retro SKILL.md skillA
retro 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/retro@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/retro/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261014.9c3854a, committed Oct 14, 2026
- First version recorded
- Aug 20, 2026
- Size
- 3,088 bytes
- Repository stars
- 22
- License
- a license file GitHub does not identify
任务磕磕碰碰才做成、被纠正了好几次之后用；用户说「复盘」「总结经验」「记下来」时也用。回顾这次会话的纠错轨迹，筛出下次还会犯的错，沉淀进 AGENTS.md 或技能，同类任务下次不用再教一遍。.
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
# 复盘并沉淀经验 这次对话结束后你什么都不会记得。刚才的纠正、试错、最终跑通的路径， 不现在写下来，下次同类任务用户还得从头再教一遍。 用户指定了复盘重点的话优先照它来：$ARGUMENTS ## 1. 回顾轨迹 从对话开头到现在过一遍，列出： - 用户纠正过你几次，每次纠正的是什么——你当时的（错误）假设 vs 实际； - 失败过的工具调用和命令：症状（报错原文）→ 真因； - 最终跑通的路径，和你最初的计划差在哪几步。 ## 2. 筛选 同时满足三条的才值得记： - **反直觉**：下次靠推理和读代码还是会犯同样的错； - **grep 不到**：代码和文档里查得到的不记——那是下次自己找得到的东西； - **是规律不是偶然**：只见过一次的现象，把适用条件写清楚再记。 一条都筛不出来就直接说「这次没有值得沉淀的经验」，到此为止。硬写出来 的空话不是零收益，是负的——它占清单位置，稀释真正有用的经验。 ## 3. 决定去向 **默认进项目级。** 编码任务里摸出来的经验十有八九是这个仓库的规律—— 这里的构建顺序、这里的报错、这里的约定。放错方向的代价不对称：该全局 的放成项目级，大不了换个项目再沉淀一遍；该项目级的放成全局，是让所有 项目付上下文税，还可能在别处是错的。 - **一句话纪律** → `<项目>/AGENTS.md`。保持短：那个文件每一行都在对 所有会话收上下文税。 - **某一类任务的完整打法** → 项目 `.riot/skills/`。**先看已有技能的 清单**：这次的坑落在某个已有技能的范围内，就更新它，不要另开一份 近似的——两份互相抢，哪份都不完整。 - **只对这一次有效的细节** → 不记。 例外才进全局（配置目录那层）：跟仓库代码无关、跟用户本人或用户的机器 有关的——工作习惯、环境坑（「Dock 起的应用继承不到 shell 环境变量」 属于这类）。拿不准就项目级；要写全局，先问用户一声。 ## 4. 写 - 写新技能：加载 skillify 技能，照它的写法来。要点是 description 写 「什么时候用」——那是模型下次想起它的唯一线索；正文只写模型猜不到 的。目录和 frontmatter 的机制细节见 extend-riot 技能。 - 更新已有技能或 AGENTS.md：新坑写成「症状 → 真因」，报错原文照抄 进去——下次撞到症状才对得上号。 ## 5. 收尾 报给用户：改了/新建了哪个文件，每条经验一句话。值不值得留由用户把 关——经验库是用户的，不是你的。改动下一轮对话生效。
Read the whole file at its exact version.
How to install
mdr add riot-org/riot/retro@sha256:e7aebb814783f372The 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_vufuyu4slj5tnfxx)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Aug 20, 2026 and Oct 14, 2026, about one every 55 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261014.9c3854a latest | 2026-10-14 | 9c3854a | 3,088 B | A | view · diff |
| git:20260820.16d82f8 | 2026-08-20 | 16d82f8 | 3,082 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 (3088 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_vufuyu4slj5tnfxx GET https://markdownregistry.com/api/v1/resolve?ref=riot-org/riot/retro GET https://markdownregistry.com/api/v1/blob/e7aebb814783f37240c5f7340d6dc7c0ed3659c045bac48488dea4026772bab0
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.