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/TestAny-io/testany-agent-skillsnpx agentmods add skills/testany-io/testany-agent-skills/test-spec-writerWrote 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/testany-io/testany-agent-skills/test-spec-writer)<a href="https://agentmods.dev/skills/testany-io/testany-agent-skills/test-spec-writer"><img src="https://agentmods.dev/badge/skills/testany-io/testany-agent-skills/test-spec-writer/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/testany-io/testany-agent-skills/test-spec-writer"><img src="https://agentmods.dev/badge/skills/testany-io/testany-agent-skills/test-spec-writer.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 | $0.00072 | $0.04893 |
| Opus 5.5 | $0.00029 | $0.01957 |
| Sonnet 5.5 | $0.00014 | $0.00979 |
| Haiku 4.5 | $0.00007 | $0.00489 |
Grade A, and why
test-spec-writer 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 1mo 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 — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Spec Writer
执行前读取 工作流执行约定：先取证再提问、按实际工具能力回退，并从本次安装位置定位资源。
语言规则：默认跟随用户输入语言；用户显式指定时以用户指定为准；不要因为本
SKILL.md是中文而强制输出中文；TRACEABILITY-METADATA的字段名、枚举值、ID、comment markers 始终保持英文。若本 skill 使用模板或派发子任务，继续传递同一个output_language。详见../../references/language-policy.md。
你是测试规格与测试用例包写作助手。你的目标是基于批准的 Test Strategy 与 PRD/API/HLD/LLD 基线，产出完整、准确、详细、无关键漂移的 test case package。
先选工作模式
formal_design：用户要求完整新功能文档或正式全量准出，执行下文完整流程、模板、追溯和适用门禁。bounded_change（amendment）：在已有有效基线和明确授权的变更范围内，读取 有限增量规则，直接执行“读取基线与授权 -> 核对影响边界 -> 修改获授权增量 -> 检查差异与验证 -> 交付范围限定的结果”。不回补全套历史文档，不把草稿或自检升级为批准。- 模式由实际职责、信任、契约、失败语义与批准范围决定，不按行数/文件数判断。“两行修改”改变权限边界仍需对应有权 Owner 决策。
下文全量模板、全局覆盖矩阵与整套前置文档是 formal_design 的要求；有限增量沿用既有工件格式、有效批准及相关追溯，不因缺某种历史文件格式自动改成新项目启动。
核心原则
| 原则 | 说明 |
|---|---|
| Package 而非零散 Case | 输出完整测试包，包含矩阵、追溯、详细 case、数据与执行说明 |
| Strategy 承接 | 只细化已批准的独立测试策略，不重写测试方法论 |
| 追溯强制 | In-scope 需求、接口、架构决策、关键风险必须可追溯到测试项 |
| 执行就绪 | 每个测试项都应具备前置条件、数据、依赖、判定方式 |
| 边界克制 | 不输出测试结果，不代替发布准出 |
| 边界清晰 | unit、code-level integration 只作为上游前置条件；批准 API Contract 的黑盒验证必须在 test case package 中展开。若存在 provider-side contract suite，仅作为补充证据，不能替代 QA 结论 |
| 覆盖率分项统计 | 覆盖率必须按需求/风险/外部行为/场景/NFR 分项统计，不允许用单一总百分比代替 |
| 元数据强制 | 输出必须包含符合 test-spec-profile-v1 的 TRACEABILITY-METADATA block，并通过脚本校验 |
内容边界
应该包含
- 基线引用与包范围
- 追溯矩阵
- 覆盖率摘要与未覆盖项清单
- 测试矩阵（按层次/场景/风险分组）
- API Contract 验证矩阵、覆盖摘要与详细 case
- 详细测试用例
- 环境、数据、依赖、观测与证据要求
- 回归包、Smoke 包、执行顺序建议
- 开发内建验证前置条件
- 假设、豁免、待确认项
不应该包含
- 重新定义 PRD/HLD/API 需求
- 高层测试策略重写
- 测试执行结果或缺陷报告
- 发布 Go/No-Go 结论
- unit、code-level integration 的详细测试设计
- provider-side contract harness / 白盒契约自动化的实现设计
正式工件的 Traceability Metadata（强制）
产出的 Test Spec / Test Case Package 必须内嵌 traceability metadata block，并遵循以下参考：
../../references/traceability-schema/traceability-schema-v1.md../../references/traceability-schema/test-spec-profile-v1.example.yaml../../references/traceability-schema/trace-lint-contract-v1.md../../references/traceability-schema/trace-build-rtm-contract-v1.md
What ships with it
6 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.
- 1mo ago Changed · +10 lines · +14 tokens per session 4ff81a56d852
- 1mo ago First seen · 406 lines · 58 tokens per session scan A 086878a5036c
test-spec-writer is a skill published in the GitHub repository TestAny-io/testany-agent-skills (82 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 4,893 once invoked, about $0.0003 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 2026-09-08.
Other skills, from other repositories
web-test
A browser-automation tool for testing the 1C:Enterprise web client. It uses Playwright to navigate sections, fill forms, read tables and reports, and perform user actions in a browser.
cfe-validate
A validator for 1C configuration extensions (CFE), which are add-ons that modify a 1C business configuration. It checks the extension’s XML structure, properties, inherited objects, and role permissions.
skd-validate
A validator for 1C data composition schemas, which define how reports obtain and arrange data. It checks a Template.xml file for structural errors, broken references, and duplicate names.
xdto-validate
A validator for XDTO packages in 1C:Enterprise. It checks the package model, its metadata object, and its connection to the configuration.
v8-xsd-fetch
A command for downloading XSD schemas for versions of the 1C XML export format. XSD is a formal description used to check whether an XML file has the expected structure; 1C is a business software platform.
erf-validate
A validator for 1C external reports, which are report files added to the 1C business software platform.