La couche de skills
pour AI agents.
Permettez a votre AI agent de trouver, comparer et installer automatiquement le bon skill reutilisable.
Daily leaderboards
Skills moving now, ranked with evidence.
Daily snapshots combine capped activity signals, quality, trust, GitHub adoption, and real agent outcomes.
- 1web-automation
Scrapling
32 views, 2 install copies, and excellent quality signals.
70K stars507 events - 2data-analysis
Data Science For Beginners
3 views, 0 install copies, and 4 compares across 1 active days, with capped anti-spam weighting and 1 agent outcomes.
36K stars7 events / 1d - 3coding-agents
Gpt Pilot
30 views, 0 install copies, and excellent quality signals.
34K stars97 events - 4agent-frameworks
Claude Code Best Practice
23 views, 3 install copies, and excellent quality signals.
61K stars76 events - 5ml-automation
Ray
34 views, 1 install copies, and excellent quality signals.
43K stars81 events
Agent resolve
Decrivez la tache. Obtenez un plan de skill sur.
L API renvoie un skill choisi, des alternatives, une decision de politique, des notes d audit et un plan d installation avant que l agent agisse.
Ajustement tache
96/100
Recommande pour les workflows d extraction web
Maintenance
Active
Stars, fraicheur, metadonnees et sante du repo
Revue installation
Ready
Etapes sures avant execution par l agent
Why OpenAgentSkill
N envoyez plus les agents dans des repertoires aleatoires.
Un registre de skills devient utile seulement si un agent peut lui faire confiance. OpenAgentSkill transforme des projets GitHub disperses en capacites classees, auditables et installables.
- 01
De la tache au skill
Les agents commencent par l intention, pas par les categories. Le registre mappe un job vers un skill choisi, des alternatives et des raisons de fit.
- 02
Securite avant installation
Stars, fraicheur, score qualite, risques et readiness accompagnent la commande que l agent executera.
- 03
Humains en UI, agents en API
Les humains parcourent l index; les agents appellent le meme registre via resolve, recommendation et skill endpoints.
Registry response
Un appel, un chemin d installation classe.
{
"task": "analyze stock news",
"agent_decision": {
"recommended_skill": "Last30days Skill",
"install_command": "npx skills add ...",
"why_recommended": [
"matches research workflow",
"strong Trust Score",
"audit warnings included"
],
"risk_summary": {
"safety": "review before install",
"notes": ["network access", "verify sources"]
}
}
}Architecture
Quatre couches entre intention et installation.
OpenAgentSkill n est pas une autre liste statique; c est une boucle de registre qu un agent peut appeler avant d ecrire des fichiers, ouvrir un navigateur ou installer du code tiers.
Indexed
21,527
Signals
Fit · Risk
Surface
API · UI
- 01
Intent capture
A human or upstream agent describes the job in natural language.
Task · Agent · ContextIntent - 02
Recommendation engine
rankerSkills are ranked by workflow fit, maintenance, stars, and audit signals.
Fit · Quality · FreshnessRank - 03
Skill trust profile
Each candidate gets readiness notes, install commands, and review prompts.
Risk · Install · EvidenceAudit - 04
Agent install path
The registry returns the next action an agent can safely execute.
Codex · Claude Code · CursorInstall
Quickstart
From task description to install command.
- 01
Ask for a skill path
Resolve the task into one selected skill, alternatives, safety score, and install plan.
POST /api/agent/resolve - 02
Inspect the trust profile
Review fit, repository health, risks, and install readiness.
GET /api/agent/skills/crawl4ai - 03
Install in an agent workflow
Copy the command or hand it to Codex, Claude Code, Cursor, or a custom agent.
GET /api/skills/crawl4ai/install?format=text - 04
Automate discovery
Use the API as the registry layer behind your own agent runtime.
curl "https://www.openagentskill.com/api/agent/resolve?task=review+pull+requests&agent=codex"
Compare
Comment OpenAgentSkill differe des autres plateformes.
Le pari est simple : les repertoires ordinaires sont faits pour les humains. OpenAgentSkill permet a un AI agent de decouvrir, comparer et installer automatiquement le bon skill.
| Feature | OpenAgentSkill | skills.sh | agentskills.io | Native docs |
|---|---|---|---|---|
| Primary job | Recommend, compare, and install skills from one registry | Browse and install reusable agent skills | Define the open skill format and learning path | Explain skills inside each native agent platform |
| Agent-facing API | Yes - task-to-skill recommendations for agents | Directory and install workflow | Spec and documentation first | Platform-specific APIs and docs |
| Cross-agent positioning | Codex, Claude Code, Cursor, MCP-compatible agents, and custom tools | Open agent skills ecosystem | Open format for extending agents | Best for the vendor platform |
| Trust and audit signals | Stars, quality score, readiness notes, install review | Directory metadata | Metadata guidance in SKILL.md | Native platform controls |
| Best for | Letting an agent find the right skill automatically | Finding installable skills quickly | Learning or authoring the standard | Using skills in one product |
Comparison is based on each project's public positioning and documentation. The point is not that one project replaces another; OpenAgentSkill focuses on the registry and recommendation layer agents can call.
Workflow starts
Start from the job your agent needs to do.
Web scraping
Monitor pricing and extract tables
Coding agents
Inspect repos, patch bugs, verify changes
RAG workflows
Turn documents into grounded answers
Workflow automation
Connect repeated ops across tools
Skill layer
Registry for humans. Skill layer for agents.
Browse when you are exploring. Call the recommendation API when your agent needs to pick, compare, and install a skill automatically.