agent-skills
The secure, validated skill registry for professional AI coding agents. Extend Antigravity, Claude Code, Cursor, Copilot and more with absolute confidence.
Explore the threat model and security implementation details of the agent skills system. Learn how defense-in-depth, filesystem isolation, and crypto integrity protect against attacks.
How to Run Tests for CLI Development Using Jest in the Agent‑Skills RepositoryLearn to run Jest tests for CLI development in the agent-skills repository. Use npm test from the root to execute the full test suite with ts-jest for TypeScript ES modules.
How to Handle Skill Version Conflicts and Manage Updates in Agent-SkillsLearn to handle skill version conflicts and manage updates in agent-skills. Discover automatic updates, manual overrides, and maintain seamless skill management for your projects.
How to Add Support for Custom or Unsupported AI Agents in the Agent-Skills SystemEasily add custom or unsupported AI agents to the Agent-Skills system. Learn how to extend AGENT_TYPES and define new agent entries within the core services for custom integrations.
How Skills Are Validated for Security Vulnerabilities Before Publication in Agent-SkillsLearn how Agent-Skills validates security vulnerabilities before publication using SHA-256 hashing, Snyk scans, and CI checks to protect the public registry from a vulnerable code.
Skill Cache Mechanism in Agent-Skills: How It Works and How to Manage It ManuallyDiscover how the agent-skills cache mechanism works and manage it manually using CLI commands or the API. Learn about content hash validation for efficient skill caching.
How to Create a New Custom Skill Using the Nx Generator in Agent-SkillsLearn to create a new custom skill using the Nx generator in Agent-Skills. This tool scaffolds a complete skill package, simplifying development.
Copy vs Symlink Skill Installation Methods in Agent-Skills: A Complete GuideUnderstand copy vs symlink skill installation in agent-skills. Learn when to use each and discover automatic fallback for seamless integration.
How to Debug Skill Installation Failures and Common CLI Issues in Agent SkillsTroubleshoot Agent Skills CLI installation failures. Learn to debug errors by enabling verbose logging, checking the lockfile, and verifying cache write permissions.
How the MCP Server Exposes Skills to AI Agents via Progressive DisclosureLearn how the MCP server uses progressive disclosure to expose skills to AI agents. Discover the three step workflow: search_skills, read_skill, and fetch_skill_files for efficient data delivery.
How the Agent-Skills Lockfile System Ensures Skill Integrity and Prevents TamperingDiscover how the Agent-Skills lockfile system secures skill integrity. Learn about atomic operations, crypto hashes, Zod validation, and versioned migrations to prevent tampering.
Have a question about this repo?
These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:
curl -s "https://instagit.com/install.md" Maintain an open-source project? Get it listed too →