Retro logo

Retro

CommunityPopular
vinvcn
retro

对一次 coding session 做 retrospective。

Overview

Publishervinvcn
Repositorymattpocock-skills-zh-CN
Skill nameretro
Stars
4.5K
Forks
368
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by vinvcn on GitHub. Read the source before you install it.

Installation

Install the Retro AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/vinvcn/mattpocock-skills-zh-CN/tree/main/skills/in-progress/retro
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/vinvcn/mattpocock-skills-zh-CN.git /tmp/mattpocock-skills-zh-CN
mkdir -p .claude/skills
cp -r /tmp/mattpocock-skills-zh-CN/skills/in-progress/retro .claude/skills/retro
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Retro in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Retro on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Retro is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

用户要求做一次 retrospective。你要针对 coding agent 的 environment 提出改进建议,以改善未来的运行结果。

Steps

  1. 调用 Skill 工具并指定 writing-for-agents,获取写作风格指南。

  2. 阅读用户指定 session 的 primary sources。这可能意味着在本机搜索 session logs。如果用户没有指定 session,默认使用当前 session。

  3. 在以下类别中寻找改进候选项。

  • Navigation:agent 找到正确 files 有多容易?files 之间是否存在隐藏依赖?navigation pointer 能否让定位更容易?当 agent 花了很长时间才找到某段信息时使用。
  • Automated checks:是否有 automated checks 可以捕获 agent 犯的错误?例如 linting、typing、tests 或 filesystem linters?先阅读 repo 自己的检查命令(package.json/build-tool 中的 lint/check scripts 以及 CI workflow),这样,如果某个检查已经存在但没有接入流程或悄悄失效,真正的发现就是这个问题,而不是重新发明一套检查。若 repo 完全没有 guardrail(没有 pre-commit hook,也没有运行 lint/typecheck/test command 的 CI job),这本身就是一项发现:未纳入 lint 的 repo 是长期存在的改进缺口,而不是理所当然的默认状态。当 agent 犯了本来可以被 automated check 捕获的错误,或 repo 完全没有 guardrail 时使用。
  • Coding standards:是否应该给 reviewer agent 一条新规则来执行?是否应该删除或澄清现有规则?先对违规分类:mechanical 违规(固定的语法模式、被禁用的 API、import 形式、文件位置规则)必须交给 deterministic check 处理——根据 repo 使用的语言和现有 guardrail,选择成本最低的方式:在 repo 自己的 linter 中添加自定义规则、新增 pre-commit hook,或新增 CI job。默认优先构建检查,而不是编写规则。CODING_STANDARDS.md 只用于真正的 judgement calls(跨文件一致性、"matches the surrounding style",以及任何 guardrail 都无法替代的判断)。当 reviewer agent 没有发现一个错误时使用。
  • Global AGENTS.md:是否有 steering instructions 应该移到 coding standards 或 automated checks?当 repo 或用户 global scope 中的 AGENTS.md 特别庞大时使用。
  • Tool economy:agent 是否进行了可以简化的昂贵 tool calls?是否有特别消耗 tokens 的自定义 tooling(CLI、MCP 等)?当 agent 进行昂贵 tool call 时使用。
  • No-ops:steering files 中是否有不改变 agent 行为的 instructions?当 steering files 庞大且难以维护时使用。
  • Information access:是否有机会让 agent 获得更多信息?例如把 dev server logs tee 出来,或提供对 third-party services 的 read-only access。当关键的信息对 agent 不可用时使用。
  1. 按严重程度顺序向用户呈现这些候选项。

Reference

Implementation vs Review

记住,所有工作都经过两个阶段:implementation 和 review。implementation agent 承受最大的 context pressure,负责探索、编写代码和调试失败。

review agent 承受最小的 context pressure——它收到的是 diff,因此不需要探索。它通常也不需要编写代码或调试。

因此,review agent 应负责施加 coding standards,而不是 implementation agent。

Files

你可以访问 repo 中的几个 files:

  • CLAUDE.md/AGENTS.md:这些 files 会被推入在此 repo 工作的任何 agent 的 context window。应当极其节制地使用,通常只放指向其他 files 的 navigation pointers。
  • CODING_STANDARDS.md:这个 file 在 review 时读取,而不是 implementation 时读取。如果 standards file 超过 1,000 行,应当在其中加入指向 docs folders 的 navigation pointers。
  • Docs:把 docs 当作 reference files,由其他 files 通过 pointers 指向。写新 docs 前先查找已有 docs。
  • Skills:用 skills 承载 docs(因为它们的 description 会进入 agent 的 context window),或用于 user-invoked commands。遵循 writing-for-agents skill 中的建议。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Retro AI skill do?

对一次 coding session 做 retrospective。

Why use Retro on TypingMind?

Because you install it once and use it with any model. Retro is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Retro in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vinvcn/mattpocock-skills-zh-CN/tree/main/skills/in-progress/retro. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Retro?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Retro?

As many as you like. As long as a model supports skills, you can use Retro with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Retro AI skill free?

Yes. It is published on GitHub by vinvcn under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