Automated summary
Diagnoses failing CI pipelines (logs, builds, tests) and drives safe fixes, with a guardrail that forbids papering over tests.
Strengths
- A Step 0 triage gate that separates implementation bugs, stale test expectations, and environment problems before touching code
- An explicit ban list of shortcuts (it.skip, deleted assertions, continue-on-error, eslint-disable) paired with the correct alternative
- Uses structured git log flags (--format, --topo-order, --raw) to pinpoint the culprit commit and the file/line at fault
- Hands off to a ci-cd-fixer subagent (dry-run by default) after two failed fix-and-rerun loops
Limitations
- Claude Code specific: depends on the Task tool, subagents, and ${CLAUDE_SKILL_DIR}, so it is not portable as-is
- Does not cover initial pipeline setup, only diagnosis and repair of an already-red pipeline
- Halts automation to request explicit approval whenever a test or config file must change
Use it whenever a CI pipeline is red and you need a root cause or a safe fix.
Do not load it for local build failures, ordinary implementation or review work, or first-time CI setup.
Security analysis
CautionThe skill is a legitimate CI troubleshooting guide with no destructive, exfiltrating, or obfuscated instructions. It does use powerful tools (Bash and Task) and delegates to a fixer subagent, so listing it warrants caution rather than a clean safe rating.
- •Allows Bash; examples are read-only git log commands, but Bash could be used more broadly by the agent.
- •Uses Task to launch a ci-cd-fixer subagent that may modify files; SKILL.md claims dry-run default and approval gates, but the subagent's code is not included for verification.
Examples
CI が落ちました。ログを見て原因を調べて、実装の問題かテストの問題か環境の問題か切り分けてください。The GitHub Actions build job is failing. Find the root cause, fix it, and get the pipeline green again — do not skip or delete any tests.Which commit broke CI on main? Narrow it down with git log and show me the failing file and line.name: ci description: "CIが赤くなったら呼んで。パイプライン消防隊、出動します。Use when user mentions CI failures, build errors, test failures, or pipeline issues. Do NOT load for: local builds, standard implementation work, reviews, or setup." description-en: "CI red? Call us. Pipeline fire brigade deploys. Use when user mentions CI failures, build errors, test failures, or pipeline issues. Do NOT load for: local builds, standard implementation work, reviews, or setup." description-ja: "CIが赤くなったら呼んで。パイプライン消防隊、出動します。Use when user mentions CI failures, build errors, test failures, or pipeline issues. Do NOT load for: local builds, standard implementation work, reviews, or setup." allowed-tools: ["Read", "Grep", "Bash", "Task"] user-invocable: false context: fork argument-hint: "[analyze|fix|run]"
CI/CD Skills
CI/CD パイプラインに関する問題を解決するスキル群です。
発動条件
- 「CIが落ちた」「GitHub Actionsが失敗」
- 「ビルドエラー」「テストが通らない」
- 「パイプラインを直して」
機能詳細
| 機能 | 詳細 | トリガー | |------|------|----------| | 失敗分析 | See references/analyzing-failures.md | 「ログを見て」「原因を調べて」 | | テスト修正 | See references/fixing-tests.md | 「テストを直して」「修正案を出して」 |
実行手順
- テスト vs 実装判定(Step 0)
- ユーザーの意図を分類(分析 or 修正)
- 複雑度を判定(下記参照)
- 上記の「機能詳細」から適切な参照ファイルを読む、または ci-cd-fixer サブエージェント起動
- 結果を確認し、必要に応じて再実行
Step 0: テスト vs 実装判定(品質判定ゲート)
CI 失敗時、まず原因の切り分けを行う:
CI 失敗報告
↓
┌─────────────────────────────────────────┐
│ テスト vs 実装判定 │
├─────────────────────────────────────────┤
│ エラーの原因を分析: │
│ ├── 実装が間違い → 実装を修正 │
│ ├── テストが古い → ユーザーに確認 │
│ └── 環境問題 → 環境修正 │
└─────────────────────────────────────────┘
禁止事項(改ざん防止)
⚠️ CI 失敗時の禁止事項
以下の「解決策」は禁止です:
| 禁止 | 例 | 正しい対応 |
|------|-----|-----------|
| テスト skip 化 | `it.skip(...)` | 実装を修正 |
| アサーション削除 | `expect()` を消す | 期待値を確認 |
| CI チェック迂回 | `continue-on-error` | 根本原因修正 |
| lint ルール緩和 | `eslint-disable` | コードを修正 |
判断フロー
🔴 CI が失敗しています
**判断が必要です**:
1. **実装が間違い** → 実装を修正 ✅
2. **テストの期待値が古い** → ユーザーに確認を求める
3. **環境の問題** → 環境設定を修正
⚠️ テストの改ざん(skip化、アサーション削除)は禁止です
どれに該当しますか?
