@flitzrrr/agent-skills 1.0.0

package/.cursorrules

@@ -0,0 +1,53 @@
+# Agent Skills Hub — Cursor Rules
+# This file makes skills discoverable in Cursor IDE.
+# For detailed skill usage, see CHEATSHEET.md or individual SKILL.md files.
+
+## Available Skills (55 total from 5 sources)
+
+### Security & Code Quality
+- Use `skills/security-review/SKILL.md` for OWASP-based security audits
+- Use `skills/code-review/SKILL.md` for comprehensive code reviews
+- Use `skills/find-bugs/SKILL.md` for bug hunting in local changes
+- Use `skills/gha-security-review/SKILL.md` for GitHub Actions security
+- Use `skills/skill-scanner/SKILL.md` to scan skills for prompt injection
+
+### Git Workflow
+- Use `skills/commit/SKILL.md` for Conventional Commits formatting
+- Use `skills/create-branch/SKILL.md` for branch creation
+- Use `skills/pr-writer/SKILL.md` for PR descriptions
+- Use `skills/iterate-pr/SKILL.md` for CI fix loops
+
+### Django
+- Use `skills/django-access-review/SKILL.md` for access control / IDOR review
+- Use `skills/django-perf-review/SKILL.md` for N+1 and performance review
+
+### Project Planning (Multi-Session)
+- Use `skills/create-plan/SKILL.md` to start a structured project plan
+- Use `skills/resume-plan/SKILL.md` to continue a previous plan
+- Use `skills/update-plan/SKILL.md` to modify plans
+- Use `skills/execute-work-packet/SKILL.md` to execute plan items
+- Use `skills/generate-handover/SKILL.md` for session handoff
+
+### Document Generation
+- Use `skills/anthropic-pdf/SKILL.md` for PDF operations
+- Use `skills/anthropic-docx/SKILL.md` for Word documents
+- Use `skills/anthropic-pptx/SKILL.md` for presentations
+- Use `skills/anthropic-xlsx/SKILL.md` for spreadsheets
+
+### Frontend & React
+- Use `skills/vercel-react-best-practices/SKILL.md` for React/Next.js optimization (62 rules)
+- Use `skills/vercel-web-design-guidelines/SKILL.md` for UI/UX audit (100+ rules)
+- Use `skills/vercel-composition-patterns/SKILL.md` for React component architecture
+- Use `skills/vercel-react-native-skills/SKILL.md` for React Native/Expo
+- Use `skills/anthropic-frontend-design/SKILL.md` for bold UI design
+
+### Developer Tools
+- Use `skills/anthropic-mcp-builder/SKILL.md` to build MCP servers
+- Use `skills/anthropic-webapp-testing/SKILL.md` for Playwright testing
+- Use `skills/anthropic-claude-api/SKILL.md` for Claude API integration
+
+### SEO
+- Use `skills/seo/SKILL.md` for comprehensive SEO auditing (16 sub-skills)
+
+### Deployment
+- Use `skills/vercel-deploy-to-vercel/SKILL.md` for Vercel deployments

package/.lovable

@@ -0,0 +1,30 @@
+# Agent Skills Hub — Lovable Project Instructions
+# This file makes skills available in Lovable AI.
+
+This repository contains 55 curated AI agent skills for code review, security auditing,
+document generation, frontend development, SEO, and project planning.
+
+## How to Use
+
+Each skill is a self-contained folder under `skills/` containing a `SKILL.md` file
+with detailed instructions. When a task matches a skill's domain, read and follow
+the corresponding `SKILL.md`.
+
+## Key Skills for Lovable Projects
+
+### Web Development
+- `skills/vercel-react-best-practices/SKILL.md` — React/Next.js performance (62 rules)
+- `skills/vercel-web-design-guidelines/SKILL.md` — UI/UX accessibility audit
+- `skills/anthropic-frontend-design/SKILL.md` — Premium, non-generic UI design
+- `skills/vercel-composition-patterns/SKILL.md` — React component architecture
+
+### Quality
+- `skills/code-review/SKILL.md` — Code review checklist
+- `skills/security-review/SKILL.md` — Security audit
+- `skills/seo/SKILL.md` — SEO optimization (16 sub-skills)
+
+### Documents
+- `skills/anthropic-pdf/SKILL.md` — PDF creation & editing
+- `skills/anthropic-docx/SKILL.md` — Word document generation
+
+See `CHEATSHEET.md` for the full decision guide.

