# 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 2,005+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.

Repository: https://github.com/sickn33/agentic-awesome-skills
Canonical: https://ross.abutalabs.com/products/agentic-awesome-skills
Homepage: https://sickn33.github.io/agentic-awesome-skills/
Language: Python
License: MIT
License Family: permissive
Topics: agentic-skills, ai-agents, antigravity, claude-code, mcp, ai-workflows, codex-cli, developer-tools, gemini-cli, skill-library, agent-skills, ai-agent-skills, antigravity-skills, claude-code-skills, codex-skills, cursor-skills, gemini-skills, ai-coding, cursor, kiro
Last push: 2026-08-26T18:48:08+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 16
- inputs: {"age_days": 231, "days_push": 7, "days_rel": 7, "gap_med": 1, "n_releases_24m": 190}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 45481, forks 6660 (observed 2026-08-28T04:12:09.550022+00:00)

## What it is
AAS Core is a local, agent-first control plane that gives coding agents like Codex, Claude Code, and Gemini CLI read-only access to a catalog of 2,000+ agentic skills. It provides a CLI, a local MCP server, catalog search, stack validation, and immutable plan previews so agents can select and compose skill stacks reproducibly before any changes are applied.

## Use cases
- discover agentic skills for coding agents from a local catalog
- let Claude Code or Codex select and validate skill stacks for my project
- generate an aas-stack.json manifest and plan preview before applying changes
- run a local MCP server exposing a skill catalog to AI agents
- validate agent-chosen skill combinations without writing to my repo

## When to choose
- you use coding agents like Codex, Claude Code, Cursor, or Gemini CLI and want curated, reproducible skill stacks
- you want agent-owned skill selection with validation and human review before any target changes
- you need a local, self-hosted skill catalog with MCP integration

## When to avoid
- you need automatic skill application or recovery, which remain experimental and unsupported
- you want a hosted control plane or managed service rather than a local tool
- you expect the tool to rank or recommend skills—it only validates agent-owned selections

## Facets
- artifact type: cli-tool
- maturity: active
- function: mcp, search-engine, developer-tools, cli, plugin-system
- domain: developer-tools, large-language-models
- platform: python, cli, cross-platform, self-hosted
- tags: agentic-skills, skill-catalog, claude-code, codex-cli, gemini-cli, cursor, mcp-server, skill-discovery, stack-validation, agent-workflows, ai-agents, automation

## Member repositories
- sickn33/agentic-awesome-skills (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:09.550022+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:21:40.678264+00:00, confidence not recorded.
  - readme: https://github.com/sickn33/agentic-awesome-skills (fetched 2026-08-28T04:12:09.550022+00:00, sha c1dce443d48b)
  - homepage: https://sickn33.github.io/agentic-awesome-skills/ (fetched 2026-08-29T07:45:15.246892+00:00, sha 9effb928328a)
- Data as of 2026-08-30T08:39:29.467469+00:00.