Fetch CI errors from GitHub Actions and fix them
Scanned 6/5/2026
Install to Claude Code
npx -y skills add event4u-app/agent-config --skill fix-ci --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Fix Ci?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/event4u-app-fix-ci)More formats (shields.io, HTML) on the badges page.
---
model_tier: medium
name: fix:ci
pack: engineering-base
tier: 2
cluster: fix
sub: ci
skills: [github-ci, quality-tools]
description: Fetch CI errors from GitHub Actions and fix them
suggestion:
eligible: true
trigger_description: "CI is failing, fix the GitHub Actions errors, the pipeline is red"
trigger_context: "open PR with failing checks"
workspaces:
- agent-config-maintainer
packs:
- meta
---
# /fix ci
## Instructions
### 1. Identify the failing CI run
- Get the current branch name from `git branch --show-current`.
- Fetch the latest CI run for this branch via GitHub API:
- `GET /repos/{owner}/{repo}/actions/runs?branch={branch}&per_page=5`
- Find the most recent failed run.
### 2. Get the failure details
- Fetch the jobs for the failed run: `GET /repos/{owner}/{repo}/actions/runs/{run_id}/jobs`
- For each failed job, fetch the logs: `GET /repos/{owner}/{repo}/actions/jobs/{job_id}/logs`
- If logs are not available via API, check the check-runs and status endpoints:
- `GET /repos/{owner}/{repo}/commits/{sha}/check-runs`
- `GET /repos/{owner}/{repo}/commits/{sha}/status`
### 3. Analyze and fix
- Parse the error output to identify the root cause.
- Detect the project type: if `artisan` exists → Laravel, otherwise → Composer (see `rules/docker-commands.md`).
- Common CI failures:
- **PHPStan errors** — fix the code, do NOT add to baseline or ignoreErrors.
- **ECS (coding standard) errors** — run `vendor/bin/ecs check --fix` (auto-fix).
- **Rector changes** — run `vendor/bin/rector process` (auto-fix).
- **Test failures** — read the failing test, understand the assertion, fix the code or test.
- **Biome / TypeScript errors** — run `npm run biome:fix` or `npm run tscheck` and fix.
- Fix errors in the local codebase.
### 4. Verify
- Re-run the failing tool locally (inside the PHP container) to confirm the fix.
- If multiple tools failed, fix and verify each one.
### Rules
- **Do NOT commit or push.** Only apply local fixes.
- **Do NOT skip or ignore errors** — fix the root cause.
- If a fix is unclear, explain the error and ask the user for guidance.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.