package/AGENTS.md

@@ -0,0 +1,22 @@
+# Agent Skills Hub
+
+This repository contains 55 curated AI agent skills from 5 sources.
+Skills are located in the `skills/` directory — each contains a `SKILL.md` with instructions.
+
+## Available Skill Categories
+
+- **Security & Code Review**: `security-review`, `code-review`, `find-bugs`, `gha-security-review`
+- **Git Workflow**: `commit`, `create-branch`, `pr-writer`, `iterate-pr`
+- **Django**: `django-access-review`, `django-perf-review`
+- **Planning & Docs**: `create-plan`, `resume-plan`, `execute-work-packet`, `generate-docs`
+- **Documents**: `anthropic-pdf`, `anthropic-docx`, `anthropic-pptx`, `anthropic-xlsx`
+- **Frontend & Design**: `anthropic-frontend-design`, `vercel-react-best-practices`, `vercel-web-design-guidelines`
+- **Developer Tools**: `anthropic-mcp-builder`, `anthropic-webapp-testing`, `anthropic-claude-api`
+- **SEO**: `seo` (16 sub-skills)
+- **Deployment**: `vercel-deploy-to-vercel`
+- **Creative**: `anthropic-algorithmic-art`, `anthropic-canvas-design`, `anthropic-theme-factory`
+
+## Usage
+
+To use a skill, read the `SKILL.md` file in the corresponding `skills/<name>/` directory.
+See `CHEATSHEET.md` for a decision guide on which skill to use when.

