reza Rezvani
baca2e61ac feat(engineering): add behuman skill — Self-Mirror consciousness loop 
Based on issue #464 submission by voidborne-d. Enhanced with English-only
content (removed all Chinese), anti-patterns section, cross-references,
plugin.json, convention-compliant frontmatter, and English eval scenarios.

behuman (193 lines + reference + 8 eval scenarios):
- Self-Mirror loop: instinctive response → reflection → conscious revision
- Show mode (2.5-3x tokens) and quiet mode (1.5-2x tokens)
- 3 English examples: emotional support, life advice, personal writing
- Based on Lacan's Mirror Stage + Kahneman's Dual Process Theory
- Zero dependencies — pure prompt technique

Co-Authored-By: voidborne-d <voidborne-d@users.noreply.github.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-03 01:54:01 +02:00
Alireza Rezvani
1a06eacbb8 Merge pull request #430 from xingzihai/feat/security-dimension-v2 
feat(skill-tester): add Security dimension to quality scoring system
 2026-03-31 15:25:43 +02:00
Reza Rezvani
d02cc1c9b2 feat(plugins): add standalone plugin.json for 4 new community skills 
Each skill is now individually installable:
- llm-cost-optimizer
- prompt-governance
- business-investment-advisor
- video-content-strategist

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-31 12:36:16 +02:00
Reza Rezvani
3cd885aa33 chore: sync indexes, update marketplace and docs for 4 new community skills 
- Codex CLI: 182 skills, 4 new symlinks
- Gemini CLI: 274 items, 4 new
- engineering plugin.json: 36→38
- finance plugin.json: 2→3
- marketing plugin.json: 43→44
- marketplace.json: updated 3 bundle descriptions
- mkdocs.yml: 4 new nav entries
- docs/index.md + getting-started.md: domain counts updated
- 273 docs pages generated

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-31 12:32:57 +02:00
Reza Rezvani
1f374e7492 feat: add 4 community skills — llm-cost-optimizer, prompt-governance, business-investment-advisor, video-content-strategist 
Based on PR #448 by chad848. Enhanced with frontmatter normalization,
anti-patterns sections, ghost script reference removal, and broken
cross-reference fixes. Automotive-electrical-engineer excluded (out of
scope for software/AI skills library).

llm-cost-optimizer (engineering/, 192 lines):
- Reduce LLM API spend 40-80% via model routing, caching, compression
- 3 modes: Cost Audit, Optimize, Design Cost-Efficient Architecture

prompt-governance (engineering/, 224 lines):
- Production prompt lifecycle: versioning, eval pipelines, A/B testing
- Distinct from senior-prompt-engineer (writing) — this is ops/governance

business-investment-advisor (finance/, 220 lines):
- Capital allocation: ROI, NPV, IRR, payback, build-vs-buy, lease-vs-buy
- NOT securities advice — business capex decisions only

video-content-strategist (marketing-skill/, 218 lines):
- YouTube strategy, video scripting, short-form pipelines, content atomization
- Fills video gap in 44-skill marketing pod

Co-Authored-By: chad848 <chad848@users.noreply.github.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-31 11:43:03 +02:00
Claude
6fa92054bd release(v2.2.0): 223 skills, security suite, self-eval, full docs update 
- Add 8 new skills: 6 security (adversarial-reviewer, ai-security, cloud-security, incident-response, red-team, threat-detection), self-eval, snowflake-development
- Update all counts: 223 skills, 298 tools, 416 references, 23 agents, 22 commands
- Update CHANGELOG.md with v2.2.0 entry
- Update all plugin.json versions to 2.2.0
- Update CLAUDE.md, README.md, docs/index.md, docs/getting-started.md, mkdocs.yml
- Verify MkDocs build (301 pages), Codex/Gemini sync, all new scripts pass --help

https://claude.ai/code/session_011CHSDjqWBPRcEJ3oJrAUHS
 2026-03-31 05:55:51 +00:00
Claude
c8520885f9 feat: full ecosystem integration for PR #435 (5 security skills) and PR #436 (self-eval) 
- Updated domain plugin.json counts (engineering-team: 36, engineering: 36)
- Added 6 new skills to mkdocs.yml navigation
- Updated engineering-team/CLAUDE.md with security skills section
- Generated docs pages for all 6 new skills
- Synced Codex + Gemini indexes and symlinks
- Ran cross-platform conversion (Cursor, Aider, Windsurf, KiloCode, OpenCode, Augment, Antigravity)

