How do I install the CI Fixer skill?

Run npx skillmds@latest add adamsilverstein/ci-fixer in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is CI Fixer safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with CI Fixer?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is CI Fixer free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published CI Fixer?

adamsilverstein (@adamsilverstein) published this skill. Their other Agent Skills are listed on their SkillMD profile.

CI Fixer by adamsilverstein — Agent Skill

Name: CI Fixer
Rating: 4.5 (4 reviews)
Author: adamsilverstein

CI Fixer

Fix failing CI tests on a PR and ensure all checks pass. Use when the user wants to fix CI failures, resolve failing tests, fix linting errors on a PR, or ensure all GitHub Actions/CI checks pass. Triggers include requests like 'fix the CI', 'fix failing tests on this PR', 'make the CI pass', 'fix linting errors', 'resolve CI failures', or any CI/test fixing task.

File contents

CI Fixer Skill

Diagnose, fix, and monitor CI failures on GitHub PRs. Persistent until all required checks pass.

Workflow

Analyze PR - Get PR number, run gh pr checks to identify failures
Diagnose - Use gh run view [RUN_ID] --log-failed to get error details
Fix - Apply targeted fixes based on failure type (see below)
Verify locally - Run tests/linters locally before pushing
Commit & Push - Stage changes, commit with clear message, push
Monitor - Wait 3 minutes, check gh pr checks, repeat until all pass

Essential Commands

# Check CI status
gh pr checks [PR_NUMBER]
gh pr checks [PR_NUMBER] --json name,state,conclusion

# Get failure logs
gh run view [RUN_ID] --log-failed

# Check for failing jobs (returns empty if all pass/skip)
gh pr checks [PR_NUMBER] --json name,state,conclusion | jq '.[] | select(.state == "completed" and .conclusion != "success" and .conclusion != "skipped")'

Status meanings:

conclusion: "success" or "skipped" = OK
conclusion: "failure" = Needs fix
state: "pending"/"queued"/"in_progress" = Still running, wait

Fix Strategies

Linting: Run auto-fix first (npx eslint --fix, npx prettier --write, ./vendor/bin/phpcbf)

Tests: Read test + implementation, determine which is wrong, fix appropriately, verify locally

Types: Check TypeScript (npx tsc --noEmit) or PHPStan output, fix annotations/mismatches

Builds: Check logs for missing deps, syntax errors, import issues

Important Rules

Always verify fixes locally before pushing
Make atomic commits with clear messages
Don't blindly auto-fix; review changes
Ask user if fix is ambiguous or could break functionality
Be persistent: continue monitor/fix loop until all checks pass or user cancels

---name: ci-fixerdescription: Fix failing CI tests on a PR and ensure all checks pass. Use when the user wants to fix CI failures, resolve failing tests, fix linting errors on a PR, or ensure all GitHub Actions/CI checks pass. Triggers include requests like 'fix the CI', 'fix failing tests on this PR', 'make the CI pass', 'fix linting errors', 'resolve CI failures', or any CI/test fixing task.---# CI Fixer SkillDiagnose, fix, and monitor CI failures on GitHub PRs. Persistent until all required checks pass.## Workflow1. **Analyze PR** - Get PR number, run `gh pr checks` to identify failures2. **Diagnose** - Use `gh run view [RUN_ID] --log-failed` to get error details3. **Fix** - Apply targeted fixes based on failure type (see below)4. **Verify locally** - Run tests/linters locally before pushing5. **Commit & Push** - Stage changes, commit with clear message, push6. **Monitor** - Wait 3 minutes, check `gh pr checks`, repeat until all pass## Essential Commands```bash# Check CI statusgh pr checks [PR_NUMBER]gh pr checks [PR_NUMBER] --json name,state,conclusion# Get failure logsgh run view [RUN_ID] --log-failed# Check for failing jobs (returns empty if all pass/skip)gh pr checks [PR_NUMBER] --json name,state,conclusion | jq '.[] | select(.state == "completed" and .conclusion != "success" and .conclusion != "skipped")'```**Status meanings:**- `conclusion: "success"` or `"skipped"` = OK- `conclusion: "failure"` = Needs fix- `state: "pending"/"queued"/"in_progress"` = Still running, wait## Fix Strategies**Linting:** Run auto-fix first (`npx eslint --fix`, `npx prettier --write`, `./vendor/bin/phpcbf`)**Tests:** Read test + implementation, determine which is wrong, fix appropriately, verify locally**Types:** Check TypeScript (`npx tsc --noEmit`) or PHPStan output, fix annotations/mismatches**Builds:** Check logs for missing deps, syntax errors, import issues## Important Rules- Always verify fixes locally before pushing- Make atomic commits with clear messages- Don't blindly auto-fix; review changes- Ask user if fix is ambiguous or could break functionality- Be persistent: continue monitor/fix loop until all checks pass or user cancels

Frequently asked questions