package/CHEATSHEET.md

@@ -0,0 +1,271 @@
+# 🗺️ Agent Skills Cheatsheet
+
+> Quick decision guide: **which skill, when, and why.**
+
+---
+
+## ⚡ Quick Decision Matrix
+
+| You want to... | Use this skill | Source | Rating |
+|---|---|---|---|
+| **Security audit** code changes | `security-review` | Sentry | ★★★★★ |
+| **Code review** a PR | `code-review` | Sentry | ★★★★★ |
+| **Find bugs** in local changes | `find-bugs` | Sentry | ★★★★★ |
+| **Audit GH Actions** for supply chain attacks | `gha-security-review` | Sentry | ★★★★★ |
+| **Review Django access control** / IDOR | `django-access-review` | Sentry | ★★★★☆ |
+| **Review Django performance** / N+1 queries | `django-perf-review` | Sentry | ★★★★☆ |
+| **Write a commit message** (Conventional Commits) | `commit` | Sentry | ★★★★★ |
+| **Create a branch** | `create-branch` | Sentry | ★★★★☆ |
+| **Write a PR description** | `pr-writer` | Sentry | ★★★★★ |
+| **Fix CI failures** iteratively | `iterate-pr` | Sentry | ★★★★★ |
+| **Simplify** complex code | `code-simplifier` | Sentry | ★★★★☆ |
+| **Scan skills** for prompt injection | `skill-scanner` | Sentry | ★★★★☆ |
+| **Create new skills** | `skill-writer` / `anthropic-skill-creator` | Sentry / Anthropic | ★★★★☆ |
+| **Run SEO audit** on a website | `seo` | Agentic SEO | ★★★★★ |
+| **Plan a multi-session** project | `create-plan` | OpenCode | ★★★★★ |
+| **Resume** a previous plan | `resume-plan` | OpenCode | ★★★★★ |
+| **Execute** a work packet from plan | `execute-work-packet` | OpenCode | ★★★★★ |
+| **Generate project docs** | `generate-docs` | OpenCode | ★★★★☆ |
+| **Update existing docs** | `update-docs` | OpenCode | ★★★★☆ |
+| **Create handover** summary for next session | `generate-handover` | OpenCode | ★★★★☆ |
+| **Create/edit PDFs** | `anthropic-pdf` | Anthropic | ★★★★★ |
+| **Create/edit Word docs** | `anthropic-docx` | Anthropic | ★★★★★ |
+| **Create presentations** | `anthropic-pptx` | Anthropic | ★★★★★ |
+| **Create/edit spreadsheets** | `anthropic-xlsx` | Anthropic | ★★★★★ |
+| **Build an MCP server** | `anthropic-mcp-builder` | Anthropic | ★★★★★ |
+| **Test web apps** with Playwright | `anthropic-webapp-testing` | Anthropic | ★★★★★ |
+| **Design stunning frontends** | `anthropic-frontend-design` | Anthropic | ★★★★★ |
+| **Build Claude API apps** | `anthropic-claude-api` | Anthropic | ★★★★★ |
+| **Create generative art** with p5.js | `anthropic-algorithmic-art` | Anthropic | ★★★★☆ |
+| **Design artistic visuals** (posters, canvases) | `anthropic-canvas-design` | Anthropic | ★★★★☆ |
+| **Apply professional themes** to artifacts | `anthropic-theme-factory` | Anthropic | ★★★★☆ |
+| **Write internal comms** (3P, newsletters) | `anthropic-internal-comms` | Anthropic | ★★★☆☆ |
+| **Create Slack GIFs** | `anthropic-slack-gif-creator` | Anthropic | ★★★☆☆ |
+| **Build complex React artifacts** | `anthropic-web-artifacts-builder` | Anthropic | ★★★★☆ |
+| **Coauthor documents** collaboratively | `anthropic-doc-coauthoring` | Anthropic | ★★★★☆ |
+| **Optimize React/Next.js** performance | `vercel-react-best-practices` | Vercel | ★★★★★ |
+| **Audit web UI** for accessibility & UX | `vercel-web-design-guidelines` | Vercel | ★★★★★ |
+| **Fix React component architecture** | `vercel-composition-patterns` | Vercel | ★★★★☆ |
+| **Build React Native** apps | `vercel-react-native-skills` | Vercel | ★★★★☆ |
+| **Deploy to Vercel** | `vercel-deploy-to-vercel` | Vercel | ★★★★☆ |
+
+---
+
+## 🏗️ Skills by Source
+
+### 🔒 Sentry (getsentry/skills) — 24 skills
+
+Security, code quality, and Git workflow. Battle-tested at scale.
+
+#### Tier 1 — Must-Have
+
+| Skill | Purpose |
+|-------|---------|
+| `security-review` | OWASP-based security audit with exploitation-focused analysis |
+| `code-review` | Comprehensive code review following engineering best practices |
+| `find-bugs` | Bug hunting in local branch changes with security prioritization |
+| `gha-security-review` | GitHub Actions supply chain security analysis |
+| `commit` | Conventional Commits formatting with AI attribution |
+| `pr-writer` | Structured PR descriptions (what & why) |
+| `iterate-pr` | Automated CI fix loop until green + review feedback resolution |
+| `create-branch` | Branch creation with naming conventions |
+
+#### Tier 2 — Highly Useful
+
+| Skill | Purpose |
+|-------|---------|
