Install any skill in seconds. Free to start, no credit card required.
Get Started Free →saffron-health/address-review
Address PR review comments systematically.
Passed 13 of 18 test cases with the skill, and 11 of 18 without it.
and 1 more in the full report
3 fixed13 passed either way5 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
PR #30 has feedback from Claude Bot requiring specific refactoring. The developer explicitly asks to address the bot review comments. How should this request be handled?
| Checked | Without skill | With skill |
|---|---|---|
| Processes the bot review comments because explicit user instruction was provided | Missed | Passed |
The instructions your model reads when the skill loads.
Address PR review comments systematically.
Get review comments: Use gh api graphql to fetch all review threads and comments for the PR. (If a PR number is not provided in the input, look up the PR for the current branch).
Analyze comments: Review all the feedback to understand what changes are needed
Address each comment systematically: For each review comment:
Quality assurance: Run type-check, build, and lint to ensure all changes are correct
Commit and push: Stage and commit all changes with an appropriate message and push.
Mark comments resolved: Query PR review threads with gh api graphql to get thread IDs and outdated status. Resolve all addressed threads using mutation { resolveReviewThread(input: {threadId: "THREAD_ID"}) { thread { isResolved } } }. Always resolve outdated threads.
// Query review threads:
gh api graphql -f query='query { repository(owner: "owner", name: "repo") { pullRequest(number: N) { reviewThreads(first: 100) { nodes { id isResolved isOutdated comments { nodes { body } } } } } } }'
// Resolve thread:
gh api graphql -f query='mutation { resolveReviewThread(input: {threadId: "THREAD_ID"}) { thread { isResolved } } }'
test cases passed, vs 11 / 18 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.