Menu
Fetch PR review comments, verify each against real code/docs, fix valid issues, commit and push
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
A brief description of what this skill does
Iterativer Plan-Review-Loop mit OpenAI Codex als zweiter Meinung. Use when the user runs /pair-review, asks for cross-model verification of a plan file in ~/.claude/plans/, or — most importantly — before calling ExitPlanMode in plan mode to validate the proposed plan with adversarial review.
Review and integrate upstream saas-starter template changes into a fork. Detects the fork point (forks are content-copies that share no git ancestor), lists every upstream commit since the last sync, and guides reviewing each one to integrate, skip as already-present, or exclude with a reason, adapting to this fork's divergences (branding, theme, env/deploy, i18n, fork-owned features), then ships one consolidated PR. Use when asked to sync or update from upstream, pull template changes, review what the template added, or apply an upstream fix.
Canonical Convex backend coding patterns — validators, function registration, queries, mutations, actions, schemas, pagination, cron jobs, file storage, and Better Auth integration. Use when writing or reviewing any Convex backend code.
Skill for integrating Autumn - the billing and entitlements layer over Stripe.
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
| name | triage-reviews |
| description | Fetch PR review comments, verify each against real code/docs, fix valid issues, commit and push |
| disable-model-invocation | true |
| argument-hint | [PR number] |
Fetch all review comments on the current PR, verify each finding against real code, fix valid issues, and push.
Determine the PR number:
$ARGUMENTS if providedgh pr view --json number --jq .numberFetch ALL comments (reviewers post in multiple places):
gh api --paginate repos/{owner}/{repo}/pulls/{pr}/reviews
gh api --paginate repos/{owner}/{repo}/pulls/{pr}/comments
gh api --paginate repos/{owner}/{repo}/issues/{pr}/comments
Extract unique findings — deduplicate across Copilot, Greptile, and human reviewers. Group by file and line.
For EVERY finding, verify against real code before accepting or rejecting:
btca resources to see what's available, then btca ask -r <resource> -q "..." for library/framework questionsFix all Valid findings
Run the project's lint/test commands (check CLAUDE.md for exact commands)
git add only changed files, git commit with message:
fix: Address PR review feedback
- <one-line summary per fix>
Push: gt submit (or git push if not using Graphite)
Present a final summary table of ALL findings with verdicts:
| # | Source | File:Line | Finding | Verdict | Reason |
|---|