+| `django-access-review` | Django IDOR & access control review |
+| `django-perf-review` | Django N+1 queries & performance optimization |
+| `code-simplifier` | Reduce complexity while maintaining functionality |
+| `skill-scanner` | Security analysis of agent skills for prompt injection |
+| `skill-writer` / `skill-creator` | Create new agent skills following best practices |
+| `create-pr` | Direct PR creation workflow |
+
+#### Tier 3 — Specialized
+
+| Skill | Purpose |
+|-------|---------|
+| `agents-md` | AGENTS.md file management |
+| `blog-writing-guide` | Technical blog post creation |
+| `brand-guidelines` | Brand consistency enforcement |
+| `claude-settings-audit` | Claude configuration audit |
+| `doc-coauthoring` | Collaborative document editing |
+| `gh-review-requests` | GitHub review request management |
+| `presentation-creator` | Slide deck creation |
+| `sred-project-organizer` / `sred-work-summary` | SR&ED tax credit documentation |
+
+---
+
+### 🔍 Agentic SEO (Bhanunamikaze) — 16 sub-skills
+
+Comprehensive SEO auditing toolkit with Playwright integration.
+
+| Sub-Skill | Purpose |
+|-----------|---------|
+| `seo audit` | Full technical + on-page + performance audit |
+| `seo page` | Individual page analysis (meta, headings, content) |
+| `seo schema` | Schema.org structured data validation |
+| `seo sitemap` | Sitemap analysis and validation |
+| `seo robots` | robots.txt evaluation |
+| `seo images` | Image optimization (alt text, size, format) |
+| `seo links` | Internal/external link analysis |
+| `seo performance` | Core Web Vitals & speed metrics |
+| `seo mobile` | Mobile-friendliness check |
+| `seo social` | Open Graph & social meta validation |
+| `seo accessibility` | WCAG accessibility audit |
+| `seo security` | HTTPS, headers, CSP analysis |
+| `seo competitive` | Competitor comparison |
+| `seo keyword` | Keyword research & density analysis |
+| `seo content` | Content quality & readability scoring |
+| `seo report` | Comprehensive PDF/HTML report generation |
+
+**Dependencies:** Python 3.8+, optional Playwright for JS-heavy sites
+
+---
+
+### 📋 OpenCode Processing (DasDigitaleMomentum) — 9 skills
+
+Multi-session project planning and documentation framework.
+
+| Skill | Purpose | When |
+|-------|---------|------|
+| `create-plan` | Initialize structured project plan | Starting a new multi-step project |
+| `resume-plan` | Continue previous session's plan | Returning to unfinished work |
+| `update-plan` | Modify plan with new requirements | Scope changes mid-project |
+| `execute-work-packet` | Execute a specific plan item | Implementing individual tasks |
+| `generate-docs` | Create project documentation | After major milestones |
+| `update-docs` | Update existing documentation | After changes to documented features |
+| `generate-handover` | Create session handover summary | End of work session |
+| `archive-legacy-docs` | Archive outdated documentation | During documentation cleanup |
+| `author-and-verify-implementation-plan` | Write & validate implementation plans | Before complex implementations |
+
+---
+
+### 🎨 Anthropic (anthropics/skills) — 17 skills
+
+Document creation, creative design, developer tools, and enterprise workflows.
+
+#### Document Skills (Source-Available)
+
+| Skill | Purpose | Key Features |
+|-------|---------|-------------|
+| `anthropic-pdf` | PDF read/write/merge/split/OCR | pypdf, pdfplumber, reportlab, pytesseract |
+| `anthropic-docx` | Word document creation & editing | docx-js (new), XML manipulation (edit), tracked changes |
+| `anthropic-pptx` | Presentation creation & editing | pptxgenjs (new), XML (edit), visual QA workflow |
+| `anthropic-xlsx` | Spreadsheet creation & analysis | openpyxl, pandas, formula recalculation |
+
+#### Creative & Design
+
+| Skill | Purpose | Key Features |
+|-------|---------|-------------|
+| `anthropic-frontend-design` | Production-grade UI design | Bold aesthetics, anti-AI-slop philosophy |
+| `anthropic-canvas-design` | Artistic visual creation (posters, art) | Design philosophy → canvas execution pipeline |
+| `anthropic-algorithmic-art` | Generative art with p5.js | Seeded randomness, interactive parameter exploration |
+| `anthropic-theme-factory` | 10 professional themes for any artifact | Color palettes + font pairings, custom theme creation |
