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 ryanzhao1011/workframe --skill test-case-designgit clone --depth 1 https://github.com/ryanzhao1011/workframeWrote 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/ryanzhao1011/workframe/test-case-design)<a href="https://agentmods.dev/skills/ryanzhao1011/workframe/test-case-design"><img src="https://agentmods.dev/badge/skills/ryanzhao1011/workframe/test-case-design/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/ryanzhao1011/workframe/test-case-design"><img src="https://agentmods.dev/badge/skills/ryanzhao1011/workframe/test-case-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00223 | $0.04686 |
| Opus 5.5 | $0.00089 | $0.01874 |
| Sonnet 5.5 | $0.00045 | $0.00937 |
| Haiku 4.5 | $0.00022 | $0.00469 |
Grade A, and why
test-case-design 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 24d 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
测试用例设计与验证技能
前置依赖
调用本 skill 前需读 skill: document-norms §1（文档归属矩阵）/ §2（frontmatter 字段标准，特别是 type=test-case + §2.6 req_slug+sub_req_slug 引用契约）。modules/ 体系下用例落盘到 projects/modules/<basic>/<sub>/requirements/<req_slug>/<sub_req_slug>/test-cases/，YAML 顶层字段 type: test-case + module: <basic>/<sub> + req_slug: <req_slug> + sub_req_slug: <sub_req_slug> 必填（version 字段已废除）。
适用场景
- @qa 收到
pending_qa状态的任务时 - 代码变更后需要做功能验证时
- 回归验证时
六步流程
第 0 步：选型（这次测什么类型、多深、多广、要不要隔离）
怎么用这一步：下面三问全部问完，命中哪档取哪档，多个命中取最高。答「是」或「说不准」都算命中。
- 错了会不会传出这个文件之外？ → 命中 = 至少档 2
- 有没有东西会因为你改的那部分内容产出可比较的结果（通过/不通过、分数、diff、快照）？ → 命中 = 至少档 3
- 改的对象本身的职责就是「判断别的东西对不对」吗？ → 命中 = 档 4
三问全不命中 → 档 1。三问要全问完，不是答否就停——档 4 与前三档不构成阶梯：一份 PRD 完整性自查清单，第 1 问答否（错误止于本文），却是不折不扣的档 4。升一档最多多花半天；降一档漏掉的那次，没有人会告诉你。
| 档 | 什么情况 | 类型 | 深度 | 广度 | 隔离 |
|---|---|---|---|---|---|
| 1 | 纯内容改动，错误止于本文 | 主路径读一遍 + 一致性核对 | 只验「写的和实际一致」 | 改动点本身 | 不需要 |
| 2 | 错误会传到别的文件或别的人，但没有东西会因此产出结果 | + 引用面核对 | + 空 / 缺失 / 异常格式 | + 同族边界三问 | 不需要，但改前先提交 |
| 3 | 有消费方会因你改的内容产出可比较的结果 | + 跑真实消费方并排对照 | + 边界矩阵；证据拿不到时如实标注强度 | + 相邻分支 | 要写进被验对象时用副本 |
| 4 | 被改的东西自己的职责就是判断别的东西对不对（测试、校验、断言、自查清单、评分标准；不论靠机器还是靠人执行） | + 用它自己的失败方式打一遍 | + 先跑基线确认是绿的 + 结论的反面要能被打出来 | + 同契约的其他实现 | 必须副本 |
升档是累加不是替换——档 3 要做的包含档 2 的全部动作。档位是爆炸半径，不是用心程度：判在档 1 就按档 1 交付，多做的部分不算加分，只是把本该留给档 3/4 的力气花在了不需要的地方。
第 2 问怎么答（判错最多的一处，三条都要过）：
- 判存不存在，不判你现在跑不跑得动——跑不动（要 CI / 要凭证 / 要真机）是证据问题，按证据强度如实写进「不含」，不是降档理由
- 判它对你改的那部分敏不敏感——某道闸只读 frontmatter 而你改的是正文措辞，它对本次改动不敏感，不因它升档；否则在任何带 lint 的仓里每个文件都是档 3，档 1 与档 2 被抽空
- 不看对象是不是代码：一份配置有脚本读它并报错 → 档 3；一份文档的措辞被另一份文档引用、没有东西会因此产出结果 → 档 2。按对象类型分会把这两个判反
档 4 为什么单列：前三档改错了会炸，有信号；档 4 改错了静默不报——写完但从没真正执行过的检查，和通过长得一模一样。写 PRD 完整性自查清单、写输出质量的评分标准，同样落这一档。
同族边界三问（广度的判据）：这个事实在别处还有几份副本？这个约定还有几个使用方？这次改动周边还有哪些同类条目没碰到？
与 skill:
systematic-debugging第 3 步影响面五维互补不重合——五维按技术维度切（代码依赖 / 数据 / 接口 / 性能 / 安全）、只适用于修 bug、产出的是影响清单；三问按「同一事实的多处存在」切，产出的是测试范围。修 bug 时两组都要过。
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.
- 24d ago Changed · +51 lines · +159 tokens per session cca21ac0aa09
- 1mo ago First seen · 184 lines · 64 tokens per session scan A caaaadb26f8c
test-case-design is a skill published in the GitHub repository ryanzhao1011/workframe (7 stars, last pushed 26d ago), licensed MIT. It adds 223 tokens to every session and 4,686 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
feature-acceptance
A browser-based acceptance testing process that compares an online implementation with a product requirements document and, when available, an HTML prototype. It records what is complete, partial, missing, or inconsistent, with screenshots and prioritized blockers.
ci-tests
Run the test suite for the current repo, auto-detecting Python (pytest/uv), Node (vitest/pnpm), or Rust (cargo test).
browser-qa
Use to exercise the running app in a real browser — after UI changes, before ship, or when the user asks to QA the site, smoke-test a branch, or check "does it actually work". Drives affected routes headlessly via Playwright, captures console errors, failed requests, and screenshots, and produces a report with a…
tdd
Use when building any T3 feature or bugfix, recommended for T2 on the affected path — write the failing test before the implementation, one behavior at a time, through public interfaces.
testing-dotnet
.NET testing patterns — xUnit conventions, integration tests with WebApplicationFactory over Testcontainers, NSubstitute mocking, and test organization.
rehearsal
Test a deliverable on a zero-context reader before it ships. Use before shipping any document, guide, kit, or handoff meant to work without you, and before calling a deliverable done in goal Phase 5.