fix-pr-review-loop

Solid

Use when the user asks to fix a PR review and drive it to approval autonomously — "fix the PR review and loop until approved", "fix-pr-review-loop", "keep addressing review comments until this PR is approved", or as the standalone counterpart to work-on-issue-loop's polling/resolving steps for a PR that already exists. Takes an optional PR number/URL (defaults to the current branch's PR). Repeatedly calls fix-pr-review to resolve the latest review, waits for the resulting re-review from the selected review bot (@claude by default, @codex when selected), and repeats. Stops on a bare LGTM with nothing left to fix; once past 5 review cycles it stops at the first LGTM it sees even if non-blocking findings remain, rather than continuing to chase them.

AI & Automation 49 stars 8 forks Updated 2 days ago MIT

Install

View on GitHub

Quality Score: 83/100

Stars 20%
57
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# fix-pr-review-loop Drive an already-open PR from "has review feedback" to "reviewed to convergence" without stopping in between: resolve the latest review (fix-pr-review), wait for the bot's re-review, and repeat. Past 5 cycles the bar for "done" relaxes — any LGTM ends the loop — so a PR with recurring minor findings doesn't get fix-pr-review'd forever. This skill owns the convergence loop; work-on-issue-loop delegates to steps 2 through 4 here after it opens a PR, then writes its own report step that reuses step 5's terminal-state table with two named deltas (its own "no PR" row, plus the follow-on issue URLs it files). An edit to step 5's table therefore needs a matching edit in work-on-issue-loop step 4. ## Input - Nothing — default to the PR for the current branch (`gh pr view`). - `#<N>` / `<N>` / full URL / `owner/repo#N`. ## Steps ### 1. Resolve the PR and establish the starting state ```bash gh pr view <N|--> --json number,headRefName,headRepositoryOwner,baseRefName,url,state,isDraft ``` - If the PR is already `merged` or `closed`, stop and report — there's nothing to drive. - Fetch the current review feedback using fix-pr-review step 1's three-channel query (formal reviews, issue comments, inline diff threads) to see what has already landed. - **Unaddressed feedback is already present** (a review/comment newer than any prior disposition comment, or an unresolved inline thread): treat it as the first landed review. Set `review_count = 1`, note its timestamp,...

Details

Author
richkuo
Repository
richkuo/rk-skills
Created
2 months ago
Last Updated
2 days ago
Language
JavaScript
License
MIT

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Solid

work-on-issue-loop

Use when the user asks to implement a GitHub issue and drive it through review to completion autonomously — "work on issue and loop until approved", "work-on-issue-loop", or as the automatic follow-on from validate-issue-loop. Runs work-on-issue to implement and open the PR, triggers the first review from the selected review bot itself (@claude by default, @codex when selected), then waits for each review to land and calls fix-pr-review to resolve it. Stops on a bare LGTM with nothing left to fix; once past 5 review cycles it stops at the first LGTM it sees even if non-blocking findings remain, rather than continuing to chase them.

49 Updated 2 days ago
richkuo
Code & Development Listed

review-loop

Bounded review-apply-resolve convergence loop for a GitHub PR (draft PRs are fine). Runs up to N=5 iterations of pr-reviewer → implement-suggestion (--resolve-all) → polish simplify, converging until every review thread is resolved — through a fix OR a reply (answered question, recorded rationale) — so the PR is left with zero open threads (only genuine human-judgment flags stay open). On convergence it also refreshes the PR description to match the shipped diff and, best-effort, notes the linked Linear ticket. Use after opening a draft PR to converge the branch to a clean, review-ready state before undrafting. Also converges CI: after each iteration's push it reads the check state and delegates a red mechanical failure to ci-auto-fix, so convergence means zero open threads AND CI not red (--no-ci opts out; create-pr and autonomous-workflow pass it because they own their own CI phase). On a UI PR it also runs the committed preview-spec block against the live preview deployment once at exit (report-only, never

13 Updated today
mthines