メニュー
Auto-select test tiers based on change scope — unit for small, full suite for large. Use when running tests, discussing testing strategy, or after code modifications.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/laurigates/claude-plugins --skill test-tier-selectionコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Install, configure and troubleshoot MCP servers. Use when adding/enabling servers, editing .mcp.json, fixing OAuth, or when a server runs stale code after an upstream fix.
FinOps snapshot — org billing, workflow stats, cache usage. Use when you want a high-level view of CI spending or workflow health before diving deeper.
GitHub Actions billing, workflow efficiency, and waste analysis at org or repo level. Use when investigating CI/CD costs, wasted runs, or optimizing triggers.
SKILL.md を表示中
SOC 職業分類に基づく
| created | "2025-12-16T00:00:00.000Z" |
| modified | "2026-07-31T00:00:00.000Z" |
| reviewed | "2026-04-25T00:00:00.000Z" |
| name | test-tier-selection |
| description | Auto-select test tiers based on change scope — unit for small, full suite for large. Use when running tests, discussing testing strategy, or after code modifications. |
| user-invocable | false |
| allowed-tools | Read, Glob, Grep |
Automatic guidance for selecting appropriate test tiers based on change context and scope.
| Use this skill when... | Use test-consult instead when... |
|---|---|
| Mechanically deciding which tier to run for a given change | Reviewing overall test pyramid balance or strategy |
| Mapping change type (refactor, API, UI) to required tiers | Designing a new feature's test approach |
| Justifying why an E2E run is or isn't needed | Diagnosing flaky tests in an existing suite |
| Picking between test-quick, test-run, and test-full | Setting up a project's test infrastructure (use test-setup) |
| Tier | Duration | Scope | When to Run |
|---|---|---|---|
| Unit | < 30s | Single function/module | After every code change |
| Integration | < 5min | Component interactions | After feature completion |
| E2E | < 30min | Full user flows | Before commit/PR |
| Change Type | Unit | Integration | E2E |
|---|---|---|---|
| Single function fix | Required | Skip | Skip |
| New feature (1 file) | Required | Required | Skip |
| Multi-file feature | Required | Required | Required |
| Refactoring | Required | Required | Optional |
| API changes | Required | Required | Required |
| UI changes | Required | Optional | Required |
| Bug fix (isolated) | Required | Optional | Skip |
| Database changes | Required | Required | Required |
| Config changes | Required | Required | Optional |
Escalate to Integration when:
Escalate to E2E when:
# Tier 1: Unit (fast feedback)
/test:quick
# Tier 2: Integration (feature completion)
/test:full --coverage
# Tier 3: E2E (pre-commit)
/test:full
Consult test-architecture agent when:
3 flaky tests detected
Consult test-runner agent when:
Consult system-debugging agent when:
1. Run /test:quick
2. If pass: Continue working
3. If fail: Fix immediately
1. Run /test:full --coverage
2. Check coverage targets met
3. If gaps: /test:consult coverage
1. Run /test:full
2. All tiers must pass
3. Review coverage report
1. /test:consult new-feature
2. Write tests (TDD)
3. Run /test:quick during development
4. Run /test:full before PR
This skill auto-activates when:
/test:* commands invoked