https://claude.ai/code/session_01XY4i7SR4BHLWJpdjwGnNLG
 2026-03-30 19:11:46 +00:00
Ethan Kreloff
c48c92aa96 feat(engineering): add self-eval skill 
Adds self-eval skill for honest AI work quality evaluation. Uses two-axis scoring (ambition x execution), mandatory devil's advocate reasoning, and cross-session anti-inflation detection via .self-eval-scores.jsonl persistence.
 2026-03-30 21:07:45 +02:00
xingzihai
e0e683ee5e fix(skill-tester): make Security dimension opt-in with --include-security flag 
- Add --include-security flag to quality_scorer.py
- Default: 4 dimensions × 25% (backward compatible)
- With --include-security: 5 dimensions × 20%
- Update tier recommendation logic for optional Security
- Update documentation to reflect opt-in behavior

This addresses the breaking change concern from PR review:
the weight change from 25% to 20% would affect all existing
audit baselines. The new opt-in approach preserves backward
compatibility.
 2026-03-27 10:05:12 +00:00
xingzihai
2f92a1dfcb feat(skill-tester): add Security dimension to quality scoring system 
- Add SecurityScorer module (605 lines) with comprehensive security assessment
- Add 4 security scoring components:
  - Sensitive data exposure prevention (hardcoded credentials detection)
  - Safe file operations (path traversal prevention)
  - Command injection prevention (shell=True, eval, exec detection)
  - Input validation quality (argparse, error handling, type checking)
- Add 53 unit tests with 850 lines of test code
- Update quality_scorer.py to integrate Security dimension (20% weight)
- Rebalance all dimensions from 25% to 20% (5 dimensions total)
- Update tier requirements:
  - POWERFUL: Security ≥70
  - STANDARD: Security ≥50
  - BASIC: Security ≥40
- Update documentation (quality-scoring-rubric.md, tier-requirements-matrix.md)
- Version bump to 2.0.0

This addresses the feedback from PR #420 by providing a focused, well-tested
implementation of the Security dimension without bundling other changes.
 2026-03-26 13:25:27 +00:00
Reza Rezvani
86fc905e97 chore: sync cross-platform indexes, regenerate docs, fix plugin.json counts 
- Codex CLI: 174 skills synced, 11 new symlinks
- Gemini CLI: 262 items synced, 11 new
- engineering plugin.json: 33 → 35 skills
- engineering-team plugin.json: 28 → 29 skills
- Docs regenerated: 261 pages (214 skills + 25 agents + 22 commands)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-25 15:42:39 +01:00
Reza Rezvani
f352e8cdd0 fix: trim 3 SKILL.md files to comply with Anthropic 500-line limit 
Per Anthropic docs: "Keep SKILL.md under 500 lines. Move detailed
reference material to separate files."

- browser-automation: 564 → 266 lines (moved examples to references/)
- spec-driven-workflow: 586 → 333 lines (moved full spec example to references/)
- security-pen-testing: 850 → 306 lines (condensed OWASP/attack details, moved to references/)

No content deleted — all moved to existing reference files with pointers.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-25 15:20:47 +01:00
Reza Rezvani
268061b0fd fix: move browser-automation and spec-driven-workflow scripts to scripts/ directory 
Validator expects scripts in scripts/ subdirectory, not at skill root.
Moved 6 scripts to match repo convention.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-25 14:53:14 +01:00
Reza Rezvani
43bb5c4d59 Merge branch 'feature/sprint-phase-3-gaps' into dev 
# Conflicts:
#	docs/skills/engineering-team/index.md
#	docs/skills/engineering/index.md
#	mkdocs.yml
 2026-03-25 14:23:21 +01:00
Alireza Rezvani
c1b2aacb74 Merge pull request #408 from alirezarezvani/feature/sprint-improvements 
improve(engineering): enhance 5 existing skills — tdd-guide, env-secrets-manager, senior-secops, database-designer, senior-devops
 2026-03-25 14:22:04 +01:00
Alireza Rezvani
ea2b33ab52 Merge pull request #407 from alirezarezvani/feature/sprint-phase-2-cloud 
feat(engineering-team): add azure-cloud-architect, security-pen-testing; extend terraform-patterns
 2026-03-25 14:22:01 +01:00
Reza Rezvani
87f3a007c9 feat(engineering,ra-qm): add secrets-vault-manager, sql-database-assistant, gcp-cloud-architect, soc2-compliance 
secrets-vault-manager (403-line SKILL.md, 3 scripts, 3 references):
- HashiCorp Vault, AWS SM, Azure KV, GCP SM integration
- Secret rotation, dynamic secrets, audit logging, emergency procedures