+| `anthropic-slack-gif-creator` | Animated GIFs optimized for Slack | PIL/Pillow, GIFBuilder, easing functions |
+
+#### Developer Tools
+
+| Skill | Purpose | Key Features |
+|-------|---------|-------------|
+| `anthropic-mcp-builder` | Build MCP servers for LLM integration | TypeScript/Python, 4-phase workflow, evaluation creation |
+| `anthropic-webapp-testing` | Web app testing with Playwright | Server lifecycle management, reconnaissance patterns |
+| `anthropic-claude-api` | Build apps with Claude API/SDK | Multi-language support (8 langs), Agent SDK, tool use |
+| `anthropic-web-artifacts-builder` | Complex React artifacts for claude.ai | React 18 + TypeScript + Tailwind + shadcn/ui |
+
+#### Enterprise & Communication
+
+| Skill | Purpose | Key Features |
+|-------|---------|-------------|
+| `anthropic-internal-comms` | Internal communications (3P, newsletters) | Template-based, format guides per comm type |
+| `anthropic-doc-coauthoring` | Collaborative document editing | Multi-author workflows |
+| `anthropic-brand-guidelines` | Brand consistency enforcement | Visual identity standards |
+| `anthropic-skill-creator` | Create new agent skills | Structured skill development |
+
+---
+
+### ⚛️ Vercel (vercel-labs/agent-skills) — 5 skills
+
+React/Next.js performance, web design, and deployment.
+
+| Skill | Purpose | Rules |
+|-------|---------|-------|
+| `vercel-react-best-practices` | React/Next.js performance optimization | 62 rules, 8 categories (waterfalls, bundles, SSR, re-renders) |
+| `vercel-web-design-guidelines` | UI accessibility & UX audit | 100+ rules (a11y, forms, animation, dark mode, i18n) |
+| `vercel-composition-patterns` | React component architecture | Compound components, state lifting, boolean prop elimination |
+| `vercel-react-native-skills` | React Native/Expo best practices | FlashList, Reanimated, gesture handling, monorepo |
+| `vercel-deploy-to-vercel` | Deploy apps to Vercel | Auto-detects 40+ frameworks, preview/production deploys |
+
+---
+
+## 🎯 Scenario Guide
+
+### "I'm starting a new feature"
+
+1. `create-plan` → Structure the work
+2. `create-branch` → Create feature branch
+3. `execute-work-packet` → Implement tasks from plan
+4. `commit` → Write proper commits
+5. `pr-writer` → Create PR description
+6. `iterate-pr` → Fix CI until green
+
+### "I need to review code"
+
+1. `code-review` → General code review
+2. `security-review` → Security-focused review
+3. `find-bugs` → Bug hunting in diff
+4. `django-access-review` → Django IDOR check (if Django)
+5. `django-perf-review` → Django N+1 check (if Django)
+6. `gha-security-review` → GitHub Actions audit (if GHA changes)
+
+### "I'm building a web app"
+
+1. `vercel-react-best-practices` → Performance patterns
+2. `vercel-composition-patterns` → Component architecture
+3. `anthropic-frontend-design` → Stunning UI design
+4. `vercel-web-design-guidelines` → Accessibility audit
+5. `anthropic-webapp-testing` → Playwright testing
+6. `vercel-deploy-to-vercel` → Ship it
+
+### "I need to create documents"
+
+| Format | Skill |
+|--------|-------|
+| PDF | `anthropic-pdf` |
+| Word (.docx) | `anthropic-docx` |
+| PowerPoint (.pptx) | `anthropic-pptx` |
+| Excel (.xlsx) | `anthropic-xlsx` |
+
+### "I need SEO analysis"
+
+1. `seo` → Run `seo audit` for comprehensive analysis
+2. Focus sub-skills: `seo page`, `seo schema`, `seo performance`
+3. Generate: `seo report` for stakeholder deliverables
+
+### "I'm building an MCP server"
+
+1. `anthropic-mcp-builder` → Full 4-phase development guide
+2. Research → Plan → Implement → Test → Evaluate
+
+### "I need to hand off work to next session"
+
+1. `generate-handover` → Session summary
+2. `update-docs` → Keep docs current
+3. `resume-plan` → Pick up where you left off next time
+
+---
+
+## 📊 Compatibility Matrix
+
+| Skill Category | Antigravity | Claude Code | Cursor | Generic Agent |
+|---------------|:-----------:|:-----------:|:------:|:-------------:|
+| Sentry (code/security) | ✅ | ✅ | ✅ | ✅ |
+| Agentic SEO | ✅ | ✅ | ⚠️ | ✅ |
+| OpenCode (planning) | ✅ | ✅ | ✅ | ✅ |
+| Anthropic (docs) | ⚠️ | ✅ | ⚠️ | ⚠️ |
+| Anthropic (creative) | ⚠️ | ✅ | ⚠️ | ⚠️ |
+| Anthropic (dev tools) | ✅ | ✅ | ⚠️ | ⚠️ |
+| Vercel (React) | ✅ | ✅ | ✅ | ✅ |
+| Vercel (deploy) | ⚠️ | ✅ | ⚠️ | ⚠️ |
+
+✅ = Full support · ⚠️ = Partial (may need adaptation)

package/CLAUDE.md

@@ -0,0 +1,22 @@
+# Agent Skills Hub
+
+This repository contains 55 curated AI agent skills from 5 sources.
+Skills are located in the `skills/` directory — each contains a `SKILL.md` with instructions.
+
+## Available Skill Categories
+
+- **Security & Code Review**: `security-review`, `code-review`, `find-bugs`, `gha-security-review`
+- **Git Workflow**: `commit`, `create-branch`, `pr-writer`, `iterate-pr`
+- **Django**: `django-access-review`, `django-perf-review`
+- **Planning & Docs**: `create-plan`, `resume-plan`, `execute-work-packet`, `generate-docs`
+- **Documents**: `anthropic-pdf`, `anthropic-docx`, `anthropic-pptx`, `anthropic-xlsx`
+- **Frontend & Design**: `anthropic-frontend-design`, `vercel-react-best-practices`, `vercel-web-design-guidelines`
+- **Developer Tools**: `anthropic-mcp-builder`, `anthropic-webapp-testing`, `anthropic-claude-api`
+- **SEO**: `seo` (16 sub-skills)
+- **Deployment**: `vercel-deploy-to-vercel`
+- **Creative**: `anthropic-algorithmic-art`, `anthropic-canvas-design`, `anthropic-theme-factory`
+
+## Usage
+
+To use a skill, read the `SKILL.md` file in the corresponding `skills/<name>/` directory.
+See `CHEATSHEET.md` for a decision guide on which skill to use when.

