test-spec
Skill4 starsChanged 6 months agoMITView on GitHub
Convert a PRD, bug report, or task description into structured test points and targeted validation commands.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- geekatron/jerrytheir own version, first seen Nov 1, 2026
- mik2win/foureyestheir own version, first seen Oct 8, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- geekatron/jerry★ 37same name
- mik2win/foureyes★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository7 other files it gives its agents.
- acceptance-checkSkill
- bugfixSkill
- implementation-checkSkill
- release-checkSkill
- reviewSkill
- task-specSkill
- token-reportSkill
The file
Files
test-spec
把 PRD、bug 描述或任务条目转成可执行、可验收的测试点,帮助 QA/Engineer 在实现前明确正常路径、失败路径和回归范围。
用法
/test-spec <PRD、bug 或任务描述>
目标
- 从输入中提取验收标准和风险点
- 生成分层测试点,覆盖正常路径、异常路径和边界条件
- 给出适合小步验证的命令或检查模板
- 明确哪些测试需要人工检查、哪些可以自动化
适用场景
- PRD 或任务需要转成 QA 测试点
- bugfix 需要补充回归测试范围
- 实现前需要确认验收路径和边界条件
- 已有验收标准需要拆成可执行检查项
不适用场景
- 直接修复代码缺陷
- 替代 QA 验收结论
- 在需求不清时擅自扩大测试范围
- 执行长时间、全量或高风险命令
测试维度模板
每次输出至少覆盖以下维度,并为每类给出测试目标、输入/前置条件、检查方式和通过标准:
- 正常路径:验证用户或系统按预期完成主流程;说明关键输入、期望输出和最小验证命令。
- 失败路径:验证错误输入、外部依赖失败或前置条件不满足时的行为;说明错误提示、回退路径或不变式。
- 边界条件:覆盖空值、最小/最大值、缺失字段、旧数据结构或兼容输入;说明边界为何相关。
- 回归风险:列出可能受影响的既有能力、关联测试文件和需要复查的历史行为。
- 验证命令模板:给出优先级最高的定向命令、文档检查或手工检查路径,避免默认全量测试。
- 测试数据与环境:说明 fixture、临时目录、环境变量或人工准备项;没有特殊要求时写“无”。
执行规则
- 先定位输入类型:PRD、bug、任务条目或验收标准。
- 测试点必须对应可观察行为或可检查产物。
- 缺少预期行为时先标记待澄清,不得猜测业务目标。
- 优先推荐定向测试、文档检查或最小复现命令。
- 输出必须区分自动验证和人工检查。
示例
/test-spec docs/plan/vision.md 中登录流程 PRD,生成正常路径、失败路径和边界测试点/test-spec bug: opc runs cost 在旧 run_metrics.json 缺 cost 字段时报错,生成回归测试点
输出骨架
[示例用例]
- 从需求生成测试点:输入 PRD/任务 → 输出正常路径、失败路径、边界条件和验收映射
- 从 bug 生成回归测试:输入缺陷现象/复现路径 → 输出复现检查、修复验证和回归风险
[测试目标] ...
[测试点]
- 正常路径:目标 / 输入 / 检查方式 / 通过标准
- 失败路径:触发条件 / 期望失败行为 / 检查方式 / 通过标准
- 边界条件:边界值 / 相关原因 / 检查方式 / 通过标准
- 回归风险:受影响能力 / 关联文件 / 复查方式
- 测试数据与环境:fixture / 临时目录 / 环境变量 / 人工准备项
[验证命令模板]
- ...
[人工检查项]
- ...
[回归风险] ...验收标准
- 至少包含“从需求生成测试点”和“从 bug 生成回归测试”两类示例
- 输出骨架包含测试目标、测试点、验证命令、人工检查和回归风险
- 每个测试维度都有检查方式和通过标准
- 缺少输入或预期行为时能标记待澄清,不输出伪确定结论
验收
- 说明该 skill 把 PRD、bug 或任务描述转成测试点
- 明确 QA/Engineer 责任边界
- 输出测试点可关联到验收标准或缺陷复现路径
- 验证建议优先定向、可复现、低成本
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

