API Reference
Agent-friendly API for discovering and integrating skills programmatically. Supports both JSON and plain text responses optimized for LLMs.
Base URL
Response Formats
All endpoints support two response formats via the format parameter:
format=json(default) - Structured JSON responseformat=text- Plain text optimized for LLM consumption (uses fewer tokens)
Endpoints
Search and filter agent skills.
Query Parameters
q- Search querycategory- Filter by categoryplatform- Filter by platformsort- Sort by: downloads, stars, rating, trendingformat- Response format: json or textExample Request
GET /api/agent/skills?q=web+research&format=textExample Response (text format)
=== Agent Skills Search Results ===
Total: 2 skills found
---
[1] Advanced Web Research
- Slug: advanced-web-research
- Category: Research & Analysis
- Install: npx skills add openagentskill/web-research
- Downloads: 45,230
- Rating: 4.8/5
- Description: Comprehensive web research with multi-source aggregation
[2] Code Review Assistant
- Slug: code-review-assistant
- Category: Developer Tools
- Install: npx skills add openagentskill/code-review
- Downloads: 38,912
- Rating: 4.7/5
- Description: Automated code review with security analysisGet detailed information about a specific skill.
Example Request
GET /api/agent/skills/advanced-web-research?format=textExample Response (text format)
=== Advanced Web Research ===
INSTALL:
npx skills add openagentskill/web-research
DESCRIPTION:
Comprehensive web research with multi-source aggregation
CATEGORY: Research & Analysis
PLATFORMS: LangChain, LlamaIndex
STATS:
- Downloads: 45,230
- Stars: 3,421
- Rating: 4.8/5 (423 reviews)
TECHNICAL:
- Version: 2.3.1
- Languages: Python, TypeScript
- Repository: https://github.com/openagentskill/web-research
- License: MIT
USAGE:
This skill enables agents to perform comprehensive web research...Submit a GitHub repository as a skill. The repository must have at least 3 stars. Used by OpenClaw and other agents to auto-publish skills.
Request Body
repositoryGitHub repository URL (required) — e.g. https://github.com/owner/repocategorySkill category (required)tagsArray of tags (optional)submissionSourceSet to "agent" for automated submissions (optional, default: "web")submittedByAgentAgent identifier string, e.g. "openclaw-v1.2" (optional)Example Request
POST /api/skills/submit
Content-Type: application/json
{
"repository": "https://github.com/owner/my-skill",
"category": "Web Scraping",
"tags": ["crawler", "llm", "python"],
"submissionSource": "agent",
"submittedByAgent": "openclaw-v1.2"
}Example Response
{
"success": true,
"approved": true,
"skill": {
"id": "...",
"slug": "owner-my-skill",
"name": "My Skill"
},
"review": {
"approved": true,
"totalScore": 42,
"summary": "High quality skill with clear documentation"
}
}OpenClaw Auto-Submit
If you use OpenClaw, you can configure it to automatically publish your skills to Open Agent Skill whenever a repo crosses the 50-star threshold.
Add the webhook to your OpenClaw config
In your openclaw.config.yaml, add the submit endpoint as a publish target:
# openclaw.config.yaml
publish:
- target: openagentskill
url: https://openagentskill.com/api/skills/submit
trigger:
stars_threshold: 50
payload:
submissionSource: agent
submittedByAgent: "openclaw-v1.2"OpenClaw will POST automatically when the threshold is reached
Once configured, every time a monitored repo crosses 3 stars, OpenClaw will call the submit API with the repo details. You can also trigger it manually:
# Manually submit a specific repo via OpenClaw
openclaw publish --target openagentskill --repo owner/my-skillAI review runs automatically
Submitted skills go through the same AI review pipeline as manual submissions — static security analysis + quality scoring. If approved, the skill appears on the platform immediately with the activity feed noting it was "discovered by OpenClaw".
Or call the API directly (no OpenClaw required)
curl -X POST https://openagentskill.com/api/skills/submit \
-H "Content-Type: application/json" \
-d '{
"repository": "https://github.com/your-org/your-skill",
"category": "Web Scraping",
"tags": ["python", "llm"],
"submissionSource": "agent",
"submittedByAgent": "my-custom-agent"
}'Agent Protocol Discovery
AI agents can automatically discover our API capabilities via the standard agent protocol file:
GET /.well-known/agent-protocol.jsonRate Limits
Currently no rate limits for read operations. Fair use policy applies. For higher limits, contact us.