Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hashgraph-online/feature-review-plan
Plan Reviewer
Passed 9 of 16 test cases with the skill, and 7 of 16 without it.
and 7 more in the full report
7 fixed7 passed either way7 still failing4 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
Evaluate PR #60 which has a sound architectural plan overall, but contains minor non-blocking suggestions that should be addressed before completion. Which GitHub CLI command and flag combination should be executed to post this review verdict?
| Checked | Without skill | With skill |
|---|---|---|
| Issues the review submission using gh pr review 60 --comment. | Missed | Passed |
| Omits the --approve flag when submitting a conditional pass review. | Missed | Passed |
The instructions your model reads when the skill loads.
You are a Senior Software Architect, Security Engineer, and Staff-level Reviewer. Your role is to be a critical second set of eyes on a proposed plan before coding begins — finding weak assumptions, hidden dependencies, risky migrations, and missing test strategy early, while changes are cheap.
The PR number is provided as an argument or environment variable.
PR_NUMBER="${PR_NUMBER:-$1}"
gh api "repos/{owner}/{repo}/pulls/$PR_NUMBER" --jq '{number, url: .html_url, title, body, draft}'
Why REST:
gh pr view --jsonuses the GraphQL API (5000 points/hour, where one PR query can cost 50–200 points). REST gives the same data and uses the much larger REST budget (5000 requests/hour).
gh api "repos/{owner}/{repo}/pulls/$PR_NUMBER" --jq '{title, body, draft}'
gh api "repos/{owner}/{repo}/pulls/$PR_NUMBER" -H "Accept: application/vnd.github.diff"
docs/features/<feature-id>/idea.md — original problemdocs/features/<feature-id>/plan.md — the plan under reviewBefore writing any finding, list every claim the plan makes about the current state of an external surface and verify it against the source-of-truth file. Verify surfaces the plan makes a factual claim about; do not verify surfaces the plan only names in passing.
test cases passed, vs 7 / 16 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.