# openclaw/agent-skills

Useful skills for agents and claws.

Repository: https://github.com/openclaw/agent-skills
Canonical: https://ross.abutalabs.com/products/openclaw-agent-skills
Language: Python
License: MIT
License Family: permissive
Last push: 2026-09-02T11:33:53+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 35, longevity 7
- inputs: {"age_days": 103, "days_push": 0, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1075, forks 97 (observed 2026-09-03T02:15:15.756102+00:00)

## What it is
A shared catalog of reusable skills (workflow definitions and helper scripts) for coding agents like Codex and Claude Code, installable via a CLI script. It centralizes common workflows such as code review closeout, remote validation, and session viewing so they can be reused across repositories.

## Use cases
- install shared skills for claude code
- reuse code review workflow across repos
- share agent workflows between codex and claude
- validate user-visible behavior against a contract
- view agent session transcripts locally
- hand off a task from one agent to another
- publish coding sessions to a read-only catalog

## When to choose
- you use Codex or Claude Code and want consistent workflows across many repositories
- you want to avoid copying SKILL.md files manually between projects
- you need structured review closeout or remote validation workflows for agents

## When to avoid
- you need product-specific skills tied to a single repo
- you don't use AI coding agents
- you need a general-purpose agent framework rather than a curated skill catalog

## Facets
- artifact type: library
- maturity: active
- function: developer-tools, workflow-automation, code-review, testing, documentation
- domain: developer-tools
- platform: cli, cross-platform, python
- tags: agent-skills, codex, claude-code, skill-catalog, prompt-workflows, code-review-automation, automation, ai-agents

## Member repositories
- openclaw/agent-skills (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:15.756102+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 2026-08-30T06:55:31.204703+00:00, confidence not recorded.
  - readme: https://github.com/openclaw/agent-skills (fetched 2026-09-03T02:15:15.756102+00:00, sha f281a91384f9)
- Data as of 2026-08-30T08:39:29.467469+00:00.