CI Failure Triage and Repair

What it does

When your agent uses it

• A CI run or GitHub Actions job has gone red
• Tests fail and you need to know whether the code or the test is wrong
• A fix-and-rerun loop keeps failing across several files

Example prompts

• “CI is red on my pull request; read the logs and tell me what broke.”
• “The tests will not pass after my refactor, so work out whether the test or the implementation is wrong.”
• “Fix the failing pipeline, but ask me before changing any test expectations.”

Requirements

• Pre-approved tools (allowed-tools): Read, Grep, Bash, Task, Monitor

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1テスト vs 実装判定（Step 0）
2. 2ユーザーの意図を分類（分析 or 修正）
3. 3複雑度を判定（下記参照）
4. 4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
5. 5結果を確認し、必要に応じて再実行

What it can do on your machine

Read from SKILL.md and the folder at commit 2b2b748. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Grep
  • Bash
  • Task
  • Monitor

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • git

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

CI Failure Triage and Repair loads about 1.1k tokens when it runs, and up to ~3.7k if it reads all its reference files. Until then it costs about 54 tokens; SKILL.md has 104 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~54

When it runs · the whole SKILL.md, loaded when a task matches

~1.1k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~3.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Grep, Bash, Task, Monitor

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Chachamaru127/claude-code-harness at commit 2b2b748, republished under its MIT licence (© Chachamaru127). 104 words, ~1,056 tokens.

name

ci

description

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.

allowed-tools

Read, Grep, Bash, Task, Monitor

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…

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…

user-invocable

true

context

fork

argument-hint

[analyze|fix|run]

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                │
└─────────────────────────────────────────┘

⚠️ 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 |

## 🚨 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

# 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

🔍 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

Task tool:
  subagent_type="ci-cd-fixer"
  prompt="依頼種別: {診断のみ|承認済み修正}\n目的と理由: {expected_behavior_and_why}\n担当範囲: {owned_paths}\n完了条件: {DoD_and_required_checks}\n仕様と承認の参照: {spec_and_user_instruction}\n観測ログと再現条件: {error_log_and_reproduction}\n範囲内で原因を調べ、依頼種別に応じて診断または修正を完了してください。判断理由、変更箇所、実行コマンドと結果、未確認点を返してください。テスト/設定の変更は既存の承認ゲートに従ってください。"

🔧 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

© Chachamaru127, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/ci of Chachamaru127/claude-code-harness.

• SKILL.md
• references/analyzing-failures.md
• references/fixing-tests.md

Open the folder on GitHubat commit 2b2b748

Used in 1 other repository

We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in Chachamaru127/claude-code-harness, which our catalogue first saw on October 7, 2026.

• aiskillstore/marketplaceskills/chachamaru127/ci