7c54a72d94
Post-merge sync of v2.7.3 (#679 already in dev). Three things in one commit: ## 1. /update-docs pipeline (Steps 1-7) Cross-platform sync verified clean across 3 platforms (.codex 305 / .gemini 355 / .hermes 305 — aeo + security-guidance present in all three indexes). 401 → 403 MkDocs pages generated. **Files refreshed to v2.7.3 / 313 / 46+ / 60+ counts:** - `.claude-plugin/marketplace.json` — top-level description + metadata description + metadata.version (was 2.7.0). - `CLAUDE.md` — Current Scope line, new v2.7.3 Highlights section, footer (Last Updated + Version + Status). - `README.md` — tagline, badges, Skills Overview row counts (Engineering POWERFUL 44 → 45, Marketing 44 → 45 w/ 8 pods), Python Tools count, FAQ counts. Hermes footnote ticked v2.7.2 → v2.7.3. - `docs/index.md` — title, meta description, hero subtitle, grid card. - `docs/getting-started.md` — meta description, FAQ count. - `mkdocs.yml` — site_description + 3 nav entries (skill + agent + cmd). - `marketing-skill/.claude-plugin/plugin.json` — 44 → 45 skills, 7 → 8 pods, v2.2.3 → v2.7.3. - `marketing-skill/CLAUDE.md` — 43 → 45 skill count, 32 → 58 Python tools, 7 → 8 pods. Added AEO skill to skill map. ## 2. /plugin-audit on both new skills (full 8-phase pipeline) **aeo (marketing-skill/skills/aeo/)** — PASS WITH WARNINGS: - Phase 2 Structure: 86.4/GOOD (after auto-fix of YAML frontmatter parse error — colon in description value needed quote-wrapping) - Phase 3 Quality: 52.4/D (validator expects legacy fields v2.7 skills don't use — repo-wide pattern, not a defect) - Phase 4 Scripts: 3/3 PASS - Phase 5 Security: 2 HIGH NET-EXFIL findings on urllib.request — same known false-positive as sister seo-audit skill (URL fetch is core functionality for content-audit-by-URL tools, not exfiltration) - Phase 6 Marketplace: plugin.json valid (v2.7.3, all required fields) - Phase 7 Ecosystem: indexed in all 3 platforms - Phase 8 Code Review: 22 workflow sections, refs cite 8/17/37 sources (≥7 floor met), 0 broken links, attribution present **security-guidance (engineering/security-guidance/)** — PASS WITH WARNINGS: - Phase 2/3/4: low scores due to hook-plugin layout mismatch with script-plugin validators (hook plugins use `hooks/` not `scripts/` per Claude Code spec — fundamental structural mismatch, not a defect) - Phase 5: 6 CRITICAL + 4 HIGH findings are all recursive false- positives — auditor detects the hook's OWN pattern-detection strings (`"exec("`, `"eval("`, `"yaml.load("` are substring literals used as detection rules, NOT actual calls). Verified zero real exec/eval calls in the file. - Phase 6/7: clean (plugin.json valid, hooks.json valid, indexed in all 3 platforms, mkdocs nav entry added) - Phase 8: 291 LOC, syntax valid, clear exit-code contract (0=clean, 2=block per Claude Code hook spec), session-state caching @ lines 158-191, 30-day cleanup @ line 163, attribution full, live smoke test (`eval(input())` in Write → exit 2 + warning) PASS - **Real defects: 0.** ## 3. Layout fix (Phase 7 audit catch) The /plugin-audit Phase 7 caught a real layout bug: cs-aeo.md placed at `marketing-skill/agents/cs-aeo.md` and `marketing-skill/commands/ cs-aeo.md` was unreachable by `scripts/generate-docs.py` (which only walks root `agents/<domain>/` and root `commands/`). Result: docs/ pages for cs-aeo agent + /cs:aeo command were never generated. **Moved to repo-canonical locations:** - `marketing-skill/agents/cs-aeo.md` → `agents/marketing/cs-aeo.md` - `marketing-skill/commands/cs-aeo.md` → `commands/cs-aeo.md` Cleaned empty `marketing-skill/agents/` + `marketing-skill/commands/` directories. Re-ran `scripts/generate-docs.py`: 401 → 403 pages (73 agents + 34 commands — both new entries present). ## CHANGELOG.md Added [2.7.3] - 2026-05-17 entry with full Added / Changed / Layout fix / Cross-platform sync / Honest audit results / PRs / Verification sections. Audit results documented verbatim including the known false-positives — no claims of clean security where the auditor flagged patterns it can't disambiguate. https://claude.ai/code/session_01FEUmeuYhmnxVFq7EZM8ZSw
9.5 KiB
| title | description | hide | ||
|---|---|---|---|---|
| 313 Agent Skills for Codex, Gemini CLI & OpenClaw | 313 production-ready Claude Code skills and agent plugins for 12 AI coding tools — including v2.7.3 AEO (Answer Engine Optimization for ChatGPT / Perplexity / Claude / Gemini / Mistral citation) + security-guidance PreToolUse hook, the v2.7.0 megaprompt-derived productivity / marketing / research stacks (capture, email-pair, reflect, landing, pulse, litreview, grants, dossier, patent, syllabus, notebooklm, research orchestrator), and the v2.6.0 Matt Pocock productivity quartet (write-a-skill, caveman, grill-me, handoff). Engineering, product, marketing, compliance, and finance agent skills for Claude Code, OpenAI Codex, Gemini CLI, Hermes Agent, Cursor, and OpenClaw. |
|
Agent Skills
313 production-ready skills, 46+ cs-* agents (incl. founder-mode C-suite, Matt Pocock productivity quartet, v2.7.0 megaprompt-derived research stack, and v2.7.3 cs-aeo), 7 personas, and an orchestration protocol for AI coding tools. { .hero-subtitle }
Get Started{ .md-button .md-button--primary } Browse Skills{ .md-button } GitHub :fontawesome-brands-github:{ .md-button }
Works with
What's Inside
-
:material-toolbox:{ .lg .middle } 313 Skills
Production-ready instruction packages with structured workflows, Python automation tools, and reference documentation across 12 domains. v2.7.3 adds AEO (Answer Engine Optimization for LLM citation) and a security-guidance PreToolUse hook. v2.7.0 added 13 Path-B skills (productivity, marketing, research). v2.6.0 added the Matt Pocock productivity quartet under MIT.