sql-database-assistant (457-line SKILL.md, 3 scripts, 3 references):
- Query optimization, migration generation, schema exploration
- Multi-DB support (PostgreSQL, MySQL, SQLite, SQL Server)
- ORM patterns (Prisma, Drizzle, TypeORM, SQLAlchemy)

gcp-cloud-architect (418-line SKILL.md, 3 scripts, 3 references):
- 6-step workflow mirroring aws-solution-architect for GCP
- Cloud Run, GKE, BigQuery, Cloud Functions, cost optimization
- Completes cloud trifecta (AWS + Azure + GCP)

soc2-compliance (417-line SKILL.md, 3 scripts, 3 references):
- SOC 2 Type I & II preparation, Trust Service Criteria mapping
- Control matrix generation, evidence tracking, gap analysis
- First SOC 2 skill in ra-qm-team (joins GDPR, ISO 27001, ISO 13485)

All 12 scripts pass --help. Docs generated, mkdocs.yml nav updated.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-25 14:05:11 +01:00
Reza Rezvani
67e2bfabfa improve(engineering): enhance tdd-guide, env-secrets-manager, senior-secops, database-designer, senior-devops 
tdd-guide (164 → 412 lines):
- Spec-first workflow, per-language examples (TS/Python/Go)
- Bounded autonomy rules, property-based testing, mutation testing

env-secrets-manager (78 → 260 lines):
- Cloud secret store integration (Vault, AWS SM, Azure KV, GCP SM)
- Secret rotation workflow, CI/CD injection, pre-commit detection, audit logging

senior-secops (422 → 505 lines):
- OWASP Top 10 quick-check, secret scanning tools comparison
- Supply chain security (SBOM, Sigstore, SLSA levels)

database-designer (66 → 289 lines):
- Query patterns (JOINs, CTEs, window functions), migration patterns
- Performance optimization (indexing, EXPLAIN, N+1, connection pooling)
- Multi-DB decision matrix, sharding & replication

senior-devops (275 → 323 lines):
- Multi-cloud cross-references (AWS, Azure, GCP architects)
- Cloud-agnostic IaC section (Terraform/OpenTofu, Pulumi)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-25 13:49:25 +01:00
Reza Rezvani
2056ba251f feat(engineering-team): add azure-cloud-architect, security-pen-testing; extend terraform-patterns 
azure-cloud-architect (451-line SKILL.md, 3 scripts, 3 references):
- 6-step workflow mirroring aws-solution-architect for Azure
- Bicep/ARM templates, AKS, Functions, Cosmos DB, cost optimization
- architecture_designer.py, cost_optimizer.py, bicep_generator.py

security-pen-testing (850-line SKILL.md, 3 scripts, 3 references):
- OWASP Top 10 systematic audit, offensive security testing
- XSS/SQLi/SSRF/IDOR detection, secret scanning, API security
- vulnerability_scanner.py, dependency_auditor.py, pentest_report_generator.py
- Responsible disclosure workflow included

terraform-patterns extended (487 → 740 lines):
- Multi-cloud provider configuration
- OpenTofu compatibility notes
- Infracost integration for PR cost estimation
- Import existing infrastructure patterns
- Terragrunt DRY multi-environment patterns

Updated engineering-team plugin.json (26 → 28 skills).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-25 13:32:22 +01:00
Reza Rezvani
97952ccbee feat(engineering): add browser-automation and spec-driven-workflow skills 
browser-automation (564-line SKILL.md, 3 scripts, 3 references):
- Web scraping, form filling, screenshot capture, data extraction
- Anti-detection patterns, cookie/session management, dynamic content
- scraping_toolkit.py, form_automation_builder.py, anti_detection_checker.py
- NOT testing (that's playwright-pro) — this is automation & scraping

spec-driven-workflow (586-line SKILL.md, 3 scripts, 3 references):
- Spec-first development: write spec BEFORE code
- Bounded autonomy rules, 6-phase workflow, self-review checklist
- spec_generator.py, spec_validator.py, test_extractor.py
- Pairs with tdd-guide for red-green-refactor after spec

