Skip to content

feat(autoreview): import OpenClaw closeout review skill - #9

Draft
tonoizer wants to merge 2 commits into
mainfrom
cursor/add-autoreview-skill-dd1b
Draft

feat(autoreview): import OpenClaw closeout review skill#9
tonoizer wants to merge 2 commits into
mainfrom
cursor/add-autoreview-skill-dd1b

Conversation

@tonoizer

Copy link
Copy Markdown
Owner

Summary

Imports Peter Steinberger's autoreview skill from openclaw/agent-skills into this pack.

Changes

  • Add .agents/skills/autoreview/ with upstream SKILL.md, helper scripts, fixtures/tests, and provenance AGENTS.md
  • Add MIT LICENSE.txt and pack-local agents/openai.yaml
  • Add /autoreview Claude slash command wrapper
  • Track source in README.md, THIRD_PARTY_NOTICES.md, and skills-lock.json
  • Add root .gitignore for Python bytecode (matches upstream)

Notes

  • Canonical source remains openclaw/agent-skills; this is a synced import, not a fork of behavior
  • Helper smoke: autoreview --help works; scripts/autoreview_test.py reported 33 tests OK
  • Live engine review still needs Codex/Claude/Pi and TruffleHog on the host

Test plan

  • Validate all SKILL.md frontmatter (name + description)
  • Confirm /autoreview points at the new skill
  • Run ./.agents/skills/autoreview/scripts/autoreview --help
  • Run python3 .agents/skills/autoreview/scripts/autoreview_test.py
  • Optionally run live closeout with --engine codex when credentials are available
Open in Web Open in Cursor 

cursoragent and others added 2 commits July 25, 2026 07:56
Copy Peter Steinberger's openclaw/agent-skills autoreview workflow into the
pack with helper scripts, tests, MIT notice, slash command, and source tracking.

Co-authored-by: Kevin Beier <hey@kevinbeier.com>
Keep the imported skill source-only and ignore Python __pycache__ artifacts.

Co-authored-by: Kevin Beier <hey@kevinbeier.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants