test SKILL.md skillA
test from ylxmf2005/longrein is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ylxmf2005/longrein/test@git:20260923.8eb4b09Pins git:20260923.8eb4b09 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ylxmf2005/longrein
- Path
skills/test/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260923.8eb4b09, committed Sep 23, 2026
- First version recorded
- Jul 23, 2026
- Size
- 3,594 bytes
- Repository stars
- 11
- License
- none declared
用户要求测试、E2E、回归、复现缺陷，或要判断一个功能、修复、迁移能不能交付时使用。先写测试计划，再从真实入口走到结果真正生效的地方执行，最后按计划逐项报告。写代码过程中跑一下单测、编译这类顺手检查不用；判断代码写得好不好用 review。.
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
# test 测试是想办法证明它是错的，而不是替实现找通过的理由。一路测到结果真正生效、或被真实使用方看到的地方：请求成功、命令退出 0、页面提示完成、单测变绿，都只证明它们自己那一层。 ## 先写计划 计划从这些来源长出来：`.agents/tasks/<任务>/shape.md` 的目标和验收标准（如果有）、原始缺陷、实际 diff、公共接口，以及受影响的调用方和消费者。不从通用检查清单长出来。 先写清被测的对象和环境：哪个版本或构建、哪个环境、用什么身份和数据、在哪里观察结果。每个关键场景一个用例，写到另一个人不用现场补细节就能执行： - 为什么测，失败会影响谁； - 具体的输入、请求或操作步骤； - 期望的结果，以及系统最终应处于什么状态； - 在哪里、用什么确认这个最终状态； - 测试会改动哪些数据，怎样清理。 执行前反过来检查计划：如果产品其实是错的，这些用例有没有可能全部通过？常见的漏洞是只验证了操作被触发、没验证最终状态，或者漏了旧的调用方、权限、异步消费者和失败恢复路径。 非平凡的测试先把计划给用户看一眼，然后开始执行；执行中发现计划没覆盖的风险，补进计划，已有用例不删。 ## 执行 先确认实际测到的是预期的版本、进程、数据和环境。按承诺对应的入口来测：承诺的是界面行为，就亲自走界面；API、数据库、日志和下游系统用来确认最终状态，不能代替界面上的操作。 每个用例先记下实际做了什么、看到了什么，再给结论。失败和重跑都保留，不用后来的通过覆盖先前的失败，也不根据计划或记忆补写没发生过的步骤。发现产品问题时先留下可以复现的证据；只有用户要求或授权了修复才去修，修完按受影响范围重测。某个条件不满足时，只暂停依赖它的用例，其余继续。测试中创建的数据、进程和配置，清理后确认已经清掉，保留的写明。 ## 报告 计划里的每个用例在报告中都有且只有一个结果： - **通过**：直接证据支持全部预期； - **失败**：实际行为和预期不符； - **未完成**：没能完整执行或确认，写明原因，例如环境不可用、被其他失败挡住、主动跳过或缺少最终状态的证据。 总体结论只看关键用例的证据，不看通过率：给出能不能交付，列出失败项、未完成项和因此还不能证明的范围，以及测试留下的数据或进程。 ## 保存 简单改动、一个检查就能完整证明的，直接在对话里报告测了什么、结果如何、还有什么没证明。需要计划的测试写到 `.agents/tasks/<任务>/test.md`，先写"计划"一节，执行后在同一文件补"报告"一节；截图、日志、请求和响应等原始材料放在同目录的 `evidence/` 下，正文说明它们证明了什么。 一次性的测试脚本属于这次测试的证据；要把自动化测试长期加进产品代码，属于实现工作，按当前授权处理。
Read the whole file at its exact version.
How to install
mdr add ylxmf2005/longrein/test@sha256:63bf8d648f4e1980The line at the top of this page pins the label git:20260923.8eb4b09, 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_oscnweivle5rsmfg)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 23, 2026 and Sep 23, 2026, about one every 16 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260923.8eb4b09 latest | 2026-09-23 | 8eb4b09 | 3,594 B | A | view · diff |
| git:20260910.4546a3c | 2026-09-10 | 4546a3c | 4,564 B | A | view · diff |
| git:20260727.9ce3b8d | 2026-07-27 | 9ce3b8d | 4,512 B | A | view · diff |
| git:20260725.cfce686 | 2026-07-25 | cfce686 | 2,977 B | A | view · diff |
| git:20260723.62f007f | 2026-07-23 | 62f007f | 3,408 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 (3594 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
ylxmf2005/longrein · 11 stars · license none declared · pushed 2026-10-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_oscnweivle5rsmfg GET https://markdownregistry.com/api/v1/resolve?ref=ylxmf2005/longrein/test GET https://markdownregistry.com/api/v1/blob/63bf8d648f4e19802c29d44011d7527df3ba88d7b5764927487e8eceeecf24cd
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.
More from ylxmf2005/longrein
Every file in ylxmf2005/longrein