package/README.md

@@ -0,0 +1,126 @@
+# 🧠 Agent Skills Hub
+
+> **121 AI agent skills** from **15 industry-leading sources** — organized, evaluated, and **multiplatform-ready** for all major AI coding IDEs.
+
+## ✅ Supported Platforms
+
+| Platform | Config File | Setup |
+|----------|------------|-------|
+| **Claude Code** | `CLAUDE.md` | Clone repo, skills auto-discovered |
+| **Antigravity** | `skills/` dir | Symlink `skills/` into agent skill dir |
+| **Codex** (OpenAI) | `AGENTS.md` | Clone repo, `AGENTS.md` auto-loaded |
+| **OpenCode** | `AGENTS.md` + `skills/` | Clone repo, reference skills in prompts |
+| **Cursor** | `.cursorrules` | Clone repo into workspace, rules auto-loaded |
+| **Lovable** | `.lovable` | Add as project dependency |
+| **Windsurf** | `AGENTS.md` | Clone repo, reference skill paths |
+| **Generic Agent** | `SKILL.md` per skill | Read `skills/<name>/SKILL.md` |
+
+## Sources (15)
+
+| # | Source | Skills | Focus |
+|---|--------|--------|-------|
+| 1 | [getsentry/skills](https://github.com/getsentry/skills) | 24 | Security, code review, Git workflow, Django |
+| 2 | [Bhanunamikaze/Agentic-SEO-Skill](https://github.com/Bhanunamikaze/Agentic-SEO-Skill) | 16 | Comprehensive SEO auditing |
+| 3 | [DasDigitaleMomentum/opencode-processing-skills](https://github.com/DasDigitaleMomentum/opencode-processing-skills) | 9 | Multi-session planning & docs |
+| 4 | [anthropics/skills](https://github.com/anthropics/skills) | 17 | Document gen, creative design, MCP, API |
+| 5 | [vercel-labs/agent-skills](https://github.com/vercel-labs/agent-skills) | 5 | React/Next.js, web design, deployment |
+| 6 | [trailofbits/skills](https://github.com/trailofbits/skills) | 30 | Advanced security auditing, static analysis, smart contracts |
+| 7 | [cloudflare/skills](https://github.com/cloudflare/skills) | 9 | Workers, Durable Objects, MCP, web perf |
+| 8 | [stripe/ai](https://github.com/stripe/ai) | 2 | Stripe best practices & SDK upgrades |
+| 9 | [expo/skills](https://github.com/expo/skills) | 3 | Expo app design, deployment, upgrades |
+| 10 | [google-labs-code/stitch-skills](https://github.com/google-labs-code/stitch-skills) | 7 | Design-to-code, shadcn/ui, Remotion |
+| 11 | [hashicorp/agent-skills](https://github.com/hashicorp/agent-skills) | 3 | Terraform code/module/provider generation |
+| 12 | [supabase/agent-skills](https://github.com/supabase/agent-skills) | 1 | Postgres best practices |
+| 13 | [callstackincubator/agent-skills](https://github.com/callstackincubator/agent-skills) | 5 | React Native, GitHub workflows |
+| 14 | [K-Dense-AI/claude-scientific-skills](https://github.com/K-Dense-AI/claude-scientific-skills) | 100+ | Science, bioinformatics, ML, chemistry |
+| 15 | [ComposioHQ/skills](https://github.com/ComposioHQ/skills) | 1 | Connect agents to 1000+ external apps |
+
+## Repository Structure
+
+```
+agent-skills/
+├── skills/               ← 121 symlinks (flat access to all skills)
+├── vendor/               ← 15 Git submodules (upstream sources)
+├── AGENTS.md             ← Codex / OpenCode / Windsurf
+├── CLAUDE.md             ← Claude Code
+├── .cursorrules          ← Cursor IDE
+├── .lovable              ← Lovable AI
+├── CHEATSHEET.md         ← Decision guide: which skill when
+└── README.md             ← This file
+```
+
+## Quick Start
+
+```bash
+# Clone with all submodules
+git clone --recurse-submodules git@github.com:flitzrrr/agent-skills.git
+
+# Update all upstream sources
+git submodule update --remote --merge
+```
+
+## Install via npm
+
+```bash
+npx @flitzrrr/agent-skills install
+```
+
+## Platform Setup
+
+### Claude Code
+```bash
+git clone --recurse-submodules git@github.com:flitzrrr/agent-skills.git
+# CLAUDE.md auto-discovered
+```
+
+### Antigravity (Gemini)
+```bash
+ln -sf /path/to/agent-skills/skills/* ~/.gemini/antigravity/skills/
+```
+
+### Codex (OpenAI)
+```bash
+git clone --recurse-submodules git@github.com:flitzrrr/agent-skills.git
+# AGENTS.md auto-discovered
+```
+
+### Cursor
+```bash
+git clone --recurse-submodules git@github.com:flitzrrr/agent-skills.git
+# .cursorrules auto-loaded
+```
+
+### OpenCode
+```bash
+# Skills are symlinked — see CHEATSHEET.md for usage
+ln -sf /path/to/agent-skills/skills/* ~/.opencode/skills/
+```
+
+### Lovable
+```bash
+git submodule add git@github.com:flitzrrr/agent-skills.git skills
+```
+
+## Naming Convention
+
+| Source | Prefix | Example |
+|--------|--------|---------|
+| Sentry | *(none)* | `code-review`, `security-review` |
+| SEO | `seo` | `seo` |
+| OpenCode | *(none)* | `create-plan`, `resume-plan` |
+| Anthropic | `anthropic-` | `anthropic-pdf`, `anthropic-mcp-builder` |
+| Vercel | `vercel-` | `vercel-react-best-practices` |
+| Trail of Bits | `tob-` | `tob-static-analysis`, `tob-semgrep-rule-creator` |
+| Cloudflare | `cloudflare-` | `cloudflare-wrangler`, `cloudflare-web-perf` |
+| Stripe | `stripe-` | `stripe-stripe-best-practices` |
+| Expo | `expo` | `expo` |
+| Google Stitch | `stitch-` | `stitch-shadcn-ui`, `stitch-remotion` |
+| HashiCorp | `terraform-` | `terraform-code-generation` |
+| Supabase | `supabase-` | `supabase-postgres` |
+| CallStack | `callstack-` | `callstack-react-native-best-practices` |
+| Scientific | `scientific` | `scientific` (100+ sub-skills) |
+| Composio | `composio` | `composio` |
+
+## License
+
+Each vendored repository retains its original license. See individual repos for details.

