AI Agent Skills

An AI agent skill is a reusable set of task instructions in a SKILL.md file, often accompanied by examples, scripts or reference material. A coding agent reads the skill to follow a procedure, such as investigating a failing test or reviewing an API. You still review the instructions, any bundled files and the result.

Agentic Awesome Skills (AAS), formerly Antigravity Awesome Skills, is an open-source library of these instructions for Codex, Claude Code, Cursor and other coding agents. Its canonical source is sickn33/agentic-awesome-skills. Original code uses MIT; original written content uses CC BY 4.0, with imported skills retaining their own notices. See sources and licenses.

A practical first example

For a failing test, inspect systematic-debugging and its bundled files, then use the setup guide for your agent. Give the agent a concrete task:

Investigate this failing test. Use the reviewed debugging skill to reproduce the
failure, identify its cause, propose a minimal fix, and rerun the relevant tests.

The observable result is a reproduced failure, an explained change and test output. Installing a skill alone does not establish that the task succeeded.

How AAS Core helps

For Codex and Claude Code, AAS Core lets your agent search and read the local catalog, choose skills for your project, and record its selection for review. Follow Codex setup or Claude Code setup to connect it. For Cursor, follow the direct installation guide.

The agent uses compose_stack to record exact IDs in aas-stack.json; the CLI validates that selection and previews a plan before any separate installation. AAS does not scan your repository, choose skills, call a remote model, or write project files through MCP.

What to look for in an AI agent skill system

• Explicit input boundary: is project analysis performed by the coding agent and passed as a reviewable profile?
• Agent-owned selection: can the coding agent search and read every skill before choosing exact IDs?
• Reproducibility: can the chosen IDs be pinned to a catalog identity and replayed without a metadata eligibility gate?
• Durable desired state: can the approved selection be recorded independently of the agent conversation?
• Preview before change: can the system validate the manifest and produce an exact plan without changing the target?
• Source and compatibility evidence: are provenance, risk, host support, and distribution boundaries explicit?

When Agentic Awesome Skills is a good fit

• You use Codex or Claude and want the agent to choose a focused stack for a real project.
• You want complete local search and inspection without repository scanning or remote-model calls by AAS.
• You need a reviewable aas-stack.json and CLI validation and planning before target changes.
• You also value a broad catalog and multiple distribution options around the Core workflow.

When a smaller curated repo may be better

• You only want a fixed, vendor-maintained shortlist and do not need project-aware composition.
• You prefer selecting and invoking individual skills manually.
• Your host does not yet have an AAS Core adapter and direct distribution is sufficient.

Start with a tool-specific guide

• claude-code-skills.md
• cursor-skills.md
• codex-cli-skills.md
• gemini-cli-skills.md

Compare catalogs and distribution models

• agentic-awesome-skills-vs-awesome-claude-skills.md
• best-claude-code-skills-github.md
• best-cursor-skills-github.md

Quick recommendation

• Choose AAS Core if you want complete local catalog access, agent-owned selection, reproducible stack composition, and a preview plan.
• Choose direct distribution if you already know the exact skills you want or your host does not support the Core path.
• Choose a smaller curated repository if a fixed editorial shortlist matters more than complete catalog access and durable desired state.