PluginBench
Skill
Review
Audit score 70

loop-on-ci

cursor/plugins

Monitor PR checks and fix failures until green using gh pr checks.

What is loop-on-ci?

Automates the process of watching pull request CI checks and iterating on failures until all required checks pass. Uses gh pr checks as the authoritative source for PR-attached checks, including both GitHub Actions and other CI systems.

  • Resolves the active PR for the current branch
  • Inspects all PR-attached checks (not just GitHub Actions)
  • Watches pending checks with fail-fast mode to catch failures early
  • Diagnoses and summarizes check failures
  • Re-validates the full check set after each push until green
  • Provides GitHub Actions logs for failed runs when available

How to install loop-on-ci

npx skills add https://github.com/cursor/plugins --skill loop-on-ci
Prerequisites
  • GitHub CLI (gh) installed and authenticated
  • An active pull request on the current branch
Claude Code
Cursor
Windsurf
Cline

How to use loop-on-ci

  1. 1.Run the skill to resolve the PR for your current branch
  2. 2.Inspect the current PR checks to see their status
  3. 3.If checks have failed, diagnose those failures; if pending, watch with fail-fast mode
  4. 4.Make fixes and push your changes
  5. 5.Re-run the check inspection after each push
  6. 6.Repeat until all required checks are green

Use cases

Good for
  • Iterating on CI failures in a pull request until all checks pass
  • Monitoring multiple types of checks (GitHub Actions, third-party CI systems) from a single source of truth
  • Quickly identifying and fixing the root cause of check failures without manual log inspection
  • Preventing accidental merges by ensuring all required checks are green before proceeding
Who it's for
  • Software engineers working with pull requests
  • CI/CD practitioners managing multi-check workflows
  • Teams using GitHub with mixed CI systems

loop-on-ci FAQ

Why use gh pr checks instead of gh run list?

gh pr checks includes all PR-attached checks from any CI system, while gh run list only covers GitHub Actions. This ensures you see the complete picture of all required checks.

What should I do if a check failure is unrelated to my PR?

If the failure appears fixed on main, merge the latest main into your branch instead of adding unrelated fixes to your PR.

How should I handle flaky tests?

Retry once and document the flake evidence. Do not repeatedly force pushes to work around intermittent failures.

Can I use --no-verify to bypass hooks?

No. The skill enforces that you should not bypass hooks to force progress; instead, address the underlying failure cause.

Full instructions (SKILL.md)

Source of truth, from cursor/plugins.


name: loop-on-ci description: Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.

Loop on CI

Trigger

Need to watch a branch or pull request and iterate on CI failures until all required checks are green.

Use gh pr checks as the source of truth. It includes all PR-attached checks, while gh run list only covers GitHub Actions.

Workflow

  1. Resolve the PR for the current branch.
  2. Inspect current PR checks before waiting.
  3. If checks already failed, diagnose those failures first.
  4. If checks are pending, watch with gh pr checks --watch --fail-fast.
  5. After each push, re-check the full PR check set and repeat until green.

Commands

# Resolve the active PR
gh pr view --json number,url,headRefName

# Inspect all attached checks
gh pr checks --json name,bucket,state,workflow,link

# Watch pending checks and fail fast
gh pr checks --watch --fail-fast

# GitHub Actions logs, when the failing check links to a GHA run
gh run view <run-id> --log-failed

Guardrails

  • Keep each fix scoped to a single failure cause when possible.
  • Do not bypass hooks (--no-verify) to force progress.
  • If the failure is clearly unrelated to the PR and appears fixed on main, merge latest main instead of bloating the PR with unrelated fixes.
  • If failures are flaky, retry once and report flake evidence.
  • Re-run gh pr checks --json name,bucket,state,workflow,link after every push; the check set can change.

Output

  • Current CI status
  • Failure summary and fixes applied
  • PR URL once checks are green