Iterate on PR Until CI Passes

SkillAI & models

iterate-pr is a skill for AI agents that handles the loop of fixing a pull request until its checks pass. It automates the feedback-fix-push-wait cycle: when CI fails or reviewers leave feedback, the agent applies fixes, pushes updates, and waits for the next round of results. This saves you from manually re-running checks and pushing small corrections yourself.

Use Iterate on PR Until CI Passes in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Iterate on PR Until CI Passes and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the Iterate on PR Until CI Passes skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Have an AI agent that can load skills.

Iterate on PR Until CI PassesStart free

What your AI can do with it

  • Fix CI failures on a pull request automatically
  • Address review feedback left on a PR
  • Push fixes continuously until all checks are green
  • Automate the feedback-fix-push-wait cycle

Getting started

  1. Have an AI agent that can load skills.
  2. Add the iterate-pr skill to your agent's available skills.
  3. Open or identify a pull request whose checks are failing or that has review feedback.
  4. Ask your agent to iterate on the PR until CI passes.

What this skill tells your AI

The instructions your AI receives, as published by davila7/claude-code-templates in cli-tool/components/skills/sentry/iterate-pr/SKILL.md and read by ahel’s review.

Continuously iterate on the current branch until all CI checks pass and review feedback is addressed.

Requires: GitHub CLI (gh) authenticated and available.

Process

Step 1: Identify the PR

gh pr view --json number,url,headRefName,baseRefName

If no PR exists for the current branch, stop and inform the user.

Step 2: Check CI Status First

Always check CI/GitHub Actions status before looking at review feedback:

gh pr checks --json name,state,bucket,link,workflow

The bucket field categorizes state into: pass, fail, pending, skipping, or cancel.

Important: If any of these checks are still pending, wait before proceeding:

  • sentry / sentry-io
  • codecov
  • cursor / bugbot / seer
  • Any linter or code analysis checks

These bots may post additional feedback comments once their checks complete. Waiting avoids duplicate work.

Step 3: Gather Review Feedback

Once CI checks have completed (or at least the bot-related checks), gather human and bot feedback:

Review Comments and Status:

gh pr view --json reviews,comments,reviewDecision

Inline Code Review Comments:

gh api repos/{owner}/{repo}/pulls/{pr_number}/comments

PR Conversation Comments (includes bot comments):

gh api repos/{owner}/{repo}/issues/{pr_number}/comments

Look for bot comments from: Sentry, Codecov, Cursor, Bugbot, Seer, and other automated tools.

Step 4: Investigate Failures

For each CI failure, get the actual logs:

# List recent runs for this branch
gh run list --branch $(git branch --show-current) --limit 5 --json databaseId,name,status,conclusion

# View failed logs for a specific run
gh run view <run-id> --log-failed

Do NOT assume what failed based on the check name alone. Always read the actual logs.

Step 5: Validate Feedback

For each piece of feedback (CI failure or review comment):

  1. Read the relevant code - Understand the context before making changes
  2. Verify the issue is real - Not all feedback is correct; reviewers and bots can be wrong
  3. Check if already addressed - The issue may have been fixed in a subsequent commit
  4. Skip invalid feedback - If the concern is not legitimate, move on

Step 6: Address Valid Issues

Make minimal, targeted code changes. Only fix what is actually broken.

Step 7: Commit and Push

git add -A
git commit -m "fix: <descriptive message of what was fixed>"
git push

Step 8: Wait for CI

Use the built-in watch functionality:

gh pr checks --watch --interval 30

This waits until all checks complete. Exit code 0 means all passed, exit code 1 means failures.

Alternatively, poll manually if you need more control:

gh pr checks --json name,state,bucket | jq '.[] | select(.bucket != "pass")'

Step 9: Repeat

Return to Step 2 if:

  • Any CI checks failed
  • New review feedback appeared

Continue until all checks pass and no unaddressed feedback remains.

Exit Conditions

Success:

  • All CI checks are green (bucket: pass)
  • No unaddressed human review feedback

Ask for Help:

  • Same failure persists after 3 attempts (likely a flaky test or deeper issue)
  • Review feedback requires clarification or decision from the user
  • CI failure is unrelated to branch changes (infrastructure issue)

Stop Immediately:

  • No PR exists for the current branch
  • Branch is out of sync and needs rebase (inform user)

Tips

  • Use gh pr checks --required to focus only on required checks
  • Use gh run view <run-id> --verbose to see all job steps, not just failures
  • If a check is from an external service, the link field in checks JSON provides the URL to investigate

Signals

GitHub stars
32k
Forks
4k
Last commit
Oct 2026

Questions

When should I use iterate-pr?
Use it when you need to fix CI failures, address review feedback, or continuously push fixes until all checks on a pull request are green.
What does it automate?
It automates the feedback-fix-push-wait cycle: applying fixes, pushing updates, and waiting for the next round of CI or review results.
Does it stop when checks pass?
It keeps iterating on the PR until all checks are green.
Advanced
Item type
skill
Key
iterate-pr
Source
github.com/davila7/claude-code-templates