A tool that monitors PR CI status and automatically attempts to fix failed builds.
Install
mkdir -p .claude/skills/monitor && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/2929" && unzip -o skill.zip -d .claude/skills/monitor && rm skill.zipInstalls to .claude/skills/monitor
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Monitor a PR until CI is 100% green, fixing any failuresKey capabilities
- →Retrieve pull request check status
- →Analyze CI failure logs
- →Generate code fixes for failed checks
- →Commit and push corrections to the repository
- →Poll CI status with a 60-second interval
How it works
The agent checks the status of pull request CI jobs using the GitHub CLI. If failures occur, it reads the logs, applies a fix, pushes the changes, and waits 60 seconds before re-evaluating the status.
Inputs & outputs
When to use monitor
- →Automating PR build fixes
- →Monitoring long-running CI jobs
- →Reducing manual intervention for failed tests
About this skill
Monitor this PR and ensure it's 100% green. If any CI checks fail, analyze the failure, fix the issue, and push the fix. Repeat until all checks pass.
Steps:
- Get current PR status with
gh pr checks - If all green, done
- If any failing, get the failure logs
- Analyze and fix the issue
- Commit and push the fix
- Sleep 60s between status checks (CI can take a while)
- Repeat until 100% green
$ARGUMENTS
When not to use it
- →When CI failures are caused by infrastructure outages
- →When the repository requires manual approval for commits
Limitations
- →Requires the CI to provide readable failure logs
- →Limited to issues that can be resolved via code commits
How it compares
Unlike manual debugging, this agent automates the cycle of log analysis, code modification, and status verification until the build succeeds.
Compared to similar skills
monitor side by side with the closest alternatives in the catalog.
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
gh-fix-ci
openai
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.
fix-sync
ClickHouse
Fix the "CH Inc sync" job in a pull request by resolving conflicts in the corresponding clickhouse-private sync PR.
gha
ykdojo
Analyze GitHub Actions failures and identify root causes
github-actions-failure-debugging
Rabithua
Guide for debugging failing GitHub Actions workflows. Use this when asked to debug failing GitHub Actions workflows.
country-atlas-ci-fix
dimbo1324
Use when GitHub Actions, pre-commit, tests, typing, lint, SQL lint, Docker smoke, or Playwright checks fail.
github-workflow-automation
ruvnet
Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management