ci-autofix-loop

Automate CI remediation by diagnosing failing checks and applying minimal fixes.

3|Updated Jan 14, 2014
One-click install
npx skills add https://github.com/prateek/dotfiles --skill ci-autofix-loop
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ci-autofix-loop
Source: https://github.com/prateek/dotfiles/tree/main/.agents/skills/ci-autofix-loop
Command: npx skills add https://github.com/prateek/dotfiles --skill ci-autofix-loop

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

End-to-end CI remediation workflow that automatically diagnoses failing checks on a PR or branch and applies minimal fixes to restore green status.

Core Features & Use Cases

  • Enumerate failing checks via GitHub CLI and categorize them into Buildkite failures, GitHub Actions failures, or manual blockers.
  • Diagnose failures using provider logs from Buildkite or GitHub Run logs, extract actionable signals, and map them to minimal code changes.
  • Apply automated fixes, run code-simplifier and code-review steps, commit and push, then re-check and iterate until all checks pass.

Quick Start

Trigger the CI autofix loop on the current branch to diagnose, fix, and re-run failing checks until they are green.

Frequently Asked Questions about ci-autofix-loop

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automatically fix failing CI checks on a pull request?

This automated remediation loop diagnoses failing checks via GitHub CLI, extracts actionable signals from provider logs, applies minimal code fixes, commits, pushes, and re-checks until green.

Does the CI autofix loop work with both Buildkite and GitHub Actions?

Yes, the CI autofix loop supports both Buildkite and GitHub Actions, categorizing failing checks and diagnosing provider logs to apply minimal fixes across both platforms.

What do I need to set up before running automated CI remediation?

You need the gh CLI for GitHub integration, Buildkite access, and a configured repository to enumerate failing checks, extract provider logs, and commit fixes.

How does automated CI diagnosis map build failures to code fixes?

Automated CI diagnosis extracts actionable signals from Buildkite or GitHub Run logs, maps them to minimal code changes, and runs code-simplifier and code-review steps before re-checking.

What happens when automated CI fixes fail to make checks pass?

The loop iterates by diagnosing remaining failures from provider logs, applying additional minimal fixes, committing, pushing, and re-checking until all checks pass.

Can I use this to fix failing checks on a feature branch instead of a PR?

Yes, the automated remediation loop applies to feature branches as well as PRs, diagnosing and fixing failing checks in GitHub Actions and Buildkite until green.