CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
35.0 pts
Supply chainhash, typosquat, maintainer, lockfile
20%
20.0 pts
Maintenancestaleness, pinning, CI
15%
15.0 pts
TransparencySKILL.md, perms, README
15%
15.0 pts
Communityinstalls, verify, response
15%
15.0 pts
Findings & checks · 0 flagged
Security
✓—All security checks passedNo findings in this category for the latest scan.pass
Supply chain
✓—All supply chain checks passedNo findings in this category for the latest scan.pass
Maintenance
✓—All maintenance checks passedNo findings in this category for the latest scan.pass
Transparency
✓—All transparency checks passedNo findings in this category for the latest scan.pass
Community
✓—All community checks passedNo findings in this category for the latest scan.pass
Every scanned point with the score it earned and what moved between them.
40dc24f
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
<div align="center">
OpenSIN-Skills
The World's Largest Open-Source AI Agent Skill Library
280+ Skills | 9 Expertise Domains | 8 Operations Categories | 9 Personas | 8 Orchestration Patterns
What if your AI agent had the expertise of a Senior Architect, the creativity of a CMO, AND the automation power to deploy infrastructure, generate media, and orchestrate entire coding teams?
</div>
Architecture
graph TB
subgraph "Knowledge Layer (235 Skills)"
ENG[Engineering<br/>50+ skills]
PROD[Product<br/>30+ skills]
MKT[Marketing<br/>25+ skills]
CLVL[C-Level<br/>20+ skills]
PM[Project Mgmt<br/>25+ skills]
QM[RA/QM<br/>30+ skills]
BIZ[Business Growth<br/>20+ skills]
FIN[Finance<br/>15+ skills]
end
subgraph "Action Layer (47 Skills)"
A2A[Agent Creation<br/>11 skills]
BROWSER[Browser Automation<br/>5 skills]
DEPLOY[Deployment<br/>2 skills]
MEDIA[Media Generation<br/>10 skills]
PLAN[Planning<br/>6 skills]
DOCS[Documents<br/>4 skills]
end
subgraph "Orchestration"
PERS[9 Personas]
ORCH[8 Patterns]
end
ENG --> BRAIN((Agent Brain))
PROD --> BRAIN
MKT --> BRAIN
CLVL --> BRAIN
PM --> BRAIN
QM --> BRAIN
BIZ --> BRAIN
FIN --> BRAIN
A2A --> BRAIN
BROWSER --> BRAIN
DEPLOY --> BRAIN
MEDIA --> BRAIN
PLAN --> BRAIN
DOCS --> BRAIN
PERS --> BRAIN
ORCH --> BRAIN
style BRAIN fill:#00ff41,stroke:#333,stroke-width:3px,color:#000Two Systems, One Brain
| Layer | Source | Count | Purpose |
|---|---|---|---|
| Knowledge | claude-skills by Alireza Rezvani | 235 | How to think, decide, plan |
| Action | OpenSIN-AI | 47 | How to execute, automate, deploy |
| Personas | Combined | 9 | Role-based agent identities |
| Orchestration | Combined | 8 | Multi-skill coordination patterns |
Quick Start
# Clone the library
git clone https://github.com/OpenSIN-AI/OpenSIN-Skills.git
cd OpenSIN-Skills
# Install with bun (NEVER npm)
bun install
# Validate all skills
python3 scripts/validate-skill.py --all .
# Generate skill catalog
python3 scripts/catalog-generator.py . --output catalog.json --statsSkill Domains
Knowledge Skills (from claude-skills)
| Domain | Skills | Description |
|---|---|---|
engineering/ | 50+ | Software architecture, system design, code review, testing, DevOps |
product-team/ | 30+ | Product strategy, user research, roadmapping, analytics |
marketing-skill/ | 25+ | Content strategy, SEO, growth, brand, social media |
c-level-advisor/ | 20+ | CEO, CTO, CFO, COO advisory and decision frameworks |
project-management/ | 25+ | Agile, Scrum, risk management, stakeholder communication |
ra-qm-team/ | 30+ | Regulatory affairs, quality management, compliance, audits |
business-growth/ | 20+ | Market analysis, partnerships, scaling, internationalization |
finance/ | 15+ | Financial planning, budgeting, forecasting, investor relations |
Operational Skills (OpenSIN native)
| Category | Skills | Description |
|---|---|---|
operations/agent-creation/ | 11 | Create A2A agents, Telegram bots, auth plugins, HF Spaces |
operations/browser-automation/ | 5 | Stealth browsing, crash testing, web verification |
operations/deployment/ | 2 | Cloudflare Workers, Vercel deployment |
operations/media/ | 10 | Image generation, video (Sora), 3D (NVIDIA), thumbnails |
operations/planning/ | 6 | Enterprise planning, debugging, parallel exploration |
operations/documents/ | 4 | PDF, DOCX, visual repos, design systems |
operations/google/ | 2 | Google account management |
operations/misc/ | 6 | Preview, self-healing, SEO, governance, research |
Skill Authoring Standard
Every skill follows our 13-pattern standard:
- Context-First Design — YAML frontmatter with metadata
- Practitioner Voice — Write as an expert, not a textbook
- Multi-Mode Workflows — Build + Optimize (minimum)
- Related Skills Navigation — Cross-references between skills
- Reference Separation — Keep refs in separate files
- Proactive Triggers — When to activate this skill
- Output Artifacts — What the skill produces
- Quality Loop — Self-review checklist
- Communication Standard — Clear formatting
- Python Tools — stdlib-only, --help support
- A2A Integration (OpenSIN) — Agent fleet connectivity
- MCP Tooling (OpenSIN) — Model Context Protocol tools
- Fleet Dispatch (OpenSIN) — HF VM coder delegation
Patterns 1-10 from claude-skills by Alireza Rezvani. Patterns 11-13 by OpenSIN-AI.
See SKILL-AUTHORING-STANDARD.md for full details.
Python Tools
All Python scripts are stdlib-only (zero pip installs):
# Validate skills
python3 scripts/validate-skill.py --all . --json
# Generate catalog
python3 scripts/catalog-generator.py . --output catalog.jsonIntegration
Works with: OpenCode | Cursor | Aider | Windsurf | Kilo Code | Augment
Credits
- Alireza Rezvani — Creator of claude-skills (235 expertise skills, MIT License)
- OpenSIN-AI — 47 operational skills, A2A integration, fleet dispatch patterns
License
MIT — Use freely. Credit appreciated.