firefrost-gaming/claude-skills-reference
3
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
521 Commits 1 Branch 0 Tags
d69e233ff328a6913bc852107dfad69585584000
Commit Graph

521 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
alirezarezvani
d69e233ff3 chore: sync codex skills symlinks [automated] 2026-03-18 07:31:01 +00:00
Reza Rezvani
de7723036a Revert "feat(engineering): add review-fix-a11y skill (WCAG 2.2 a11y audit + fix) (#375)" 
This reverts commit 49c9f2109f.
 2026-03-18 08:30:27 +01:00
alirezarezvani
827027b19b chore: sync codex skills symlinks [automated] 2026-03-18 07:20:54 +00:00
ivanopenclaw223-alt
49c9f2109f feat(engineering): add review-fix-a11y skill (WCAG 2.2 a11y audit + fix) (#375) 
Adds review-fix-a11y (WCAG 2.2 a11y audit + fix) and free-llm-api skills.

Includes:
- review-fix-a11y: WCAG 2.2 audit workflow, a11y_audit.py scanner, contrast_checker.py
- free-llm-api: ChatAnywhere, Groq, Cerebras, OpenRouter, llm-mux, One API setup
- secret_scanner.py upgrade with secrets-patterns-db integration (1,600+ patterns)

Co-authored-by: ivanopenclaw223-alt <ivanopenclaw223-alt@users.noreply.github.com>
 2026-03-18 08:20:44 +01:00
Leo
115c6dc5ff fix: add missing plugin.json files and restore trailing newlines 
- Add plugin.json for review-fix-a11y skill
- Add plugin.json for free-llm-api skill
- Restore POSIX-compliant trailing newlines in JSON index files
 2026-03-18 08:20:18 +01:00
Reza Rezvani
eb4943060e fix(marketplace): restore agenthub entry lost during PR #369 merge conflict resolution 
The agenthub marketplace entry was added in commit 2f57ef8 but dropped
when PR #369 (code-to-prd) merged with a conflict in marketplace.json.
Re-adds the entry with all cross-domain keywords and 7 slash commands.

Total plugins: 22 (was 21)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-17 15:57:48 +01:00
Alireza Rezvani
c5844c8224 Merge pull request #370 from alirezarezvani/feat/plugin-audit-command 
feat(commands): add /plugin-audit — 8-phase validation pipeline
 2026-03-17 15:54:18 +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
920e8547af feat(commands): add /plugin-audit — 8-phase validation pipeline for skills and plugins 
- Add commands/plugin-audit.md (distributable) + .claude/commands/plugin-audit.md (local invocation)
- 8 phases: discovery, structure validation, quality scoring, script testing,
  security audit, marketplace compliance, ecosystem integration, domain code review
- Auto-fixes non-critical issues, only prompts user for breaking changes
- Integrates skill_validator.py, quality_scorer.py, script_tester.py, skill_security_auditor.py
- Domain-appropriate review via cs-* agents (engineering, product, marketing, etc.)
- Update product-team counts: 12→14 skills, 13→16 tools, 7→8 commands
- Add /code-to-prd and /plugin-audit to mkdocs.yml nav
- Regenerate docs (248 pages, 19 commands)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-17 15:38:00 +01:00
alirezarezvani
434e889d22 chore: sync codex skills symlinks [automated] 2026-03-17 12:24:42 +00:00
Alireza Rezvani
6058596ab8 Merge pull request #369 from alirezarezvani/feat/code-to-prd 
feat(product-team): add code-to-prd skill — reverse-engineer any codebase into PRD
 2026-03-17 13:24:30 +01:00
Alireza Rezvani
25095cbde6 Merge branch 'dev' into feat/code-to-prd 2026-03-17 13:24:13 +01:00
Reza Rezvani
fd1d86ba0b fix(code-to-prd): achieve 97.6 validator score — frontmatter, sections, expected outputs 
- SKILL.md frontmatter: add Name, Tier, Category, Dependencies, Author,
  Version as capitalized top-level keys (validator requirement)
- SKILL.md sections: add Name and Description headings (validator requirement)
- Add expected_outputs/ with 3 sample files: PRD README, page doc, enum dict
- prd_scaffolder.py: add validate_analysis(), --validate-only, --dry-run
  flags, structured print_summary() — now 333 LOC (was 255, within 300-500)
- Add scripts/.gitignore to exclude generated prd/ test output