Updated engineering plugin.json (31 → 33 skills).
Added both to mkdocs.yml nav and generated docs pages.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-25 12:57:18 +01:00
Reza Rezvani
ce1d7925cc feat(engineering): integrate focused-fix skill — docs, command, agent, marketplace 
- Normalize SKILL.md frontmatter to repo standard (remove non-standard
  license, metadata.* fields; inline description)
- Generate docs page (docs/skills/engineering/focused-fix.md)
- Add to mkdocs.yml nav (skills + commands)
- Create /focused-fix slash command (commands/ + .claude/commands/)
- Add to cs-senior-engineer agent (skill integration + new workflow #4)
- Update marketplace.json and plugin.json descriptions (30 → 31 skills)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-23 13:59:30 +01:00
Reza Rezvani
e065a8c4d0 feat(engineering): add focused-fix — deep-dive feature repair skill 
5-phase protocol (SCOPE → TRACE → DIAGNOSE → FIX → VERIFY) for
systematically repairing entire features/modules. Includes bidirectional
dependency tracing, root-cause confirmation, risk labeling, 3-strike
architecture escalation, and phase-skip guards.

Cherry-picked from PR #388 (avinashchby).

Co-Authored-By: avinashchby <24788443+avinashchby@users.noreply.github.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-23 13:14:51 +01:00
Reza Rezvani
193f71e56f fix: correct broken install paths, improve skill descriptions, standardize counts 
Cherry-picked from PR #387 (ssmanji89) and rebased on dev.

- Fix 6 wrong PM skill install paths in INSTALLATION.md
- Fix content-creator → content-production script paths
- Fix senior-devops CLI flags to match actual deployment_manager.py
- Replace vague descriptions with trigger-oriented "Use when..." on 7 engineering skills
- Standardize skill count 170 → 205+, finance 1 → 2, version 2.1.1 → 2.1.2
- Use python3 instead of python for macOS compatibility
- Remove broken integrations/ link in README.md

Excluded: *.zip gitignore wildcard (overrides intentional design decision)

Co-Authored-By: sully <ssmanji89@gmail.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-23 11:57:40 +01:00
Reza Rezvani
ea04644987 fix(plugins): change author from string to object in plugin.json 
Claude Code plugin manifest requires author as {"name": "..."}, not a
plain string. Fixes install error: "author: Invalid input: expected
object, received string"

Affected: agenthub, a11y-audit

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-19 09:02:28 +01:00
Reza Rezvani
4709662631 feat(marketplace): add 6 missing standalone plugins — total 22→28 
Added to marketplace:
- a11y-audit (WCAG 2.2 accessibility audit)
- executive-mentor (adversarial thinking partner)
- docker-development (Dockerfile, compose, multi-stage)
- helm-chart-builder (Helm chart scaffolding)
- terraform-patterns (IaC module design)
- research-summarizer (structured research synthesis)

Also fixed version 1.0.0 → 2.1.2 on 4 plugin.json files
(executive-mentor, docker-development, helm-chart-builder, research-summarizer)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-18 09:01:31 +01:00
Reza Rezvani
6453a29ecf fix(security-auditor): reduce false positives — whitelist plugin dirs, remove 'token' from exfil pattern 
- Add .claude-plugin, .codex, .gemini to hidden file allowlist (FS-HIDDEN)
  These are required plugin infrastructure directories, not secrets.
- Remove 'tokens?' from PROMPT-EXFIL regex — 'access token' is a standard
  technical term in auth reference docs, causing false positives on every
  skill that documents JWT/OAuth flows (e.g. saas-scaffolder auth-billing-guide)
- Remaining PROMPT-EXFIL patterns (credentials, secrets, api_keys, .env, .ssh,
  .aws, ~/home, /etc) are specific enough to catch real threats

