sickn33/agentic-awesome-skills

AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,600+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.

What it solves

Agentic Awesome Skills (AAS) provides a massive, curated library of over 2,600 installable SKILL.md playbooks. It solves the problem of agents (like Claude Code or Codex) needing specific, reusable instructions to perform complex tasks across various domains without the user having to write detailed prompts from scratch every time.

How it works

The project consists of a catalog of skills and a core tooling system (AAS Core) that allows AI agents to search, select, and validate a set of skills for a specific project. Agents use a local Model Context Protocol (MCP) to inspect the catalog and compose a "stack" of skills. Users can then validate this stack and review an immutable plan before the skills are actually installed into their agent's environment (e.g., Cursor, Gemini CLI, or Claude Code).

Who it’s for

Developers, product designers, and security engineers who use AI agents or AI-powered IDEs and want to extend their agent's capabilities with pre-defined, expert-level instructions for tasks like web app building, DevOps, QA automation, and data analytics.

Highlights

  • Massive Library: Access to 2,671+ installable playbooks.
  • Agent-First Workflow: Designed for agents to search and select the most relevant skills for a project.
  • Broad Compatibility: Supports a wide range of tools including Claude Code, Cursor, Gemini CLI, Codex, and GitHub Copilot.
  • Specialized Plugins: Offers focused bundles for specific roles like Security Engineer, Web App Builder, and Data Analytics.
  • Safe Installation: Includes a validation and planning phase to ensure the chosen skill set is reviewed before application.

Related

  • Project
    MengTo/Skills

    A curated library of procedural playbooks and prompts that turn complex design and coding workflows into reusable skills for AI agents to ensure consistent, high-quality output.

  • Project
    openai/skills

    A repository of reusable instruction and script packages that AI agents can use to perform specific tasks in a repeatable way.

  • Project
    Leon-Drq/openagentskill

    A skill layer for AI agents that allows them to find, audit, and install the most suitable and trusted reusable skills for specific tasks.

  • Project
    aiskillstore/marketplace

    An open-source marketplace repository for AI agent skills, providing a secure distribution system and CLI for adding capabilities to tools like Claude Code and Codex.

  • Project
    BuilderIO/skills

    A collection of composable skills and tools that extend AI agents with capabilities for visual planning, automated software delivery pipelines, and cost-efficient model orchestration.