Analyzes code-level test coverage (lines, branches, functions, statements) from npm test reports and recommends tests to address gaps and improve quality.
npx claudepluginhub joshuarweaver/cascade-code-general-misc-3 --plugin asiaostrich-universal-dev-standardsThis skill is limited to using the following tools:
Analyze test coverage across multiple dimensions and provide actionable recommendations.
Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.
Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
Analyze test coverage across multiple dimensions and provide actionable recommendations.
多維度分析測試覆蓋率並提供可執行的建議。
Related: For requirement-level coverage (which AC have tests?), use
/ac-coverageinstead. This skill (/coverage) focuses on code-level coverage (lines, branches, functions).相關：如需需求層級覆蓋率（哪些 AC 有對應測試？），請改用
/ac-coverage。此技能（/coverage）專注於程式碼層級覆蓋率。
| Dimension | What it Measures | 測量內容 |
|---|---|---|
| Line | Lines of code executed | 執行的程式碼行數 |
| Branch | Decision paths taken | 決策路徑覆蓋 |
| Function | Functions called | 呼叫的函數 |
| Statement | Statements executed | 執行的陳述式 |
| Level | Coverage | Use Case | 適用場景 |
|---|---|---|---|
| Minimum | 60% | Legacy code | 遺留程式碼 |
| Standard | 80% | Most projects | 大多數專案 |
| High | 90% | Critical systems | 關鍵系統 |
| Critical | 95%+ | Safety-critical | 安全關鍵 |
/coverage - Run full coverage analysis | 執行完整覆蓋率分析
/coverage src/auth - Analyze specific module | 分析特定模組
/coverage --recommend - Get test recommendations | 取得測試建議
After /coverage completes, the AI assistant should suggest:
覆蓋率分析完成。建議下一步 / Coverage analysis complete. Suggested next steps:
- 覆蓋率不足 → 執行
/tdd補齊測試 — Coverage gaps → Run/tddto add tests- 已達標 → 執行
/checkin品質關卡 ⭐ Recommended / 推薦 — Targets met → Run/checkinquality gates- 發現熱點 → 執行
/refactor改善可測試性 — Hotspots found → Run/refactor
完整的 AI 行為定義請參閱對應的命令文件：
/coverageFor complete AI agent behavior definition, see the corresponding command file:
/coverage