Skyll

Skyll - Agent Skill Discovery

Skyll enables agents to dynamically discover and retrieve skills at runtime. Instead of having all skills pre-loaded, agents can search for relevant skills on-demand and inject them into context.

When to Use This Skill

Use Skyll when:

• The current task requires specialized knowledge or workflows not in context
• Looking for best practices for a specific framework, library, or domain
• Needing procedural knowledge for complex multi-step tasks
• Wanting to enhance capabilities with community-contributed skills

Quick Usage

Option 1: Python Client (Recommended)

from skyll import Skyll

async with Skyll() as client:
    # Search for relevant skills
    skills = await client.search("react performance optimization", limit=3)
    
    for skill in skills:
        print(f"Skill: {skill.title}")
        print(f"Score: {skill.relevance_score}")
        print(skill.content)  # Full SKILL.md content

Option 2: REST API

Search for skills:

curl "https://api.skyll.app/search?q=react+performance&limit=3"

Get a specific skill:

curl "https://api.skyll.app/skills/anthropics/skills/skill-creator"

Response Format

The API returns ranked skills with relevance scores (0-100):

{
  "query": "react performance",
  "count": 3,
  "skills": [
    {
      "id": "react-best-practices",
      "title": "React Best Practices",
      "description": "Performance optimization for React and Next.js",
      "source": "vercel-labs/agent-skills",
      "relevance_score": 85.5,
      "install_count": 82800,
      "content": "# React Best Practices\n\n## Performance\n..."
    }
  ]
}

Key Fields

Search Parameters

Example Workflow

When an agent needs to build a React Native app but lacks mobile expertise:

1. Search for relevant skills:

   skills = await client.search("react native best practices", limit=2)
   

2. Inject top skill into context:

   context = skills[0].content  # Full SKILL.md content
   

3. Use the skill's knowledge to complete the task

API Endpoints

Installation

For Python agents:

pip install skyll

For other languages, use the REST API directly at https://api.skyll.app.

Links

• API: https://api.skyll.app
• Docs: https://api.skyll.app/docs
• Demo: https://skyll.app
• GitHub: https://github.com/assafelovic/skyll

Source: assafelovic/skyll — distributed by TomeVault.