testcase-generator SKILL.md skillA
testcase-generator from joe-qai/qa-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add joe-qai/qa-skills/testcase-generator@git:20260501.afda12cPins git:20260501.afda12c in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- joe-qai/qa-skills
- Path
testcase-generator/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260501.afda12c, committed May 1, 2026
- First version recorded
- Mar 11, 2026
- Size
- 33,214 bytes
- Repository stars
- 30
- License
- none declared
业务流程导向的测试用例生成器。只有在接收到PRD文档、MD文档、TXT文档、Word文档时，执行 /testcase-generator 才调用此技能进行测试用例设计生成。当用户需要评审已有用例、编写测试方案、设计测试场景、规划测试策略、评估测试覆盖率时也调用此技能。当用户提到测试用例、测试方案、测试计划、测试场景、测试覆盖、用例评审、怎么测、如何验证、测试设计、质量保障、冒烟测试、回归测试等任何与测试用例设计相关的话题时调用。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 业务流程导向的测试用例生成器 (testcase-generator) ## 1. 目标 从需求文档中识别业务功能流程，按照业务流程顺序设计可执行的测试用例。生成的用例必须符合质量评估标准，保证易执行性。 ## 2. 执行步骤（按顺序执行） > **重要**：本技能触发后，模型应首先读取 `references/prompts.md` 作为执行提示词模板，按照其中的角色定义、思考链（CoT）、用例结构、Few-Shot 示例和用例评审报告模板来生成测试用例。触发本技能后，请按以下7个阶段执行（阶段1→阶段7）。**请严格按顺序执行，任何阶段都不允许跳过，包括阶段4的模块评审报告和阶段7的用例评审报告，并生成所有必要的报告文件**。 ### Multi-Agent 串行Pipeline架构 本技能采用 Multi-Agent 串行Pipeline架构，将测试用例生成流程拆分为4个独立子Agent串行执行： | 子Agent | 职责 | 所属阶段 | | ------------- | ----------------------- | -------- | | **需求分析Agent** | 读取需求文档，识别功能模块、业务流程、约束条件 | 阶段3：需求解析 | | **模块评审Agent** | 评审模块生成结果，输出评审结论 | 阶段4：模块评审 | | **用例生成Agent** | 基于测试点生成具体测试用例 | 阶段6：用例生成 | | **用例评审Agent** | 执行用例评审，输出评审报告 | 阶段7：用例评审 | **阶段与Agent映射**： ``` 阶段3：需求解析 → 需求分析Agent 阶段4：模块评审 → 模块评审Agent 阶段5：测试策略 → （无独立Agent，整合在需求解析中） 阶段6：用例生成 → 用例生成Agent 阶段7：用例评审 → 用例评审Agent ``` ### 执行流程（必须按顺序） ``` ┌─────────────────────────────────────────────────────────────────────────────┐ │ testcase-generator 执行流程 │ ├─────────────────────────────────────────────────────────────────────────────┤ …
Read the whole file at its exact version.
How to install
mdr add joe-qai/qa-skills/testcase-generator@sha256:cfc514b4f91f8f2aThe line at the top of this page pins the label git:20260501.afda12c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_hfzn6hrrktzr3wds)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Mar 11, 2026 and May 1, 2026, about one every 25 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260501.afda12c latest | 2026-05-01 | afda12c | 33,214 B | A | view · diff |
| git:20260325.34f3a7e | 2026-03-25 | 34f3a7e | 7,886 B | A | view · diff |
| git:20260311.13a323e | 2026-03-11 | 13a323e | 20,183 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (33214 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
joe-qai/qa-skills · 30 stars · license none declared · pushed 2026-09-29 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_hfzn6hrrktzr3wds GET https://markdownregistry.com/api/v1/resolve?ref=joe-qai/qa-skills/testcase-generator GET https://markdownregistry.com/api/v1/blob/cfc514b4f91f8f2aaa54871ecb713d84ff11553a7890b6034df06a85b5125766
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.