Borrowing it
Nothing to install: this file belongs to shenjingnan/xiaozhi-client. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/shenjingnan/xiaozhi-client/main/.agents/skills/e2e-coverage-analyzer/SKILL.mdgit clone --depth 1 https://github.com/shenjingnan/xiaozhi-clientWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/shenjingnan/xiaozhi-client/e2e-coverage-analyzer)<a href="https://agentmods.dev/skills/shenjingnan/xiaozhi-client/e2e-coverage-analyzer"><img src="https://agentmods.dev/badge/skills/shenjingnan/xiaozhi-client/e2e-coverage-analyzer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/shenjingnan/xiaozhi-client/e2e-coverage-analyzer"><img src="https://agentmods.dev/badge/skills/shenjingnan/xiaozhi-client/e2e-coverage-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00038 | $0.02003 |
| Opus 5.5 | $0.00015 | $0.00801 |
| Sonnet 5.5 | $0.00008 | $0.00401 |
| Haiku 4.5 | $0.00004 | $0.00200 |
Grade A, and why
e2e-coverage-analyzer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E 覆盖率分析器
分析当前分支相对于 main 的改动,评估 tests/e2e/ 中现有测试用例是否足以覆盖改动涉及的功能点。
上下文
- 当前分支: !
git branch --show-current - 分叉点 commit: !
git merge-base main HEAD - 改动文件列表: !
git --no-pager diff --name-only main...HEAD - 改动内容摘要(统计): !
git --no-pager diff --stat main...HEAD - 改动详细内容: !
git --no-pager diff main...HEAD
现有 e2e 测试用例清单
!find tests/e2e -maxdepth 1 -type d ! -path tests/e2e | sort
你的任务
按以下四个阶段执行,每个阶段输出清晰的中文报告。
阶段一:改动分析
-
过滤核心逻辑文件:从改动文件列表中排除以下非逻辑文件类型:
- 配置文件:
*.config.*,*.env*,tsconfig*.json,.eslintrc*,.prettierrc* - 类型定义文件:
*.d.ts,types/*.ts,interfaces/*.ts - 文档和说明文件:
*.md,CHANGELOG*,LICENSE* - 锁定文件:
package-lock.json,pnpm-lock.yaml,yarn.lock - CI/CD 配置:
.github/**,.gitlab-ci*,Dockerfile*,docker-compose* - 测试文件本身:
**/*.test.ts,**/*.spec.ts,tests/**,__tests__/**
保留以下类型的文件作为核心逻辑文件:
src/web/**下的组件、页面、hooks、store、工具函数src/server/**下的服务、路由、控制器、中间件、处理器src/下各模块的源码逻辑文件
- 配置文件:
-
识别功能点:对每个核心逻辑文件,结合 git diff 的实际改动内容,分析其涉及的功能维度:
- 页面/路由:涉及哪个页面或路由(如
/dashboard) - UI 组件:涉及哪些 UI 组件(如 MCP 工具表格、对话框、表单等)
- 交互行为:涉及的点击、输入、切换、拖拽等用户操作
- 数据流:涉及的数据请求、状态变更、事件处理
- 视觉呈现:涉及的新增/修改的 UI 元素、样式变化
- 页面/路由:涉及哪个页面或路由(如
-
输出改动分析报告,格式如下:
=== 改动分析报告 === 核心逻辑文件(共 N 个): 1. src/web/pages/Dashboard.tsx - 涉及页面:Dashboard 页面 - 涉及功能点:新增状态卡片 X、修改表格列 Y 排除的非逻辑文件(共 M 个): - package.json(依赖变更) ...
阶段二:覆盖匹配
-
读取所有现有 e2e 测试用例:遍历
tests/e2e/下每个子目录中的test.md文件,提取每个用例覆盖的功能点关键词。 -
建立映射关系:将阶段一识别的功能点与现有测试用例进行匹配。匹配规则:
- 精确匹配:测试用例名称或步骤明确提及了改动的功能点
- 关联匹配:测试用例覆盖了改动所在的页面/组件区域,虽然未直接测试该具体改动,但执行路径会经过相关代码
- 无匹配:改动涉及的功能点没有任何测试用例覆盖
-
输出覆盖匹配报告,格式如下:
=== 覆盖匹配报告 === 已覆盖的功能点: | 功能点 | 匹配测试用例 | 匹配类型 | |--------|-------------|---------| | Dashboard 页面加载 | 测试Dashboard页面加载 | 精确匹配 | 缺少覆盖的功能点: | 功能点 | 涉及文件 | 风险等级 | |--------|---------|---------| | 新增的 XXX 功能 | src/web/components/XXX.tsx | 高 | 覆盖率总结: - 总功能点数:N - 已覆盖:M(X%) - 未覆盖:K(Y%)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 208 lines · 38 tokens per session scan A 2bc85ff934d5
e2e-coverage-analyzer is a skill published in the GitHub repository shenjingnan/xiaozhi-client (345 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 2,003 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.