GROK BOT TOOLS · SKILL
Failing test triage, proposed diff only失敗したテストの原因調査と修正差分の提案
Runs the named failing tests, traces the first supported cause, and proposes a small diff. Stops before applying it, weakening tests, committing or pushing.
指定された失敗テストを実行し、根拠のある最初の原因をたどって、小さな修正差分を提案します。差分の適用、テストの弱体化、コミットやプッシュの前に止まります。
Where it goesどこに貼るか
Grok Build: save the file as .grok/skills/failing-test-triage/SKILL.md in the repository, or as ~/.grok/skills/failing-test-triage/SKILL.md for every project. It then shows up as the slash command /failing-test-triage.
Grok Build:リポジトリの .grok/skills/failing-test-triage/SKILL.md に保存します。すべてのプロジェクトで使うなら ~/.grok/skills/failing-test-triage/SKILL.md に。スラッシュコマンド /failing-test-triage として呼べるようになります。
First three moves最初の3手
- Fill the blanks and save the text as ./.grok/skills/failing-test-triage/SKILL.md in the repository.
- Open the repository in Grok Build and invoke /failing-test-triage for one local failing test.
- Compare the command output, cited lines and proposed diff before approving any edit.
- 空欄を埋め、リポジトリ内の ./.grok/skills/failing-test-triage/SKILL.md に文面を保存します。
- Grok Build でリポジトリを開き、ローカルで失敗するテスト1件を対象に /failing-test-triage を呼び出します。
- 編集を承認する前に、コマンドの出力、参照行、提案された差分を照らし合わせます。
Where it stops止まる条件
- Before applying a diff, committing, pushing, merging, deploying or using force operations: ask for approval.
- Before weakening, skipping or deleting tests: keep the existing checks intact.
- Before sending messages, publishing, purchasing, paying, deleting files or changing production: ask for approval.
- When the command is unsafe, the environment is missing or the failure cannot be reproduced: report the gap without inventing a cause.
- 差分の適用、コミット、プッシュ、マージ、デプロイ、強制操作の前に、承認を求めます。
- テストの弱体化、スキップ、削除はせず、既存の検証内容を保ちます。
- メッセージの送信、公開、購入、支払い、ファイルの削除、本番環境の変更の前に、承認を求めます。
- コマンドが安全に実行できない、必要な環境がない、失敗を再現できない場合は、原因を作らず不足を報告します。
Blanks to fill埋める空欄
| Blank空欄 | What goes there入れるもの |
|---|---|
[REPOSITORY] | Local repository to inspect and run tests in.調査とテスト実行の対象となるローカルリポジトリです。 |
[TEST_COMMAND] | Exact command for the failing tests in a local test environment.ローカルのテスト環境で失敗テストを実行する正確なコマンドです。 |
[FAILURE_LOG] | Existing failure output, with its command and date if known.既存の失敗ログです。分かれば実行コマンドと日時も添えます。 |
Replace every bracket. Leave none behind.
角かっこはすべて置き換え、残さないでください。
The text文面
Download SKILL.mdSKILL.md で持ち帰る Fork itフォークする Results & questions結果・質問を書く
--- name: failing-test-triage description: Run named failing tests and trace their first supported cause when asked to diagnose a repository test failure. Return a small proposed diff without applying it. when-to-use: diagnose a failing test, trace this test failure, explain a failed assertion metadata: author: BotShelf Vampire (unofficial, not xAI) short-description: Test failure evidence and a proposed diff license: MIT --- # Failing test triage, proposed diff only ## When to use Use this when I ask you to investigate failing repository tests. Keep the scope to the named failures and their direct causes. ## Inputs and access - Local repository: [REPOSITORY]. - Test command: [TEST_COMMAND]. - Existing failure output: [FAILURE_LOG]. Read source, tests and local configuration. Run commands only in the local test environment. Inspect the command and its setup before running it; stop if it could contact production or perform an action needing approval. ## Steps 1. Record the current revision and existing working changes. Leave those changes alone. 2. Read the supplied failure output and identify the command, failing test and earliest relevant error. Separate setup failures from assertion failures. 3. Run the specified tests once. Capture the exit status and relevant output without secrets. If setup is unavailable, stop execution and describe what is missing. 4. Trace the earliest causal failure through the test and implementation. Cite file names and lines. Distinguish a supported cause from a hypothesis; later failures may be consequences. 5. Propose the smallest implementation change as a diff in the response. Explain how it addresses the cause and which focused checks should follow. Do not apply it or change expectations to hide a failure. ## Check the result Confirm the diagnosis agrees with the captured output and cited source. Check that the proposed diff preserves test coverage and unrelated working changes. List commands actually run separately from suggested checks. Do not describe an unapplied fix as successful. ## What to return Return the reproduction command and outcome, first supported cause, evidence locations, proposed diff, and next checks. Include incomplete work and unresolved hypotheses. ## Needs my approval Ask before applying edits, installing dependencies, committing, pushing, merging, deploying or using force operations. Stop before sending messages, publishing, purchasing, paying, deleting files or changing production. Never weaken, skip or delete tests to make the failure disappear. ## If data is missing or stale If the log refers to another revision, identify the mismatch. If the failure does not recur, report that outcome and the remaining uncertainty. Do not invent a cause or run unrelated commands indefinitely.
License: MIT. Free, no sign-up. Use is at your own risk. BSV does not run it or set it up for you.
ライセンス:MIT。無料・登録不要。利用は自己責任です。BSVが代わりに実行・セットアップすることはありません。
What it adds to the official page公式ページに足しているもの
The official page describes the structure and discovery of Grok Build skills. This text adds a failure investigation sequence, evidence checks and a proposed-diff boundary.
公式ページは、Grok Build のスキルの構造と読み込み方法を説明しています。この文面は、失敗原因を調べる手順、根拠の確認、差分の提案で止める境界を加えています。
Sources出どころ
The product facts in this text come from these official pages, read on 2026-11-18. Products change: when a page and this text disagree, the page is right.
この文面の製品に関する記述は、次の公式ページ(2026-11-18 に確認)に基づいています。製品は変わります。公式ページとこの文面が食い違うときは、公式ページが正です。
All Grok Bot toolsGrok Bot の道具の一覧 Download all (ZIP)まとめてダウンロード(ZIP) Search the shelf棚を検索