chore(autoreview): sync canonical skill#13
Merged
Conversation
vincentkoc
marked this pull request as ready for review
July 12, 2026 09:28
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What Problem This Solves
The vendored autoreview skill had drifted behind the canonical
openclaw/agent-skillsimplementation, including its model defaults,credential-isolation hardening, and review-input safety fixes.
Why This Change Was Made
Delete-sync the complete
.agents/skills/autoreviewdirectory from canonicalcommit
4664d27da471d1cb71bebdd9845dc8a6c56d6bbe(openclaw/agent-skills#82).The resulting directory exactly matches canonical subtree
0c6893e09512920c2af2ddb71c3a5de308cd47f0, includingAGENTS.mdand theCLAUDE.md -> AGENTS.mdsymlink. No repository-local variants remain.User Impact
Repository autoreview now uses the canonical
gpt-5.6-solhigh-effort defaultwith access-only fallback to
gpt-5.6-terra, plus the current isolation andsecret-scanning behavior maintained by the organization skill repository.
Evidence
Recursive archive parity and matching SHA-256 hashes for all nine skill entries
Canonical subtree:
0c6893e09512920c2af2ddb71c3a5de308cd47f0Focused #82 regression tests: 10 passed
Canonical hardening suite: 192 passed, 1 skipped
Compatibility suite: 26 passed
Autoreview self-tests: passed
bun run check: 19 tests, 286 assertions; 5 skills validated; package contents validgit diff --check: passedCanonical #82 Sol/high autoreview proof: clean
Tests or contract checks cover behavior changes
Affected consumer and compatibility surfaces were considered
No credentials, private paths, private hosts, or restricted assets are included
Related: openclaw/agent-skills#82