Install
$ agentstack add mcp-dmgrok-agent-skills-directory Open-source listing, not yet scanned by AgentStack. Follow the source repository for install instructions.
Security review
⚠ Flagged1 finding(s); flagged for manual review. · v0.1.0 How review works →
- • Prompt-injection patterns
- • Secret / credential exfiltration
- • Dangerous shell & filesystem operations
- • Untrusted network calls
- • Known-malicious package signatures
- high Pipes remote content directly into a shell (remote code execution).
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Agent Skills Directory
Intelligent skill discovery for AI agents. Find, install, and manage quality-validated skills from 40+ official providers — all from one place.
skillsdir suggest # Smart recommendations for your project
skillsdir search "testing" # Search 130+ curated skills
skillsdir install anthropic/pdf # Install with one command
[](https://dmgrok.github.io/agentskillsdirectory/) [](https://dmgrok.github.io/agentskillsdirectory/) [](https://dmgrok.github.io/agentskillsdirectory/)
Why This Exists
There are thousands of AI agent skills scattered across GitHub. Which ones work? Which are maintained? Which fit your project?
We aggregate, validate, and score skills from 40+ official providers so you can make informed decisions — no guesswork.
| Feature | Description | |---------|-------------| | 🎯 Smart Recommendations | Analyzes your project and suggests relevant skills | | 📊 Quality Scoring | 0–100 points based on docs, maintenance, and trust | | 🟢 Maintenance Tracking | Active · Maintained · Stale · Abandoned | | 🛡️ Security Validated | Scanned for secrets and prompt injection | | 🏢 Official Sources | Anthropic, OpenAI, GitHub, Vercel, Stripe, Cloudflare + more | | 💯 100% Local | No LLM or external API required |
Install
# macOS
brew install dmgrok/tap/skillsdir
# Linux / macOS
curl -fsSL https://raw.githubusercontent.com/dmgrok/agent_skills_directory/main/install.sh | bash
# Python
pip install skillsdir
Usage
Get recommendations for your project
skillsdir suggest # Analyze current directory
skillsdir suggest /path/to/project # Analyze specific project
skillsdir suggest --verbose # Show scoring details
The suggest command reads your README, detects languages and frameworks, and ranks skills using a multi-factor scoring algorithm — entirely offline, no LLM needed.
Search and explore
skillsdir search "pdf extraction" # Keyword search
skillsdir info anthropic/pdf # Detailed skill info
Install and manage
skillsdir install anthropic/pdf # Install globally
skillsdir install anthropic/pdf --project # Install to project (auto-detects agent)
skillsdir install anthropic/pdf -p --agent claude # → .claude/skills/
skillsdir install anthropic/pdf -p --agent copilot # → .github/skills/
skillsdir install anthropic/pdf -p --agent codex # → .codex/skills/
skillsdir install anthropic/pdf -p --agent cursor # → .cursor/skills/
skillsdir list # List installed skills
skillsdir update # Update all skills
skillsdir uninstall anthropic/pdf # Remove a skill
Create and publish
skillsdir init # Create a new skill.json
skillsdir validate # Validate your skill
skillsdir login # Authenticate with GitHub
skillsdir publish # Push to GitHub
skillsdir publish --submit # Request inclusion in directory
Providers
Skills are aggregated from 40+ repositories across the AI agent ecosystem.
Featured
| Provider | Repository | Stars | |----------|-----------|-------| | Anthropic | anthropics/skills | ⭐ 54K+ | | Obra Superpowers | obra/superpowers | ⭐ 37K+ | | GitHub Copilot | github/awesome-copilot | ⭐ 19K+ | | Vercel | vercel-labs/agent-skills | ⭐ 16K+ | | VoltAgent | voltagent/awesome-agent-skills | ⭐ 5K+ | | NotebookLM | notebooklm-skill | ⭐ 2K+ | | OpenAI Codex | openai/skills | ⭐ 2K+ | | heilcheng | heilcheng/awesome-agent-skills | ⭐ 1K+ | | HuggingFace | huggingface/skills | ⭐ 1K+ | | Playwright | playwright-skill | ⭐ 1K+ |
Enterprise & Official
Stripe · Cloudflare · Supabase · Trail of Bits · Expo · Sentry · Google Labs Stitch · Better Auth · Tinybird · Neon Database · fal.ai · Remotion · nginity
Community
SkillCreator.ai · iOS Simulator · Claude Marketplace · CSV Summarizer · Tapestry Skills · AWS Skills · FFUF Web Fuzzing · D3.js Visualization · EPUB Converter · Sanjay AI Skills · PICT Test Cases · Family History · Move Code Quality
Quality System
Every skill gets a quality score (0–100) based on three factors:
| Factor | Max Points | Details | |--------|-----------|---------| | Maintenance | 50 | 🟢 Active (<30d) = 50 · 🟡 Maintained (<6mo) = 40 · 🟠 Stale (<1yr) = 20 · 🔴 Abandoned = 5 | | Documentation | 30 | Scripts (+10) · References (+10) · Assets (+10) | | Provider Trust | 20 | Official = 20 · Community = 10 |
Supported Agents
| Agent | Project Path | Auto-Detection | |-------|-------------|----------------| | Claude | .claude/skills/ | CLAUDE.md, .claude/ | | Copilot | .github/skills/ | .github/copilot-instructions.md | | Codex | .codex/skills/ | AGENTS.md | | Cursor | .cursor/skills/ | .cursorrules |
API & Exports
The catalog is updated daily at 06:00 UTC and available via CDN:
https://cdn.jsdelivr.net/gh/dmgrok/agent_skills_directory@main/catalog.json
Pre-filtered exports for specific ecosystems:
| Export | Filter | URL | |--------|--------|-----| | Claude Skills | Quality ≥ 50 | exports/claude-skills.json | | Copilot Skills | Quality ≥ 50 | exports/copilot-skills.json | | Premium Skills | Quality ≥ 70 | exports/premium-skills.json | | Active Skills | Updated < 6mo | exports/active-skills.json | | MCP-Compatible | Tagged mcp | exports/mcp-compatible.json |
import requests
