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 flanliulf/SpecLite --skill speclite-qa-write-test-guidegit clone --depth 1 https://github.com/flanliulf/SpecLiteWrote 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/flanliulf/speclite/speclite-qa-write-test-guide)<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-qa-write-test-guide"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-qa-write-test-guide/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/flanliulf/speclite/speclite-qa-write-test-guide"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-qa-write-test-guide.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 | $0.00120 | $0.01082 |
| Opus 5 | $0.00060 | $0.00541 |
| Sonnet 5 | $0.00024 | $0.00216 |
| Haiku 4.5 | $0.00012 | $0.00108 |
Grade A, and why
speclite-qa-write-test-guide 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 8d 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.
What it actually says
[Overview(技能说明)] 将 PRD、TSD、Story、实现文档、代码事实或对话结论转成面向测试人员的可执行测试指南。核心原则是:不写开发设计文档,而是让测试人员清楚知道怎么构造数据、怎么触发、看哪里、什么算对、什么算错。
[Core Capabilities(核心能力)]
- 测试心智模型提炼:把复杂链路压缩成测试人员需要理解的业务规则、状态语义和误判边界。
- 测试数据构造指导:明确字段、fixture、边界值、异常输入和最小数据组合。
- 触发与证据链设计:把接口、Job、配置、DB、report、trace、日志和外部系统响应串成可复核执行路径。
- 场景矩阵生成:为每个场景输出 Purpose、Data Setup、Trigger、Expected Result、Must Not Happen 和 Evidence。
- 严谨性审核:检查 accepted/finished 混淆、模糊词、缺少反向断言、证据不可定位和规格臆测。
- 可读性控制:使用测试人员视角行文,避免类名堆叠、架构复述和无法执行的泛化描述。
[Workflow(执行流程)]
本 Skill 采用事实盘点 -> 测试心智模型 -> 指南初稿 -> 严谨性审核 -> 定稿交付的迭代优化工作流。详细步骤、审核规则和输出模板见 references/speclite-qa-write-test-guide-workflow.md。
Step 1:盘点事实来源
读取用户指定文档、当前规格、代码事实或对话结论。区分当前事实、历史参考和未确认事项;缺少关键业务口径时停止并要求澄清。
Step 2:建立测试心智模型
先写测试人员必须理解的一句话规则,再列核心误判边界。例如 accepted 不等于 finished、dry-run 不等于真实写、API failure 不得写 success mapping。
Step 3:生成测试指南
以 `assets/test-guide-template.md` 为结构参考,输出测试数据构造、触发方式、证据清单、场景矩阵、通过/失败标准和排查路径。
Step 4:审核并定点修正
按 workflow reference 中的 review checklist 检查每个场景是否具备正向预期、反向断言和证据位置;修掉模糊词和开发视角表达。
Step 5:交付
输出文档路径、场景数量、关键覆盖点、审核结论和剩余未确认项。若写入运行产物,在文档末尾追加生成标注。
[Notes(注意事项)]
- 先回答测试人员的五个问题:造什么数据、怎么触发、去哪看、看到什么算对、看到什么必须报错。
- 不把接口 accepted 写成业务 finished;不把开发类名、模块层级或实现调用链当成测试执行路径。
- 每个关键规则必须同时写正向判定和反向判定,反向判定使用 Must Not Happen 表达。
- 证据必须可定位到字段、表、接口响应、trace/report、日志或外部系统响应;避免“正常”“合理”“及时”等不可执行词。
- 未确认的第三方字段、枚举、接口返回或环境配置不得猜测;标为 open question 或要求用户确认。
- 文档内容默认中文,章节标题使用 English(中文)形式;命令、路径、字段名、fixture 名称、schema/issue id 等技术标识使用英文。
[Generation Metadata(生成信息)]
本 Skill 由 speclite-skill-creator 自动生成。如需修改,必须同步更新 SKILL.md 与 SKILL.en.md,并同步维护 CHANGELOG.md、references/ 和 assets/。
What ships with it
4 files 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.
- 8d ago First seen · 50 lines · 120 tokens per session scan A 3ad0f683735a
speclite-qa-write-test-guide is a skill published in the GitHub repository flanliulf/SpecLite (4 stars, last pushed 2mo ago), licensed MIT. It adds 120 tokens to every session and 1,082 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
Backend Test Patterns
Guidance for covering the failure and edge paths of a backend change — bad input, concurrent writes, partial failure — not just the happy path.
Visual Verification Workflow
The procedure for actually confirming a UI change in a real or preview browser — golden path, an edge case, console errors, and responsive/dark-mode checks — before calling it done.
Test Patterns
What "well-tested" actually means — covering edge cases and failure modes deliberately, not just confirming the happy path runs once.
Regression Discipline
The rule that every bug fix ships with a test that fails on the old code and passes on the new — and how to write that test well.
Test Automation
Patterns for keeping the test suite fast, deterministic, and runnable in CI — mocking rules, isolation, and flakiness prevention.
Test Strategy
How to decide what to test at what level — the test pyramid, risk-based coverage, and matching test depth to change risk.