Scores: validator 65→97.6 (EXCELLENT), quality 51→73.2 (B-), scripts 2/2 PASS

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-17 13:18:33 +01:00
Reza Rezvani
530ecab247 fix(code-to-prd): pass skill-tester validation — README, assets, frontmatter, imports 
- Add README.md with quick start, framework table, output structure
- Add assets/sample-analysis.json for script testing
- Expand SKILL.md frontmatter with version, author, category, tier, dependencies
- Add Features, Usage, Examples sections to SKILL.md
- Remove __future__ imports, fix str|None → Optional[str] for Python 3.9 compat
- Validation: 65→85.7, quality: 51→62.1, scripts: 2/2 PASS

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-17 12:43:22 +01:00
Reza Rezvani
4b7a084ee3 feat(code-to-prd): expand to fullstack — add NestJS, Django, Express, FastAPI support 
- Rename frontend_analyzer.py → codebase_analyzer.py — now detects backend
  frameworks via package.json (NestJS, Express, Fastify) and project files
  (manage.py, requirements.txt for Django, FastAPI, Flask)
- Add backend route extraction: NestJS @Controller/@Get decorators,
  Django urls.py path() patterns
- Add model/entity extraction: Django models.Model fields, NestJS @Entity
  and DTO classes
- Add stack_type detection (frontend / backend / fullstack) to analysis output
- SKILL.md: add Supported Stacks table, backend directory guide, backend
  endpoint inventory template, backend page type strategies, backend pitfalls
- references/framework-patterns.md: add NestJS, Express, Django, DRF, FastAPI
  pattern tables + database model patterns + backend validation patterns
- references/prd-quality-checklist.md: add backend-specific checks (endpoints,
  DTOs, models, admin, middleware, migrations)
- Update all descriptions and keywords across plugin.json, settings.json,
  marketplace.json, and /code-to-prd command

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-17 12:28:30 +01:00
Reza Rezvani
70ada54c95 feat(code-to-prd): add ecosystem integration — command, settings, marketplace 
- Fix plugin.json version: 1.0.0 → 2.1.2 (repo versioning)
- Add /code-to-prd slash command (4-step workflow: analyze → scaffold → fill → finalize)
- Add settings.json with command registration and platform metadata
- Add code-to-prd entry to marketplace.json with keywords and category

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-17 12:20:16 +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
Leo
e6c7b0b87d docs(code-to-prd): add attribution to @lihanglogan as inspiration source 
Credits the original code-to-prd concept and methodology from
https://github.com/lihanglogan/code-to-prd (PR #368).
 2026-03-17 12:04:56 +01:00
Leo
164749cb73 feat(code-to-prd): add analysis scripts, references, and tooling docs 
- frontend_analyzer.py: scans codebase for routes, APIs, enums, framework detection
- prd_scaffolder.py: generates PRD directory with README, page stubs, appendix
- references/framework-patterns.md: React, Next.js, Vue, Nuxt, Angular, Svelte patterns
- references/prd-quality-checklist.md: validation checklist for generated PRDs
- SKILL.md updated with tooling section

Both scripts are stdlib-only (no pip install).
 2026-03-17 12:00:56 +01:00
Leo
e153e818b4 feat(product-team): add code-to-prd skill — reverse-engineer frontend into PRD 
Analyzes routes, components, state, APIs, and interactions to generate
complete Product Requirements Documents. Framework-agnostic (React, Vue,
Angular, Svelte, Next.js, Nuxt). Three-phase workflow: global scan,
page-by-page deep analysis, structured doc generation.

