skillify SKILL.md skillA
skillify from riot-org/riot is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add riot-org/riot/skillify@git:20261014.9c3854aPins git:20261014.9c3854a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- riot-org/riot
- Path
crates/riot-kernel/builtin/skills/skillify/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261014.9c3854a, committed Oct 14, 2026
- First version recorded
- Aug 17, 2026
- Size
- 2,697 bytes
- Repository stars
- 22
- License
- a license file GitHub does not identify
用户说「做成技能」「以后都这么做」，或一套流程试错多次才跑通、下次还会用时。把步骤、完成判据和用户纠正过的点提炼成 SKILL.md，和用户确认后再写。.
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
# 沉淀成技能 ## 什么值得沉淀 判据：**下次还会做，而且模型光靠常识做不对。** - 这次会话里用户纠正过你的地方——每处纠正都是一条「模型的默认做法 在这里不对」的证据，是技能正文里最值钱的原料； - 试错试出来的顺序、参数、坑（哪个命令要先跑、哪个 flag 不能省、 哪一步必须等前一步的产物）； - 用户没有明说、但反复要求的偏好。 反例：模型本来就会的通用流程（「先读文件再改」）写成技能只是噪音， 还占技能清单的位置。 ## 提炼 从会话里回答这几个问题；答不出来的用提问工具问用户，一次问完， 不要挤牙膏： 1. **触发场景**是什么？这句话就是 description——模型全靠它决定 要不要加载这个技能，写不准等于技能不存在。 2. 步骤有哪几步？每步的**完成判据**是什么（产出什么、怎么算成了）？ 3. 哪些是硬约束？顺序不能换的、某些文件不能碰的、必须先问用户的。 4. 放哪层：只跟这个项目有关 → 项目 `.riot/skills/`；跨项目通用 → 全局技能目录。 ## 写 - description 写「什么时候用」，不写做法，250 字符以内——超了会被 截断，模型只能在残句上做判断； - 正文只写**模型猜不到的**：判据、顺序、坑、约束。每句话问一遍 「删掉它，模型会做错吗」——不会就删； - 用户纠正过的点写成明确的「不要做 X，因为 Y」，别客气也别含糊； - **自由度跟着任务的脆弱程度走**：多解的任务写原则和判据就够 （审查指南），怕做错的操作写精确的命令和顺序（迁移、发布）。 给脆弱步骤留发挥空间，等于留 bug； - 别列一堆可选方案让模型现场挑。给**一个默认做法**，再写清什么 情况下换另一个； - 大段参考资料（表格、样例、脚本）放技能目录里的独立文件，正文 说明什么时候去读哪个。正文塞满资料，每次加载都是全价，用不用 都付； - 目录位置、frontmatter 字段、同名优先级这些机制，照 extend-riot 技能的说明来，不要凭记忆写。 ## 写完 把文件路径和 description 给用户过目，说明**下一轮对话生效**。 提醒一句：设置页能看到技能的解析结果，写坏了那里会显示原因。
Read the whole file at its exact version.
How to install
mdr add riot-org/riot/skillify@sha256:c8fede3f1e017464The line at the top of this page pins the label git:20261014.9c3854a, 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_o44n4hl6hkv5xjyb)
6 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Aug 17, 2026 and Oct 14, 2026, about one every 58 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261014.9c3854a latest | 2026-10-14 | 9c3854a | 2,697 B | A | view · diff |
| git:20260817.d4dfa41 | 2026-08-17 | d4dfa41 | 2,695 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 (2697 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
riot-org/riot · 22 stars · license a license file GitHub does not identify · pushed 2026-10-29 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_o44n4hl6hkv5xjyb GET https://markdownregistry.com/api/v1/resolve?ref=riot-org/riot/skillify GET https://markdownregistry.com/api/v1/blob/c8fede3f1e0174645d52de1a2ec546a42d08e1285bc128ec64446916f0c0466a
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.