メニュー
Run complete test suite in pyramid order — unit, integration, E2E. Use when running all tests before a PR, generating coverage reports, or doing pre-commit verification.
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-full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。
SKILL.md を表示中
SOC 職業分類に基づく
| created | "2025-12-16T00:00:00.000Z" |
| modified | "2026-07-04T00:00:00.000Z" |
| reviewed | "2026-04-25T00:00:00.000Z" |
| allowed-tools | Task, TodoWrite |
| args | [--coverage] [--parallel] [--report] |
| argument-hint | [--coverage] [--parallel] [--report] |
| description | Run complete test suite in pyramid order — unit, integration, E2E. Use when running all tests before a PR, generating coverage reports, or doing pre-commit verification. |
| name | test-full |
| agent | general-purpose |
| context | fork |
| Use this skill when... | Use test-quick instead when... |
|---|---|
| Running the complete pyramid (unit, integration, E2E) before a PR | You only need fast unit-test feedback |
| Generating coverage and HTML reports across all tiers | Iterating on a single failing file (use test-focus) |
| Forcing parallel pre-commit verification across the suite | Running tests for one specific framework run (use test-run) |
| Producing a CI-like full pass locally | Asking strategic questions about strategy (use test-consult) |
find . -maxdepth 1 \( -name 'pyproject.toml' -o -name 'package.json' -o -name 'Cargo.toml' -o -name 'go.mod' \)find . -type d \( -name "test*" -o -name "__tests__" \)find . -maxdepth 1 \( -name 'playwright.config.*' -o -name 'cypress.config.*' \)echo "CI=$CI GITHUB_ACTIONS=$GITHUB_ACTIONS"--coverage: Generate coverage report--parallel: Force parallel execution--report: Generate detailed HTML reportDelegate this task to the test-runner agent.
Use the Agent tool with subagent_type: test-runner to run the complete test suite. Pass all the context gathered above and specify All Tiers execution.
The test-runner agent should:
Run tests in pyramid order (fail fast):
Apply options:
--coverage: Enable coverage reporting for all tiers--parallel: Run tests in parallel where safe--report: Generate HTML reportStop on failure at any tier (don't waste time on later tiers)
Provide pyramid summary:
## Full Test Suite: [PASSED|FAILED]
| Tier | Passed | Failed | Duration |
|-------------|--------|--------|----------|
| Unit | X | Y | Zs |
| Integration | X | Y | Zs |
| E2E | X | Y | Zs |
Coverage: XX% (target: 80%)
### Failures
[Grouped by tier with file:line references]
### Recommended Actions
- [Specific next steps]
Post-action guidance:
/test:quick for iteration/test:consult coverageProvide the agent with:
The agent has expertise in:
For large test suites, spawn teammates for parallel test execution:
| Teammate | Focus | Value |
|---|---|---|
| Unit test runner | Fast unit tests | Quick feedback loop, fail-fast |
| Integration test runner | Component interactions | Service boundary validation |
| E2E test runner | Full user flows | End-to-end verification |
Each teammate runs its tier independently and reports results via the shared task list. This is optional — the skill runs tiers sequentially without agent teams.
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.