Skyll - Agent Skill Discovery

SkillSearch

Search and retrieve agent skills at runtime. This skill should be used when the agent needs to find specialized capabilities, workflows, or domain knowledge to accomplish a task. Skyll aggregates skills from skills.sh and returns full SKILL.md content ready for context injection.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Skyll - Agent Skill Discovery skill

What this skill tells your AI

The instructions your AI receives, as published by assafelovic/skyll in skills/skyll/SKILL.md and read by ahel’s review.

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

FieldDescription
idSkill identifier
titleHuman-readable title
descriptionWhat the skill does
sourceGitHub repository (owner/repo)
relevance_score0-100 match score
install_countPopularity from skills.sh
contentFull SKILL.md markdown content
referencesAdditional reference files (if requested)

Search Parameters

ParameterDefaultDescription
q / queryrequiredSearch query
limit10Max results (1-50)
include_contenttrueFetch full SKILL.md content
include_referencesfalseInclude reference files

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

EndpointDescription
GET /search?q={query}Search skills
POST /searchSearch with JSON body
GET /skills/{source}/{skill_id}Get specific skill
GET /healthHealth check
GET /docsInteractive API documentation

Installation

For Python agents:

pip install skyll

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

Links

Signals

GitHub stars
247
Forks
30
Last commit
Apr 2026

ahel review

  • K1binfo
    installs-packages

Automated review, not a security audit. Ruleset v1+k2.

Advanced
Catalog kind
skill
Gateway key
skyll
Source
github.com/assafelovic/skyll