Fixes: CI security audit failure on PR #370 (7 CRITICAL false positives)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-17 15:43:37 +01:00
Reza Rezvani
2f57ef8948 feat(agenthub): add AgentHub plugin with cross-domain examples, SEO optimization, and docs site fixes 
- AgentHub: 13 files updated with non-engineering examples (content drafts,
  research, strategy) — engineering stays primary, cross-domain secondary
- AgentHub: 7 slash commands, 5 Python scripts, 3 references, 1 agent,
  dry_run.py validation (57 checks)
- Marketplace: agenthub entry added with cross-domain keywords, engineering
  POWERFUL updated (25→30), product (12→13), counts synced across all configs
- SEO: generate-docs.py now produces keyword-rich <title> tags and meta
  descriptions using SKILL.md frontmatter — "Claude Code Skills" in site_name
  propagates to all 276 HTML pages
- SEO: per-domain title suffixes (Agent Skill for Codex & OpenClaw, etc.),
  slug-as-title cleanup, domain label stripping from titles
- Broken links: 141→0 warnings — new rewrite_skill_internal_links() converts
  references/, scripts/, assets/ links to GitHub source URLs; skills/index.md
  phantom slugs fixed (6 marketing, 7 RA/QM)
- Counts synced: 204 skills, 266 tools, 382 refs, 16 agents, 17 commands,
  21 plugins — consistent across CLAUDE.md, README.md, docs/index.md,
  marketplace.json, getting-started.md, mkdocs.yml
- Platform sync: Codex 163 skills, Gemini 246 items, OpenClaw compatible

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-17 12:10:46 +01:00
Reza Rezvani
de724ae5c4 fix(terraform-patterns): align plugin.json version to repo versioning (2.1.2) 
Review gate flagged version 1.0.0 as non-compliant with CLAUDE.md rule:
"Version follows repo versioning." Updated to 2.1.2.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-16 16:10:07 +01:00
Leo
dac49ee9f9 feat(skills): add terraform-patterns agent skill 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-15 23:29:01 +01:00
Leo
0c31067556 feat(skills): add helm-chart-builder agent skill 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-15 23:28:54 +01:00
Leo
5aaf3e5e0b seo: optimize all 9 pack descriptions — add Gemini CLI, Cursor, OpenClaw keywords + 'agent skill/plugin' framing 
Consistent format: '<N> <domain> agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw'
Updated both SKILL.md frontmatter and plugin.json for each pack.
 2026-03-15 23:22:14 +01:00
Leo
bf1473b1be feat(skills): add research-summarizer and docker-development agent skills 
research-summarizer (product-team/):
- Structured research summarization for papers, articles, reports
- Slash commands: /research:summarize, /research:compare, /research:cite
- Python tools: extract_citations.py (5 citation formats), format_summary.py (6 templates)
- References: summary-templates.md, citation-formats.md

docker-development (engineering/):
- Dockerfile optimization, compose orchestration, container security
- Slash commands: /docker:optimize, /docker:compose, /docker:security
- Python tools: dockerfile_analyzer.py (15 rules), compose_validator.py (best practices)
- References: dockerfile-best-practices.md, compose-patterns.md

Both skills include .claude-plugin/plugin.json and follow POWERFUL tier conventions.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-15 22:47:16 +01:00
Reza Rezvani
7911cf957a feat(autoresearch-agent): fix critical bugs, package as plugin with 5 slash commands 
**Bug fixes (run_experiment.py):**
- Fix broken revert logic: was saving HEAD as pre_commit (no-op revert),
  now uses git reset --hard HEAD~1 for correct rollback
- Remove broken --loop mode (agent IS the loop, script handles one iteration)
- Fix shell injection: all git commands use subprocess list form
- Replace shell tail with Python file read

**Bug fixes (other scripts):**
- setup_experiment.py: fix shell injection in git branch creation,
  remove dead --skip-baseline flag, fix evaluator docstring parsing
- log_results.py: fix 6 falsy-zero bugs (baseline=0 treated as None),
  add domain_filter to CSV/markdown export, move import time to top
- evaluators: add FileNotFoundError handling, fix output format mismatch
  in llm_judge_copy, add peak_kb on macOS, add ValueError handling

**Plugin packaging (NEW):**
- plugin.json, settings.json, CLAUDE.md for plugin registry
- 5 slash commands: /ar:setup, /ar:run, /ar:loop, /ar:status, /ar:resume
- /ar:loop supports user-selected intervals (10m, 1h, daily, weekly, monthly)
- experiment-runner agent for autonomous loop iterations
- Registered in marketplace.json as plugin #20

**SKILL.md rewrite:**
- Replace ambiguous "Loop Protocol" with clear "Agent Protocol"
- Add results.tsv format spec, strategy escalation, self-improvement
- Replace "NEVER STOP" with resumable stopping logic

**Docs & sync:**
- Codex (157 skills), Gemini (229 items), convert.sh all pick up the skill
- 6 new MkDocs pages, mkdocs.yml nav updated
- Counts updated: 17 agents, 22 slash commands

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-13 14:38:59 +01:00
Leo
12591282da refactor: autoresearch-agent v2.0 — multi-experiment, multi-domain, real-world evaluators 
Major rewrite based on deep study of Karpathy's autoresearch repo.

