Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/fishzjp/qa-skillsnpx agentmods add skills/fishzjp/qa-skills/test-case-writingWrote 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/fishzjp/qa-skills/test-case-writing)<a href="https://agentmods.dev/skills/fishzjp/qa-skills/test-case-writing"><img src="https://agentmods.dev/badge/skills/fishzjp/qa-skills/test-case-writing/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/fishzjp/qa-skills/test-case-writing"><img src="https://agentmods.dev/badge/skills/fishzjp/qa-skills/test-case-writing.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 | $0.00099 | $0.06705 |
| Opus 5 | $0.00049 | $0.03352 |
| Sonnet 5 | $0.00020 | $0.01341 |
| Haiku 4.5 | $0.00010 | $0.00671 |
Grade A, and why
test-case-writing 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 2d 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
测试用例编写
从需求模型（或原始输入源）与代码，产出人看得懂、能执行的手动用例文件（markmap），并抽取机器可读的 Test Case Schema 供下游 Skill 消费。
落盘产物：{项目}/测试用例_markmap.md（唯一人工维护源）+ {项目}/测试用例.schema.yaml（由 markmap 单向抽取，规则见 ../core/schema-extraction.md）。
When to Use
- 有代码仓库，需基于实际实现编写用例（代码优先，首选场景）
- 给定需求文档/PRD、技术设计方案、API 文档，需要编写测试用例
- 给定 Bug 报告，需要编写回归测试用例
- 需求变更时，增量更新已有测试用例
When NOT to Use
- 端到端测试整个需求（理解→策略→用例→执行→报告）→ 用
qaskill 编排 - 需要系统性需求建模（目标/范围/规则/异常/依赖/不明确项）→ 用
requirement-analysisskill；本 skill 只做轻量输入研读 - "这个功能应该怎么测"（范围/类型/深度/优先级的策略决策）→ 用
test-strategyskill - 事后独立审查存量或他人写的用例 → 用
test-case-reviewskill；本 skill 只做写时自审（阶段四） - 编写自动化测试代码 → 用
automated-e2e-testing（UI）或api-testing（接口）skill - 代码变更后判断回归范围 → 用
regression-testingskill；本 skill 只负责用例文件的增量修改 - 既无代码仓库、也无任何需求/设计文档可参考 → 无从建模与写用例：先走
exploratory-testing探索建立系统理解，或向用户索取输入材料
工作流程
阶段〇：主动索取代码仓库（开工第一件事）
启动测试用例编写前，主动向用户索要被测项目代码仓库：
- 索取内容：① 仓库地址（本地路径或远程 URL）；② 被测分支/tag；③ 本次改动范围（PR/MR 链接或
<base>...<head>diff 范围，无则默认全量） - 提问模板：
🔍 为提升用例准确性，请提供被测项目代码仓库地址与被测分支（若有本次改动的 PR/diff 范围也请给出）。代码将作为功能事实基线，文档作为对照——基于实际实现编写的用例能发现文档与实现的不一致、定位潜在 bug，纯文档模式则无法做到。
- 用户确认无代码 → 降级纯文档模式：提示「将基于文档编写，准确性受限：无法发现文档与实现的不一致、无法定位潜在 bug、无法核实风险点是否有下游消费」，跳过「代码探索与全面审查」与附录 Cx/Dn 产出。
代码模式与文档模式的差异贯穿后续所有阶段，每个阶段都会标注。
阶段一：输入研读 + 范围界定（代码优先）
从输入源中提取所有可测试点，同时识别平台、角色和测试边界。代码是静态事实的最高来源（裁决规则见 ../core/evidence.md）——有代码时以实现为准（测准声明），文档降为对照。
输入源与关注重点
| 输入源 | 重点关注 |
|---|---|
| 代码仓库（最高优先级） | 实际实现逻辑、数据结构、错误处理、与文档偏差、潜在 bug、改动范围（diff） |
| 需求文档/PRD | 功能点列表、边界说明、用户角色、业务规则 |
| 技术设计方案 | 数据模型、接口签名、状态流转、缓存策略、消息格式 |
| API 文档 | 接口参数、必填/选填、返回值、错误码、鉴权方式 |
| Bug 报告 | 复现步骤、根因分析、修复范围（回归用例） |
| FAQ/会议纪要 | 隐含需求、设计决策、边界限制 |
关键提醒：FAQ 中的每个问答都是潜在的边界用例；"非目标"声明中的限制需要对应的验证用例。
已有上游产物时直接消费：存在 需求模型.md（requirement-analysis 产出）则以其为结构化输入，澄清记录直接引用，不再重复建模；存在 测试策略.md（test-strategy 产出）则按其范围/深度/优先级要求执行，Risk Map 中的风险编号（R1、R2…）作为 risk_ref 挂到对应用例。存在 type_scope（类型域决策）时按 ../core/test-type-matrix.md 第 12 节消费方式映射执行：用例型轴（业务安全/可靠/并发/兼容，standard 及以上）产对应类型用例——type 用 security / reliability / concurrency / compatibility，名称行加 [并发] 等标签（i18n/迁移/契约轴用 type: functional + 标签）；脚本型轴（性能/视觉，standard 及以上；无障碍任意档位产 axe 扫描任务与违规清单）不产手动用例，导读区标注"执行物走专项脚本"并留给执行策略裁决；审查型（light 档）发现并入附录 Cx 审查清单；exclude 轴不产出。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago Changed · -10 tokens per session dcf732b33d26
- 6d ago Changed c9f9c4f3e5fd
- 10d ago First seen · 230 lines · 109 tokens per session scan A 3b9307cc1a70
test-case-writing is a skill published in the GitHub repository fishzjp/qa-skills (27 stars, last pushed yesterday), licensed MIT. It adds 99 tokens to every session and 6,705 once invoked, about $0.0005 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
qa-expert
Expert-level quality assurance, testing strategies, automation, and QA processes. Use when the user mentions testing, test automation, quality assurance, or Selenium, or when the task involves Testing Types, QA Processes, Test Strategy, or Defect Management.
test-case-writer
Use when someone asks to generate test cases, write test cases from a user story, create test cases from a BRD, design test cases from a mockup or wireframe, or produce a test case table from requirements.
test-review
A review checklist for newly written or changed automated tests using TypeScript and Playwright. Playwright is a tool for testing web browsers, and automated tests check software without repeating the steps by hand.
playwright-expert
Expert in Playwright E2E testing framework, auto-waiting mechanisms, test generation, trace viewer, and CI/CD integration. Use when the user mentions testing, end-to-end tests, QA, automation, end-to-end testing, or test automation, or when the task involves Playwright Framework, Test Organization, Advanced Features…
selenium-expert
Expert in Selenium WebDriver, Selenium Grid, page object model, waits, cross-browser testing, and test automation frameworks. Use when the user mentions testing, end-to-end tests, QA, automation, WebDriver, or Selenium grid, or when the task involves Selenium Components, Browser Support, Advanced Features, or Basic…
testing
A thorough testing framework for websites, user interfaces, back-end services, APIs, and builds. It checks normal use, errors, limits, and unusual combinations, and records evidence for each result.