package/bin/cli.js

@@ -0,0 +1,159 @@
+#!/usr/bin/env node
+
+const { execSync } = require("child_process");
+const path = require("path");
+const fs = require("fs");
+const os = require("os");
+
+const REPO_URL = "https://github.com/flitzrrr/agent-skills.git";
+const SKILL_DIR = path.join(os.homedir(), ".agent-skills");
+
+const PLATFORMS = {
+  claude: {
+    name: "Claude Code",
+    dir: null, // CLAUDE.md approach — project-level
+    note: "Clone repo into your project. CLAUDE.md will be auto-discovered.",
+  },
+  antigravity: {
+    name: "Antigravity (Gemini)",
+    dir: path.join(os.homedir(), ".gemini", "antigravity", "skills"),
+  },
+  codex: {
+    name: "Codex (OpenAI)",
+    dir: path.join(os.homedir(), ".codex", "skills"),
+  },
+  opencode: {
+    name: "OpenCode",
+    dir: path.join(os.homedir(), ".config", "opencode", "skills"),
+  },
+  cursor: {
+    name: "Cursor",
+    dir: null,
+    note: "Clone repo into your workspace. .cursorrules will be auto-loaded.",
+  },
+};
+
+function log(msg) {
+  console.log(`  ${msg}`);
+}
+
+function header(msg) {
+  console.log(`\n🧠 ${msg}\n`);
+}
+
+function cloneRepo() {
+  if (fs.existsSync(SKILL_DIR)) {
+    log("Updating existing installation...");
+    execSync(`git -C "${SKILL_DIR}" pull --quiet`, { stdio: "inherit" });
+    execSync(
+      `git -C "${SKILL_DIR}" submodule update --remote --merge --quiet`,
+      { stdio: "inherit" }
+    );
+  } else {
+    log("Cloning agent-skills repository...");
+    execSync(
+      `git clone --recurse-submodules --quiet "${REPO_URL}" "${SKILL_DIR}"`,
+      { stdio: "inherit" }
+    );
+  }
+}
+
+function installForPlatform(platform) {
+  const config = PLATFORMS[platform];
+  if (!config) {
+    console.error(`Unknown platform: ${platform}`);
+    console.error(`Available: ${Object.keys(PLATFORMS).join(", ")}`);
+    process.exit(1);
+  }
+
+  if (!config.dir) {
+    log(`${config.name}: ${config.note}`);
+    return;
+  }
+
+  fs.mkdirSync(config.dir, { recursive: true });
+
+  const skillsDir = path.join(SKILL_DIR, "skills");
+  const entries = fs.readdirSync(skillsDir);
+  let added = 0;
+  let skipped = 0;
+
+  for (const entry of entries) {
+    const target = path.join(config.dir, entry);
+    const source = path.join(skillsDir, entry);
+
+    if (fs.existsSync(target)) {
+      skipped++;
+      continue;
+    }
+
+    try {
+      fs.symlinkSync(source, target, "junction");
+      added++;
+    } catch {
+      // Skip if symlink fails
+      skipped++;
+    }
+  }
+
+  log(`${config.name}: ${added} skills added, ${skipped} skipped (existing)`);
+}
+
+function listSkills() {
+  const skillsDir = path.join(SKILL_DIR, "skills");
+  if (!fs.existsSync(skillsDir)) {
+    console.error("Skills not installed. Run: npx @flitzrrr/agent-skills install");
+    process.exit(1);
+  }
+  const entries = fs.readdirSync(skillsDir).sort();
+  header(`${entries.length} Available Skills`);
+  entries.forEach((s) => log(`  • ${s}`));
+}
+
+// Main CLI
+const [, , command, ...args] = process.argv;
+
+switch (command) {
+  case "install": {
+    header("Agent Skills Hub — Installation");
+    cloneRepo();
+
+    const platform = args[0];
+    if (platform) {
+      installForPlatform(platform);
+    } else {
+      log("\nInstalling for all platforms...\n");
+      for (const p of Object.keys(PLATFORMS)) {
+        installForPlatform(p);
+      }
+    }
+
+    log("\n✅ Done! See CHEATSHEET.md for which skill to use when.");
+    log(`   ${SKILL_DIR}/CHEATSHEET.md`);
+    break;
+  }
+
+  case "update": {
+    header("Updating Agent Skills...");
+    cloneRepo();
+    log("\n✅ All skills updated to latest versions.");
+    break;
+  }
+
+  case "list": {
+    listSkills();
+    break;
+  }
+
+  default: {
+    header("Agent Skills Hub — CLI");
+    log("Usage:");
+    log("  npx @flitzrrr/agent-skills install              # Install for all platforms");
+    log("  npx @flitzrrr/agent-skills install <platform>    # Install for specific platform");
+    log("  npx @flitzrrr/agent-skills update                # Update all skills");
+    log("  npx @flitzrrr/agent-skills list                  # List all skills");
+    log("");
+    log("Platforms: " + Object.keys(PLATFORMS).join(", "));
+    break;
+  }
+}

package/package.json

@@ -0,0 +1,37 @@
+{
+  "name": "@flitzrrr/agent-skills",
+  "version": "1.0.0",
+  "description": "121 AI agent skills from 15 industry-leading sources — multiplatform-ready for Claude Code, Codex, Cursor, Antigravity, OpenCode, Lovable, and more.",
+  "bin": {
+    "agent-skills": "./bin/cli.js"
+  },
+  "keywords": [
+    "ai",
+    "agent",
+    "skills",
+    "claude",
+    "codex",
+    "cursor",
+    "antigravity",
+    "opencode",
+    "lovable",
+    "SKILL.md",
+    "AGENTS.md"
+  ],
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/flitzrrr/agent-skills.git"
+  },
+  "author": "flitzrrr",
+  "license": "MIT",
+  "files": [
+    "bin/",
+    "skills/",
+    "AGENTS.md",
+    "CLAUDE.md",
+    "CHEATSHEET.md",
+    ".cursorrules",
+    ".lovable",
+    "README.md"
+  ]
+}