Architecture changes:
- Multi-experiment support: .autoresearch/{domain}/{name}/ structure
- Domain categories: engineering, marketing, content, prompts, custom
- Project-level (git-tracked, shareable) or user-level (~/.autoresearch/) scope
- User chooses scope during setup, not installation

New evaluators (8 ready-to-use):
- Free: benchmark_speed, benchmark_size, test_pass_rate, build_speed, memory_usage
- LLM judge (uses existing subscription): llm_judge_content, llm_judge_prompt, llm_judge_copy
- LLM judges call user's CLI tool (claude/codex/gemini) — no extra API keys needed

Script improvements:
- setup_experiment.py: --domain, --scope, --evaluator, --list, --list-evaluators
- run_experiment.py: --experiment domain/name, --resume, --loop, --single
- log_results.py: --dashboard, --domain, --format csv|markdown|terminal, --output

Results export:
- Terminal (default), CSV, and Markdown formats
- Per-experiment, per-domain, or cross-experiment dashboard view

SKILL.md rewritten:
- Clear activation triggers (when the skill should activate)
- Practical examples for each domain
- Evaluator documentation with cost transparency
- Simplified loop protocol matching Karpathy's original philosophy
 2026-03-13 08:22:29 +01:00
Leo
a799d8bdb8 feat: add autoresearch-agent — autonomous experiment loop for ML, prompt, code & skill optimization 
Inspired by Karpathy's autoresearch. The agent modifies a target file, runs a
fixed evaluation, keeps improvements (git commit), discards failures (git reset),
and loops indefinitely — no human in the loop.

Includes:
- SKILL.md with setup wizard, 4 domain configs, experiment loop protocol
- 3 stdlib-only Python scripts (setup, run, log — 687 lines)
- Reference docs: experiment domains guide, program.md templates

Domains: ML training (val_bpb), prompt engineering (eval_score),
code performance (p50_ms), agent skill optimization (pass_rate).

Cherry-picked from feat/autoresearch-agent and rebased onto dev.
Fixes: timeout inconsistency (2x→2.5x), results.tsv tracking clarity,
zero-metric edge case, installation section aligned with multi-tool support.
 2026-03-13 07:21:44 +01:00
Leo
5a34d661aa fix(engineering): address Claude Code review findings 
- performance-profiler: add Quick Start section with script usage examples
- interview-system-designer: fix references to match actual filenames
 2026-03-11 20:46:48 +01:00
Leo
93eee35b83 fix(engineering): improve interview-system-designer - add scripts + extract references 2026-03-11 20:25:11 +01:00
Leo
dc61de798d fix(engineering): improve runbook-generator - add scripts + extract references 2026-03-11 20:24:23 +01:00
Leo
6f55bc4fd6 fix(engineering): improve env-secrets-manager - add scripts + extract references 2026-03-11 20:23:50 +01:00
Leo
bafb155334 fix(engineering): improve agent-workflow-designer - add scripts + extract references 2026-03-11 20:23:01 +01:00
Leo
9e590c81fb fix(engineering): improve monorepo-navigator - add scripts + extract references 2026-03-11 20:22:16 +01:00
Leo
abab3b528e fix(engineering): improve codebase-onboarding - add scripts + extract references 2026-03-11 20:21:34 +01:00
Leo
60ad9d3873 fix(engineering): improve performance-profiler - add scripts + extract references 2026-03-11 20:20:26 +01:00
Leo
a851de0f94 fix(security): add disclaimers to sample code and scaffolding templates 
- payment_processor.py: add disclaimer header + replace realistic-looking keys with EXAMPLE_NOT_REAL
- project_scaffolder.py: add SCAFFOLDING PLACEHOLDER comments to generated secrets
- pipeline_orchestrator.py: no change needed (compile() used for syntax validation only)
 2026-03-11 20:18:27 +01:00