catalog = requests.get(
"https://cdn.jsdelivr.net/gh/dmgrok/agent_skills_directory@main/catalog.json"
).json()
quality_skills = [s for s in catalog["skills"] if s["quality_score"] >= 80]
Skills Listing
📋 All Skills — 687 skills across 43 providers · v2026.03.06
> Auto-generated daily · Browse interactively → > Legend: 🔒 Secrets scan · 🛡️ Injection check · 📝 Content · 🔄 No duplicate · ✅ Full skill · S=Scripts · R=References · A=Assets
| Skill | Provider | Compat | 🔒 | 🛡️ | 📝 | 🔄 | ✅ | S | R | A | Quality | Status | Dup | |-------|----------|--------|----|----|----|----|---|---|---|---|---------|--------|-----| | playwright | openai | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 100/100 | 🟢 active | | | skill-creator | anthropics | Claude+Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 100/100 | 🟢 active | | | slides | openai | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 100/100 | 🟢 active | | | app-store-optimization | nginity | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 90/100 | 🟢 active | | | aspnet-core | openai | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ⬜ | ✅ | ✅ | 90/100 | 🟢 active | | | campaign-analytics | nginity | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 90/100 | 🟢 active | | | chatgpt-apps | openai | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ⬜ | 90/100 | 🟢 active | | | content-production | nginity | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 90/100 | 🟢 active | | | customer-success-manager | nginity | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 90/100 | 🟢 active | | | datanalysis-credit-risk | github | Copilot+Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ⬜ | 90/100 | 🟢 active | | | develop-web-game | openai | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 90/100 | 🟡 maintained | | | emblem-ai-agent-wallet | emblemcompany | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 90/100 | 🟢 active | | | excalidraw-diagram-generator | github | Copilot+Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 90/100 | 🟡 maintained | | | fal-workflow | fal-ai | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ⬜ | 90/100 | 🟢 active | | | financial-analyst | nginity | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 90/100 | 🟢 active | | | game-engine | github | Copilot+Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ⬜ | ✅ | ✅ | 90/100 | 🟢 active | | | hugging-face-paper-publisher | huggingface | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 90/100 | 🟡 maintained | | | imagegen | openai | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 90/100 | 🟡 maintained | | | interpreting-culture-index | trailofbits | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 90/100 | 🟢 active | | | jupyter-notebook | openai | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 90/100 | 🟡 maintained | | | nano-banana-pro-openrouter | github | Copilot+Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ⬜ | ✅ | 90/100 | 🟢 active | | | openai-docs | openai | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ⬜ | ✅ | ✅ | 90/100 | 🟢 active | | | openai-docs | openai | Universal | ✅ | ✅ | ✅ | ⬜ | ✅ | ⬜ | ✅ | ✅ | 90/100 | 🟢 active | 🔄 → openai/openai-docs | | revenue-operations | nginity | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 90/100 | 🟢 active | | | sales-engineer | nginity | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 90/100 | 🟢 active | | | scrum-master | nginity | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 90/100 | 🟢 active | | | senior-pm | nginity | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 90/100 | 🟢 active | | | skill-creator | openai | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ⬜ | 90/100 | 🟢 active | | | social-media-analyzer | nginity | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 90/100 | 🟢 active | | | sora | openai | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 90/100 | 🟡 maintained | | | speech | openai | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 90/100 | 🟡 maintained | | | spreadsheet | openai | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ⬜ | ✅ | ✅ | 90/100 | 🟢 active | | | transcribe | openai | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 90/100 | 🟡 maintained | | | vercel-deploy | openai | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ⬜ | ✅ | 90/100 | 🟢 active | | | winui-app | openai | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ⬜ | ✅ | ✅ | 90/100 | 🟢 active | | | ab-test-setup | nginity | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ⬜ | 80/100 | 🟢 active | | | ad-creative | nginity | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ⬜ | 80/100 | 🟢 active | | | agents-sdk | cloudflare | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ⬜ | ✅ | ⬜ | 80/100 | 🟢 active | | | analytics-tracking | nginity | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ⬜ | 80/100 | 🟢 active | | | appinsights-instrumentation | github | Copilot+Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ⬜ | 80/100 | 🟡 maintained | | | aspire | github | Copilot+Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ⬜ | ✅ | ⬜ | 80/100 | 🟢 active | | | aws-cdk-development | aws-skills | Universal | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ⬜ | 80/100 | 🟢 active | | | [aws-solution-architect](https://raw.githubusercontent.com/alirezarezvani/claude-skills/main/e
…
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: dmgrok
- Source: dmgrok/agentskills_directory
- License: MIT
- Homepage: https://dmgrok.github.io/agentskillsdirectory/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.