承認が必要な場合
テスト/設定の変更がやむを得ない場合:
## 🚨 テスト/設定変更の承認リクエスト
### 理由
[なぜこの変更が必要か]
### 変更内容
[差分]
### 代替案の検討
- [ ] 実装の修正で解決できないか確認した
ユーザーの明示的な承認を待つ
Git log 拡張フラグの活用(CC 2.1.49+)
CI 失敗時の原因コミット特定に構造化ログを活用します。
原因コミットの特定
# 構造化フォーマットでコミット分析
git log --format="%h|%s|%an|%ad" --date=short -10
# トポロジカル順序で時系列分析
git log --topo-order --oneline -20
# 変更ファイルと原因の紐付け
git log --raw --oneline -5
主な活用場面
| 用途 | フラグ | 効果 |
|------|--------|------|
| 失敗原因の特定 | --format="%h|%s" | コミット一覧の構造化 |
| 時系列での追跡 | --topo-order | マージ順序を考慮した追跡 |
| 変更影響の把握 | --raw | ファイル変更の詳細表示 |
| マージ除外分析 | --cherry-pick --no-merges | 実コミットのみを抽出 |
出力例
🔍 CI 失敗原因分析
最近のコミット(構造化):
| Hash | Subject | Author | Date |
|------|---------|--------|------|
| a1b2c3d | feat: update API | Alice | 2026-02-04 |
| e4f5g6h | test: add tests | Bob | 2026-02-03 |
変更ファイル(--raw):
├── src/api/endpoint.ts (Modified) ← 型エラー発生
├── tests/api.test.ts (Modified)
└── package.json (Modified)
→ a1b2c3d のコミットが原因の可能性大
型エラー: src/api/endpoint.ts:42
サブエージェント連携
以下の条件を満たす場合、Task tool で ci-cd-fixer を起動:
- 修正 → 再実行 → 失敗のループが 2回以上 発生
- または、エラーが複数ファイルにまたがる複雑なケース
起動パターン:
Task tool:
subagent_type="ci-cd-fixer"
prompt="CI失敗を診断・修正してください。エラーログ: {error_log}"
ci-cd-fixer は安全第一で動作(デフォルト dry-run モード)。
詳細は agents/ci-cd-fixer.md を参照。
VibeCoder 向け
🔧 CI が壊れたときの言い方
1. **「CI が落ちた」「赤くなった」**
- 自動テストが失敗している状態
2. **「なんで失敗してるの?」**
- 原因を調べてほしい
3. **「直して」**
- 自動で修正を試みる
💡 重要: テストを「ごまかす」修正は禁止です
- ❌ テストを消す、スキップする
- ⭕ コードを正しく直す
「テストが間違ってそう」と思ったら、
まず確認してから対応を決めましょう
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/ci-cd-pipeline-failure-diagnosis-and-fix-mmh8qqwf/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/ci-cd-pipeline-failure-diagnosis-and-fix-mmh8qqwf' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/ci-cd-pipeline-failure-diagnosis-and-fix-mmh8qqwf/download' --output '.skill-downloads/ci-cd-pipeline-failure-diagnosis-and-fix-mmh8qqwf/SKILL.md.part' && mv '.skill-downloads/ci-cd-pipeline-failure-diagnosis-and-fix-mmh8qqwf/SKILL.md.part' '.skill-downloads/ci-cd-pipeline-failure-diagnosis-and-fix-mmh8qqwf/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/ci-cd-pipeline-failure-diagnosis-and-fix-mmh8qqwf/SKILL.md' && test -s '.skill-downloads/ci-cd-pipeline-failure-diagnosis-and-fix-mmh8qqwf/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/ci' && cp -R '.skill-downloads/ci-cd-pipeline-failure-diagnosis-and-fix-mmh8qqwf' '.claude/skills/ci'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/ci-cd-pipeline-failure-diagnosis-and-fix-mmh8qqwf'openskills read 'ci-cd-pipeline-failure-diagnosis-and-fix-mmh8qqwf'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/ci-cd-pipeline-failure-diagnosis-and-fix-mmh8qqwf/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Configure a Chat Channel with SecretRefs
DevOps
Set up chat channels using non-interactive commands, with secrets only as SecretRefs. Covers gather, mutate, repair, and prove steps for reliable delivery.
Investigate ClickHouse CI Failures
DevOps
Investigate a ClickHouse CI failure end-to-end from a PR or S3 report URL. Fetches failed tests, classifies flaky vs real regression, and checks for existing issues/fixes.
Ansible PR Review
DevOps
Reviews an Ansible PR following the project's standardized process, including changelog checks, test coverage validation, and feedback tracking.