doctor SKILL.md skillA
doctor from pillumina/ascend-sleuth is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add pillumina/ascend-sleuth/doctor@git:20261027.748c4a1Pins git:20261027.748c4a1 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- pillumina/ascend-sleuth
- Path
skills/doctor/SKILL.md- Versions recorded
- 4
- Latest version
- git:20261027.748c4a1, committed Oct 27, 2026
- First version recorded
- Oct 20, 2026
- Size
- 4,434 bytes
- Repository stars
- 5
- License
- MIT
本机环境体检：一条命令问清这台机器上哪些流程能跑、哪些会降级（缺 Python 包、git、node、gh， traces/ 能否解析，知识库索引在不在），并给出每项缺失的修法。任务开始前环境可疑、换机器、 内网新部署、或流程中途以一句 import 报错退出时用。可反复执行：同一台机器两次跑结论一致。.
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
# Doctor（本机环境体检） 依赖缺了不在开单时报，而在任务中途以一句 traceback 出现。实测：缺 PyYAML 的机器上点「导出交接包」， 面板只回一句「导出脚本没有给出 JSON 结果」。根因在 traceback 的最后一行，读者要自己认。 全仓有一批脚本在 import 阶段就依赖 PyYAML，缺一个包会同时断掉几条流程。 本 skill 的动作一件：**跑体检器，然后按它给的顺序修一项、重跑一次**。 ## 何时触发 - 用户问「这台机器能不能用」「装了什么」「为什么报缺依赖」； - 流程中途出现 `ModuleNotFoundError`、`command not found`，或面板报「没有给出 JSON 结果」这类只有结果没有原因的错误； - 换机器、换解释器、内网新部署第一次用； - 修完一项要复验。 ## 只跑一条命令 ```bash python3 scripts/doctor.py # 人读三段：结论 / 证据 / 下一步 python3 scripts/doctor.py --json # 面板或脚本消费 ``` 退出码：`0` 无阻断、`2` 有阻断项、`3` 不在 ascend-sleuth 检出里、`4` 命令行参数写错。 不要自己另写探测命令。手敲 `python3 -c "import yaml"` 只验一个包，也漏掉解释器不一致这一层。 体检器扫的是 `scripts/` 下全部脚本的 import，新增第三方包会被它自动发现；能力表写错 id 时它会自报。 ## 怎么读输出 三段各回答一个问题。 | 段 | 回答 | 用法 | |---|---|---| | 结论 | 哪些流程能跑、降级、不能跑 | 第一屏转述这三行，不让用户自己读全表 | | 证据 | 每项缺什么、影响几个脚本、修法原值 | 修的时候照抄「修：」后面那条命令 | | 下一步 | 按影响面排序的修复动作 | 一次只做第一条 | 报告末尾那行「体检用的解释器」要带上。面板与终端可能不是同一个解释器：Windows 上按 `python3` → `python` → `py -3` 的顺序探活。把包装到另一个解释器上，体检结论不会变。 解释器低于 3.10 时，Python 那一行会标降级：标准库名单在那个版本不存在，依赖判定只能按路径推断， 可能多报。先升级解释器再判结论。 ## 修复循环 1. 读结论段，记下第一条阻断项。 2. 只修那一项，命令照抄证据段给的「修：」原值。 3. 重跑同一条命令。 4. 阻断项清零后，再处理降级项。 5. 结论与上一次不一致时先停。同一台机器两次跑出不同结果，说明环境在变（PATH、解释器、代理）， 先查这个再继续修。 ## 硬规则 …
Read the whole file at its exact version.
How to install
mdr add pillumina/ascend-sleuth/doctor@sha256:006b97673aee1cacThe line at the top of this page pins the label git:20261027.748c4a1, 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_lk3tjm4av5vzprbc)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Oct 20, 2026 and Oct 27, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261027.748c4a1 latest | 2026-10-27 | 748c4a1 | 4,434 B | A | view · diff |
| git:20261027.2dabd30 | 2026-10-27 | 2dabd30 | 4,419 B | A | view · diff |
| git:20261020.24501f3 | 2026-10-20 | 24501f3 | 4,113 B | A | view · diff |
| git:20261020.a6b5608 | 2026-10-20 | a6b5608 | 3,960 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 (4434 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
pillumina/ascend-sleuth · 5 stars · license MIT · pushed 2026-10-31 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_lk3tjm4av5vzprbc GET https://markdownregistry.com/api/v1/resolve?ref=pillumina/ascend-sleuth/doctor GET https://markdownregistry.com/api/v1/blob/006b97673aee1cacb7130c442b6b20cce78113d464b16433651af101050f33fc
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 pillumina/ascend-sleuth
Every file in pillumina/ascend-sleuth