How do I install the Coverage skill?

Run npx skillmds@latest add asiaostrich/coverage in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Coverage safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Coverage?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Coverage free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Coverage?

AsiaOstrich (@asiaostrich) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Coverage by asiaostrich — Agent Skill

Name: Coverage
Rating: 4.2 (5 reviews)
Author: AsiaOstrich

Coverage

[UDS] Analyze code-level test coverage across the eight-dimension framework and recommend which gaps to close. Use when: coverage percentages look healthy but defects still ship, judging test completeness beyond line percentage, setting coverage targets. Not for: requirement-level AC-to-test traceability — use /ac-coverage; writing the missing tests — use /tdd or /spec-derive. Keywords: test coverage, eight dimensions, line coverage, branch coverage, test quality, 測試覆蓋率, 八維度, 測試完整性.

AsiaOstrich a54fe25 2 files · 12.6 KB Updated Sep 10, 2026

File contents

Test Coverage Assistant | 測試覆蓋率助手

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-coverage instead. 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。

Coverage Dimensions | 覆蓋率維度

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

8-Dimension Framework | 八維度框架

Code Coverage - Lines, branches, functions
Requirement Coverage - All requirements have tests
Risk Coverage - High-risk areas prioritized
Integration Coverage - Component interaction paths
Edge Case Coverage - Boundary conditions tested
Error Coverage - Error handling paths verified
Permission Coverage - Access control scenarios
AI Generation Quality - AI-generated test effectiveness

Coverage Targets | 覆蓋率目標

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

Workflow | 工作流程

Run coverage tool - Generate coverage report | 產生覆蓋率報告
Analyze gaps - Identify untested areas | 識別未測試區域
Prioritize - Rank by risk and importance | 依風險排序
Recommend tests - Suggest specific tests to add | 建議新增測試
Track progress - Monitor coverage over time | 追蹤進度

Usage | 使用方式

/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

Next Steps Guidance | 下一步引導

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 /tdd to add tests

已達標 → 執行 /checkin 品質關卡 ⭐ Recommended / 推薦 — Targets met → Run /checkin quality gates

發現熱點 → 執行 /refactor 改善可測試性 — Hotspots found → Run /refactor

Reference | 參考

Detailed guide: guide.md
Core standard: test-completeness-dimensions.md

AI Agent Behavior | AI 代理行為

完整的 AI 行為定義請參閱對應的命令文件：/coverage

For complete AI agent behavior definition, see the corresponding command file: /coverage

---name: coveragedescription: [UDS] Analyze code-level test coverage across the eight-dimension framework and recommend which gaps to close. Use when: coverage percentages look healthy but defects still ship, judging test completeness beyond line percentage, setting coverage targets. Not for: requirement-level AC-to-test traceability — use /ac-coverage; writing the missing tests — use /tdd or /spec-derive. Keywords: test coverage, eight dimensions, line coverage, branch coverage, test quality, 測試覆蓋率, 八維度, 測試完整性.---# Test Coverage Assistant | 測試覆蓋率助手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-coverage` instead. 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。## Coverage Dimensions | 覆蓋率維度| 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 |## 8-Dimension Framework | 八維度框架1. **Code Coverage** - Lines, branches, functions2. **Requirement Coverage** - All requirements have tests3. **Risk Coverage** - High-risk areas prioritized4. **Integration Coverage** - Component interaction paths5. **Edge Case Coverage** - Boundary conditions tested6. **Error Coverage** - Error handling paths verified7. **Permission Coverage** - Access control scenarios8. **AI Generation Quality** - AI-generated test effectiveness## Coverage Targets | 覆蓋率目標| 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 |## Workflow | 工作流程1. **Run coverage tool** - Generate coverage report | 產生覆蓋率報告2. **Analyze gaps** - Identify untested areas | 識別未測試區域3. **Prioritize** - Rank by risk and importance | 依風險排序4. **Recommend tests** - Suggest specific tests to add | 建議新增測試5. **Track progress** - Monitor coverage over time | 追蹤進度## Usage | 使用方式```/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```## Next Steps Guidance | 下一步引導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 `/tdd` to add tests> - 已達標 → 執行 `/checkin` 品質關卡 ⭐ **Recommended / 推薦** — Targets met → Run `/checkin` quality gates> - 發現熱點 → 執行 `/refactor` 改善可測試性 — Hotspots found → Run `/refactor`## Reference | 參考- Detailed guide: [guide.md](./guide.md)- Core standard: [test-completeness-dimensions.md](../../core/test-completeness-dimensions.md)## AI Agent Behavior | AI 代理行為> 完整的 AI 行為定義請參閱對應的命令文件：[`/coverage`](../commands/coverage.md#ai-agent-behavior--ai-代理行為)>> For complete AI agent behavior definition, see the corresponding command file: [`/coverage`](../commands/coverage.md#ai-agent-behavior--ai-代理行為)

Frequently asked questions