Documentation

from skyll import Skyll

async with Skyll() as client:
    skills = await client.search("react performance", limit=5)
    
    for skill in skills:
        print(f"{skill.title}: {skill.description}")
        print(skill.content)  # Full SKILL.md content

async with Skyll() as client:
    skill = await client.get("anthropics/skills", "skill-creator")
    if skill:
        print(skill.content)

async with Skyll() as client:
    skills = await client.search("react", include_references=True)
    
    for skill in skills:
        for ref in skill.references:
            print(f"📎 {ref.name}: {len(ref.content)} chars")

async with Skyll(base_url="http://localhost:8000") as client:
    skills = await client.search("testing")

git clone https://github.com/assafelovic/skyll.git
cd skyll
pip install -e ".[server]"

# GitHub token for higher rate limits (5000 vs 60 requests/hour)
GITHUB_TOKEN=ghp_your_token_here

# Cache TTL in seconds (default: 86400 = 24 hours)
CACHE_TTL=86400

uvicorn src.main:app --port 8000

from skyll import Skyll

async with Skyll(base_url="http://localhost:8000") as client:
    skills = await client.search("testing")

from src.ranking.base import Ranker

class MyCustomRanker(Ranker):
    def rank(self, skills, query="", include_references=False):
        for skill in skills:
            # Your scoring logic
            skill.relevance_score = ...
        return sorted(skills, key=lambda s: s.relevance_score, reverse=True)

# Register in src/core/service.py:
self._ranker = MyCustomRanker()

{
  "mcpServers": {
    "skyll": {
      "command": "/path/to/skyll/venv/bin/python",
      "args": ["-m", "src.mcp_server"],
      "cwd": "/path/to/skyll"
    }
  }
}

# Stdio transport (for MCP clients)
python -m src.mcp_server

# SSE transport (for web clients)
python -m src.mcp_server --transport sse --port 8080