Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Kokxi/qa-test-skills --skill qa-execution-observationgit clone --depth 1 https://github.com/Kokxi/qa-test-skillsWrote 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/kokxi/qa-test-skills/qa-execution-observation)<a href="https://agentmods.dev/skills/kokxi/qa-test-skills/qa-execution-observation"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-execution-observation/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/kokxi/qa-test-skills/qa-execution-observation"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-execution-observation.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 | $0.00144 | $0.02434 |
| Opus 5 | $0.00072 | $0.01217 |
| Sonnet 5 | $0.00029 | $0.00487 |
| Haiku 4.5 | $0.00014 | $0.00243 |
Grade A, and why
qa-execution-observation 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 4d 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
执行观察力
核心原则
同样在执行,专家看到了更多信息。通过六路信号模型(功能表现/接口响应/日志报错/UI渲染/数据一致性/性能指标)系统记录执行观察。每轮执行后输出观察记录,标注异常信号。
深度要求(参考值)
关键指标:根据场景复杂度调整观察深度
| 复杂度 | 信号捕获要求 | 说明 |
|---|---|---|
| 简单场景 | 至少捕获3路信号 | 单一功能路径 |
| 中等场景 | 至少捕获5路信号 | 多分支交互场景 |
| 复杂场景 | 全部6路信号 | 跨模块/分布式场景 |
六路信号模型
信号1:功能结果(最基础)
观察要点:
├─ 结果正确性:是否符合预期?
├─ 结果完整性:是否有遗漏?
├─ 结果一致性:多次执行结果一致吗?
└─ 结果边界:边界值处理正确吗?
观察方法:
- 对比预期结果
- 多次执行验证
- 边界值测试
信号2:性能信号(容易忽略)
观察要点:
├─ 响应时间:比正常慢多少?
├─ 加载时间:页面加载耗时?
├─ 处理时间:后台处理耗时?
└─ 资源消耗:CPU/内存/网络占用?
观察方法:
- 计时对比
- 浏览器DevTools
- 性能监控工具
异常信号:
- 响应时间 > 2秒
- 页面加载 > 3秒
- 后台处理 > 5秒
信号3:日志信号(关键线索)
观察要点:
├─ 错误日志:有没有ERROR?
├─ 警告日志:有没有WARN?
├─ 异常堆栈:有没有Exception?
├─ 业务日志:关键操作有没有记录?
└─ 性能日志:有没有慢查询?
观察方法:
- 实时查看日志文件
- grep关键错误信息
- 关注异常堆栈
日志位置:
- 应用日志:/var/log/app/
- Nginx日志:/var/log/nginx/
- 数据库日志:/var/log/mysql/
信号4:数据信号(验证结果)
观察要点:
├─ 数据创建:数据有没有正确写入?
├─ 数据更新:数据有没有正确更新?
├─ 数据删除:数据有没有正确删除?
├─ 数据一致性:各处数据一致吗?
└─ 数据完整性:数据字段完整吗?
观察方法:
- 直接查询数据库
- 对比缓存和数据库
- 检查数据关联
信号5:前端信号(用户视角)
观察要点:
├─ 页面加载:有没有白屏/卡顿?
├─ 交互响应:点击后有反应吗?
├─ 样式显示:样式正确吗?
├─ 兼容性:不同浏览器表现?
└─ 响应式:不同屏幕尺寸?
观察方法:
- 手动操作观察
- 浏览器DevTools
- 多浏览器测试
信号6:依赖信号(外部影响)
观察要点:
├─ 第三方接口:调用成功吗?
├─ 下游服务:响应正常吗?
├─ 消息队列:消息发送成功吗?
├─ 缓存服务:缓存读写正常吗?
└─ 外部资源:CDN/图片加载正常?
观察方法:
- 查看网络请求
- 检查接口调用
- 监控依赖服务
观察清单
执行前检查
- 测试环境准备好了吗?
- 测试数据准备好了吗?
- 监控工具打开了吗?
- 日志文件准备好了吗?
执行中观察
- 功能结果正确吗?
- 响应时间正常吗?
- 日志有异常吗?
- 数据写入正确吗?
- 前端显示正常吗?
- 依赖调用正常吗?
执行后验证
- 数据状态正确吗?
- 关联数据一致吗?
- 测试数据清理了吗?
- 环境恢复了吗?
异常信号识别
功能异常信号
- 返回错误码
- 返回空数据
- 返回格式错误
- 响应超时
性能异常信号
- 响应时间突增
- 页面加载缓慢
- 后台处理超时
- 资源占用过高
日志异常信号
- ERROR级别日志
- Exception堆栈
- 慢查询日志
- 异常警告
数据异常信号
- 数据未写入
- 数据不一致
- 数据格式错误
- 数据丢失
前端异常信号
- 白屏
- 卡顿
- 样式错乱
- 控制台报错
依赖异常信号
- 接口调用失败
- 服务不可用
- 消息发送失败
- 缓存读写失败
应用场景
执行登录功能测试时 → 六路信号观察:
- 功能:登录成功/失败,页面跳转正确
- 性能:响应时间>3秒(异常信号)
- 日志:控制台有"password validation failed"日志
- 数据:数据库用户状态正确更新
- 前端:错误提示显示在正确位置
- 依赖:认证服务响应正常
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.
- 4d ago Changed 63461dee087a
- 10d ago First seen · 271 lines · 144 tokens per session scan A 7e4f01262b8f
qa-execution-observation is a skill published in the GitHub repository Kokxi/qa-test-skills (24 stars, last pushed 7d ago), licensed MIT. It adds 144 tokens to every session and 2,434 once invoked, about $0.0007 per session on Opus 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
plugin-test
A testing guide for Zhin.js plugins using Vitest, a JavaScript and TypeScript testing framework. It focuses on checking command and tool behavior, ordinary business logic, and the plugin package’s required structure.
javascript-development
JavaScript/TypeScript ES2024+, async/await, DOM manipulation, Node.js, and API integration. Use when writing vanilla JS/TS code, working with REST/fetch APIs, implementing frontend logic, or configuring JS build tools.
nextjs-development
Next.js 16.2.4 with TypeScript — App Router, Server Components, use cache directive, Turbopack dev, Server Actions, ISR, SSR, SSG, MCP devtools, metadata API, route handlers, instrumentation.
php-development
PHP 8.0+ development — XAMPP, RESTful APIs, PDO/MySQL/MariaDB, and authentication. Use when building PHP backends, creating API endpoints, configuring XAMPP, or integrating PHP with databases.
react-development
React 19+ with TypeScript — hooks, custom hooks, state management (useState/useReducer/useContext), React Query/SWR, Tailwind CSS, performance. Use when building React components, apps, or optimizing renders.
tdd-cycle
Red-Green-Refactor test-driven development cycle.