-
:material-robot:{ .lg .middle } 46+ Agents
Multi-skill orchestrators that combine domain expertise for complex tasks — from engineering leads to financial analysts to research-pack routers.
-
:material-account-group:{ .lg .middle } 3 Personas
Role-based identities with curated skill loadouts, decision frameworks, and distinct communication styles.
-
:material-sitemap:{ .lg .middle } Orchestration
A lightweight protocol for coordinating personas, skills, and agents on work that crosses domain boundaries.
-
:material-language-python:{ .lg .middle } 359 Python Tools
CLI scripts that ship with skills — all stdlib-only, zero pip installs, verified working on any platform.
-
:material-puzzle-outline:{ .lg .middle } 30 Plugins
One-command installable bundles for Claude Code, Codex CLI, Gemini CLI, and OpenClaw.
-
:material-console:{ .lg .middle } 33 Commands
Slash commands for common operations — sprint planning, tech debt analysis, PRDs, OKRs, and more.
-
:material-swap-horizontal:{ .lg .middle } 12 Tool Support
Convert all skills to any supported tool's native format with a single script. No manual work.
-
:material-chat-outline:{ .lg .middle } 6 Custom GPTs
Use Agent Skills directly in ChatGPT — no setup needed. Solo Founder, SEO Audit, Content Strategy, CTO Advisor, and more.
Skills by Domain
-
:material-cog:{ .lg .middle } Engineering — Core
Architecture, frontend, backend, fullstack, QA, DevOps, SecOps, AI/ML, data engineering, Playwright testing, self-improving agent
-
:material-lightning-bolt:{ .lg .middle } Engineering — Advanced
Agent designer, RAG architect, database designer, CI/CD builder, MCP server builder, security auditor, tech debt tracker
-
:material-bullseye-arrow:{ .lg .middle } Product
Product manager, agile PO, strategist, UX researcher, UI design system, landing pages, SaaS scaffolder, analytics, experiment designer
-
:material-bullhorn:{ .lg .middle } Marketing
Content, SEO, CRO, channels, growth, intelligence, sales — 7 specialist pods with 32 Python tools
-
:material-clipboard-check:{ .lg .middle } Project Management
Senior PM, scrum master, Jira expert, Confluence expert, Atlassian admin, templates
-
:material-star-circle:{ .lg .middle } C-Level Advisory
Full C-suite (10 roles), orchestration, board meetings, culture frameworks, strategic alignment
-
:material-shield-check:{ .lg .middle } Regulatory & Quality
ISO 13485, MDR 2017/745, FDA, ISO 27001, GDPR, CAPA, risk management, quality documentation
-
:material-trending-up:{ .lg .middle } Business & Growth
Customer success, sales engineer, revenue operations, contracts & proposals
-
:material-currency-usd:{ .lg .middle } Finance
Financial analyst, SaaS metrics coach — DCF valuation, budgeting, forecasting, ARR/MRR/churn/LTV
Why Agent Skills?
-
:material-clock-fast:{ .lg .middle } Zero dependencies
All Python tools use stdlib only. No pip installs, no API keys, no configuration files. Works anywhere Python runs.
-
:material-shield-lock:{ .lg .middle } Security first
Built-in security auditor scans any skill for malicious code, data exfiltration, and prompt injection before installation.
-
:material-rocket-launch:{ .lg .middle } One-command install
Plugin marketplace for Claude Code. Sync scripts for Codex, Gemini, and Hermes Agent. Conversion script for 8 more tools.
-
:material-puzzle:{ .lg .middle } Self-contained
Each skill is independent. No cross-dependencies, no conflicts. Install one or all — they work in isolation.
-
:material-devices:{ .lg .middle } Multi-platform
Native support for 12 AI coding tools. Write once, convert to any tool's format automatically.
-
:material-check-decagram:{ .lg .middle } Production-grade
Structured workflows with validation checkpoints, not generic advice. Each skill covers end-to-end domain processes.
Quick Install
=== "Claude Code"
```bash
# Add the marketplace
/plugin marketplace add alirezarezvani/claude-skills
# Install any skill bundle
/plugin install engineering-skills@claude-code-skills
```
=== "OpenAI Codex"
```bash
npx agent-skills-cli add alirezarezvani/claude-skills --agent codex
```
=== "Gemini CLI"
```bash
git clone https://github.com/alirezarezvani/claude-skills.git
cd claude-skills && ./scripts/gemini-install.sh
```
=== "Hermes Agent"
```bash
git clone https://github.com/alirezarezvani/claude-skills.git
cd claude-skills
python scripts/sync-hermes-skills.py --verbose
# Skills appear in /skills and /<skill-name> automatically
```
=== "Cursor / Windsurf / Aider"
```bash
git clone https://github.com/alirezarezvani/claude-skills.git
cd claude-skills
./scripts/convert.sh --tool cursor # or windsurf, aider
./scripts/install.sh --tool cursor --target /path/to/project
```
Full Install Guide{ .md-button .md-button--primary } Multi-Tool Setup{ .md-button }