Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →ivanmurzak/github-pr-review-fix
Review and resolve PR comments from GitHub. Validates each comment, fixes legitimate issues.
Passed 11 of 17 test cases with the skill, and 7 of 17 without it.
and 5 more in the full report
8 fixed6 passed either way5 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
Which GraphQL mutation name must be executed to mark a fixed PR thread as closed/resolved on GitHub?
| Checked | Without skill | With skill |
|---|---|---|
| Uses the resolveReviewThread GraphQL mutation | Missed | Passed |
The instructions your model reads when the skill loads.
Review unresolved comments on the GitHub pull request associated with the current branch. Validate each comment, then fix legitimate issues.
$ARGUMENTS contains a PR number, use it.gh pr view --json number,url,headRefName,baseRefName
Fetch PR review comments (not issue-level comments) using the GitHub CLI:
gh api repos/{owner}/{repo}/pulls/{number}/comments --paginate
Filter to comments where the thread is not resolved. Group comments by thread (same in_reply_to_id or same path + line/original_line). For each thread, treat the first comment as the review request and subsequent comments as discussion.
Also fetch general PR comments (issue-level):
gh api repos/{owner}/{repo}/issues/{number}/comments --paginate
If there are zero unresolved comments, report that and stop.
For each unresolved comment or comment thread, spawn a sub-agent in parallel. Use model: "sonnet" for cost efficiency. Each agent validates the comment and, if legitimate, fixes it immediately in place.
Conflict avoidance: If multiple comments target the same file, run those agents sequentially (not in parallel) to avoid edit conflicts. Comments on different files run in parallel.
You are a code review comment validator and fixer. Your job is to determine whether a PR review comment identifies a real issue, and if so, fix it immediately.
test cases passed, vs 7 / 17 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.