feat: add code-review-calibration skill (non-default) - #512
Draft
rbren wants to merge 2 commits into
Draft
Conversation
Adds skills/code-review-calibration, a skill that mines a repository's own commit history, bug fixes, reverts, conventions, testing strategy, CI coverage, and past PR reviews to generate a calibrated .agents/skills/code-review.md with cited failure patterns. Registered in marketplaces/openhands-extensions.json without defaultEnabled, so it stays opt-in from the catalog UI. Co-authored-by: openhands <openhands@all-hands.dev>
CI requires every skill directory to ship a README.md and a .plugin/plugin.json with vendor symlinks so Codex and Claude Code can load it. Co-authored-by: openhands <openhands@all-hands.dev>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Why
The existing
code-reviewskill reviews from general principles, so its feedback is much the same in every repository. What a reviewer actually needs is knowledge of how this codebase breaks and what "correct" looks like here - and that knowledge is recoverable from the repo's own commit log, bug fixes, reverts, and past PR reviews.This skill generates that calibrated reviewer instead of hand-writing it.
Summary
skills/code-review-calibration/SKILL.md, a skill that investigates a repository in two halves - how it breaks (hotspots, reverts, SZZ fix-inducing commits, temporal coupling) and how it works (conventions, testing strategy, CI boundary, ownership and blast radius) - then writes or updates.agents/skills/code-review.mdwith failure patterns that each cite two or more SHAs.marketplaces/openhands-extensions.jsonundercode-quality.defaultEnabledis deliberately omitted, so the skill is opt-in from the catalog UI rather than seeded into new workspaces.skills/index.jsand the README catalog table.Issue Number
How to Test
Confirm the skill is registered but not default-enabled:
Expected:
found: true defaultEnabled: undefinedandin defaults: false, withDEFAULT_ENABLED_SKILL_NAMESunchanged at 11 entries.To exercise the skill itself, enable it in a workspace with a repo that has real history and ask for a calibrated code review skill; it should produce
.agents/skills/code-review.mdwhere every failure pattern cites SHAs from that repo.Video/Screenshots
n/a - skill content and catalog metadata only.
Notes
AGENTS.md.AGENTS.md,"defaultEnabled": falseis never written - absence is how a skill stays off - so the entry simply omits the key.not in any marketplace: ./plugins/issue-duplicate-checkerwarning from the sync script predates this branch and is unrelated.This PR was created by an AI agent (OpenHands) on behalf of @rbren.