Inspired by community contribution (PR #368) but rebuilt from scratch
in English with enhanced coverage for mock API detection, field
interdependencies, and execution pacing strategies.
 2026-03-17 11:56:07 +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
alirezarezvani
95ed1831f2 chore: sync codex skills symlinks [automated] 2026-03-15 22:29:36 +00:00
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
d20ba9a2fe seo: add OpenClaw skills guide — target 'openclaw skills' and 'openclaw plugins' keywords 2026-03-15 23:12:10 +01:00
Leo
173c1040c9 seo: restore 'Claude Code Skills' in H1 + key headings — preserve existing rankings while adding agent/plugin keywords 2026-03-15 22:49:34 +01:00
alirezarezvani
3dc244463c chore: sync codex skills symlinks [automated] 2026-03-15 21:48:01 +00:00
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
Leo
2b5260dbeb seo: add plugin/skill guides for Claude Code, Codex, Gemini CLI, Cursor + autoresearch program 2026-03-15 22:41:44 +01:00
Leo
77c2dbcd97 seo: rebrand to 'Agent Skills & Plugins' — expand keyword coverage for plugins, codex, gemini, cursor 2026-03-15 22:37:09 +01:00
Leo
a6f428cb0d refine(personas): rewrite with original voice — opinionated colleagues, not job descriptions 
- Cut 70% bloat (750 lines removed, 220 added)
- Dropped corporate sections (Core Capabilities, Decision Framework → merged naturally)
- Commands as the centerpiece — what you DO, not what you ARE
- 'How You Think' + 'What You Never Do' = personality, not résumé
- 'When to Use Me' with ✅/❌ = clear routing
- 'What Good Looks Like' = success without corporate metric tables

Our format: opinionated colleague with tools
Agency-agents format: job description with capabilities
Different on purpose.
 2026-03-14 00:49:21 +01:00
Leo
da734fe9dd refine(personas): add Core Capabilities, Decision Framework, Success Metrics 
Aligns new personas with agency-agents structure:
- Core Capabilities: scannable bullet-list summary
- Decision Framework: when to use (and when NOT to)
- Success Metrics: quantified outcomes

All 4 Tier 1 personas now match full agency-agents spec.
 2026-03-14 00:42:47 +01:00
Leo
8a14a069d0 feat(personas): add 4 Tier 1 personas with bundled skills and direct commands 
- Content Strategist: 6 commands (/content:audit, cluster, brief, calendar, repurpose, seo), 8 bundled skills
- Product Manager: 7 commands (/pm:story, prd, prioritize, experiment, sprint, retro, metrics), 6 bundled skills
- DevOps Engineer: 7 commands (/devops:deploy, infra, docker, monitor, incident, security, cost), 4 bundled skills
- Finance Lead: 6 commands (/finance:model, fundraise, pricing, burn, unit-economics, board), 2 bundled skills

Total personas: 3 → 7
 2026-03-14 00:38:52 +01:00
Leo
a1eb8f1f3a fix: remove unused numpy/scipy imports, delete duplicate zip file 
- quality_effectiveness_monitor.py: removed numpy/scipy (imported but never used, violates stdlib-only rule)
- epic-design.zip: removed binary duplicate of skill folder
 2026-03-13 23:03:53 +01:00
alirezarezvani
17cfff3e36 chore: sync codex skills symlinks [automated] 2026-03-13 22:03:24 +00:00
Alireza Rezvani
3c460b6583 Merge pull request #353 from abbasmir12/feat/epic-design 
feat(engineering-team): add epic-design skill with asset pipeline
 2026-03-13 23:03:13 +01:00
Alireza Rezvani
d5bcc223b4 Merge pull request #351 from sudabg/feat/ra-qm-production-tools 
feat: add 5 production Python tools for RA/QM skills (#238)
 2026-03-13 23:03:02 +01:00
Abbas Mir
00ef4fe1c8 Update SKILL.md 2026-03-14 00:17:35 +05:00
abbasmir12
2f6b037cf2 feat(engineering-team): add epic-design skill with asset pipeline 2026-03-13 18:13:50 +00:00
sudabg
2834e6868a ci: trigger workflow rerun for PR #351 2026-03-13 23:32:08 +08:00
sudabg
059f91f1a4 feat: add 5 production Python tools for RA/QM skills (#238) 
Add comprehensive CLI tools for regulatory affairs and quality management:

1. regulatory-affairs-head/scripts/regulatory_pathway_analyzer.py
   - FDA/EU MDR/UK UKCA/Health Canada/TGA pathway analysis
   - Timeline & cost estimation, optimal submission sequence

2. capa-officer/scripts/root_cause_analyzer.py
   - 5-Why, Fishbone, Fault Tree analysis methods
   - Auto-generates CAPA recommendations

3. risk-management-specialist/scripts/fmea_analyzer.py
   - ISO 14971 / IEC 60812 compliant FMEA
   - RPN calculation, risk reduction strategies

4. quality-manager-qmr/scripts/quality_effectiveness_monitor.py
   - QMS metric tracking, trend analysis
   - Predictive alerts, management review summaries

5. quality-documentation-manager/scripts/document_version_control.py
   - Semantic versioning, change control
   - Electronic signatures, document matrix

All tools: argparse CLI, JSON I/O, demo mode, dataclasses, docstrings.

Closes #238
 2026-03-13 22:26:03 +08:00
Alireza Rezvani
536c3df481 Merge pull request #349 from alirezarezvani/feat/autoresearch-plugin 
feat: autoresearch-agent — bug fixes, plugin packaging, 5 slash commands
 2026-03-13 14:41:13 +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
alirezarezvani
6dc25df8fa chore: sync codex skills symlinks [automated] 2026-03-13 09:09:31 +00:00
Alireza Rezvani
236201a155 Merge pull request #346 from alirezarezvani/feat/autoresearch-v2 
refactor: autoresearch-agent v2.0 — multi-experiment, multi-domain, real-world evaluators
 2026-03-13 10:09:20 +01:00
Alireza Rezvani
7af13f8137 Merge pull request #347 from alirezarezvani/feat/custom-gpt-cleanup 
feat: Custom GPTs page, gitignore configs, SEO README, cross-references
 2026-03-13 10:08:50 +01:00
Leo
82eea60947 feat: Custom GPTs page, gitignore configs, SEO README, cross-references 
- Gitignore individual GPT config files (custom-gpt/*-gpt.md) — instructions
  should not be publicly exposed
- Rewrite custom-gpt/README.md with SEO-optimized descriptions and live
  ChatGPT links for all 6 GPTs
- New docs page: docs/custom-gpts.md with grid cards, comparison table,
  and stats
- Add Custom GPTs to mkdocs.yml navigation
- Cross-reference Custom GPTs from:
  - Homepage (new grid card)
  - Getting Started (FAQ entry)
  - Personas page (try in ChatGPT callout)
  - Plugins page (FAQ entry)

Live GPT links:
- Solo Founder: chatgpt.com/g/g-69b315...
- SEO Audit Expert: chatgpt.com/g/g-69b3b0...
- Content Strategist: chatgpt.com/g/g-69b3af...
- Product Manager Toolkit: chatgpt.com/g/g-69b32c...
- Conversion Copywriter: chatgpt.com/g/g-69b327...
- CTO Advisor: chatgpt.com/g/g-69b326...
 2026-03-13 10:08:22 +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
alirezarezvani
c834d71a44 chore: sync codex skills symlinks [automated] 2026-03-13 06:40:49 +00:00