Pretty Skills logo

Pretty Skills

Community
huangrichao2020
pretty-skills

跨 agent 统一管理你的所有 skill 和知识。 Use when 用户要"装 pretty-skills"、"管 skill"、"ps list/add/rm/update/graph/contribute/info/sync"、 查看 skill 依赖图、贡献新 skill、跨 Claude Code / Codex / Mavis / Cursor / Windsurf 同步 skill。 本地增删改无门槛,PR 是用户主动判断不是自动同步(边缘优先开源)。

Overview

Publisherhuangrichao2020
Repositorypretty-skills
Skill namepretty-skills
Stars
54
Forks
4
Bundled files
20
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.

  • 20 bundled files

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

  • Open source

    Published by huangrichao2020 on GitHub. Read the source before you install it.

Installation

Install the Pretty Skills 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/huangrichao2020/pretty-skills/tree/main/tools/pretty-skills
  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/huangrichao2020/pretty-skills.git /tmp/pretty-skills
mkdir -p .claude/skills
cp -r /tmp/pretty-skills/tools/pretty-skills .claude/skills/pretty-skills
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pretty Skills 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 Pretty Skills 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 Pretty Skills 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.

pretty-skills

让每个 agent 都能装、每个用户都能改、每个贡献都被看见。

一句话定位

pretty-skills = 跨 agent 的 skill 管理器。

它把你写的每一个 skill 装到 5 大 agent(Claude Code / Codex / Mavis / Cursor / Windsurf)的统一位置, 让你用同一个 ps 命令就能管所有 skill 的增删改、查依赖、提 PR。

快速开始

bash
# 一行安装(首次)
curl -fsSL https://raw.githubusercontent.com/huangrichao2020/pretty-skills/main/tools/pretty-skills/install.sh | bash

# 之后随时用
ps list                        # 看本地装的所有 skill
ps info pretty-skills-creator  # 看某个 skill 的详情
ps add serenity-stock-choke    # 从主项目装一个
ps graph                       # 输出 Mermaid 依赖图
ps contribute my-new-skill     # 把本地修改推回主项目(提 PR)

设计原则

原则怎么落地
本地优先~/.pretty-skills/store/ 是真实存储,5 agent 都软链到这
改无门槛直接 vim store 里的文件即可,不需要经过工具
PR 是用户主动判断工具绝不自动 push,需要 ps contribute 才走
跨 agent 统一一次装,5 个 agent 都能用
依赖关系透明ps graph 一眼看所有 skill 的依赖图
manifest 必填没有 manifest 的 skill 不会被装(防垃圾)

目录结构

~/.pretty-skills/
├── store/                  # 公共存储(真实文件在这)
│   ├── pretty-skills/
│   ├── pretty-skills-creator/
│   └── serenity-stock-choke/
└── config.yaml             # 哪些 agent 启用 / 哪些 skill 已禁

~/.claude/skills/pretty-skills -> ~/.pretty-skills/store/pretty-skills
~/.codex/skills/pretty-skills -> ~/.pretty-skills/store/pretty-skills
~/.mavis/skills/pretty-skills -> ~/.pretty-skills/store/pretty-skills
~/.cursor/skills/pretty-skills -> ~/.pretty-skills/store/pretty-skills
~/.windsurf/skills/pretty-skills -> ~/.pretty-skills/store/pretty-skills

8 个子命令

命令作用
ps list列出本地已装的所有 skill(按 agent 分组)
ps info <name>显示 manifest、依赖、占用空间、最后修改时间
ps add <name>从主项目装一个 skill(默认源:github.com/huangrichao2020/pretty-skills/tree/main/tools)
ps rm <name>卸载(删 store + 软链)
ps update <name>拉主项目最新覆盖本地(保留本地未 commit 的修改会先备份)
ps graph扫描所有 skill 的 manifest.dependencies,输出 Mermaid 依赖图
ps contribute <name>把本地修改推回主项目(自动开 fork + 提 PR,附 changelog)
ps sync批量 update(等价于对所有 skill 跑 ps update)

与 pretty-skills-creator 的关系

  • pretty-skills(管):本文档,管所有 skill
  • pretty-skills-creator(创):创建新 skill 的入口,自动带 4 风格 HTML 占位 + 可选 PPT
  • 二者是父子关系:装好 pretty-skills 后,ps create 就把 pretty-skills-creator 调起来

为什么叫"边缘优先开源"?

GitHub 的传统是"主项目维护者写 + 用户提 PR",pretty-skills 反过来:

  • 用户本地增删改无门槛(store 是用户的)
  • 用户觉得好的内容 → 主动提 PR 回主项目
  • 主项目维护者 review 后 merge

这样每个用户都是潜在贡献者,每个 PR 都是真实使用过的反馈。 主项目不需要全知全能 — 只需要 review + merge 就行。

开发

见 docs/contributing.md(怎么给 pretty-skills 提 PR) 见 docs/skill-schema.md(怎么写一个合法 skill 的 manifest)

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 Pretty Skills AI skill do?

跨 agent 统一管理你的所有 skill 和知识。 Use when 用户要"装 pretty-skills"、"管 skill"、"ps list/add/rm/update/graph/contribute/info/sync"、 查看 skill 依赖图、贡献新 skill、跨 Claude Code / Codex / Mavis / Cursor / Windsurf 同步 skill。 本地增删改无门槛,PR 是用户主动判断不是自动同步(边缘优先开源)。

Why use Pretty Skills on TypingMind?

Because you install it once and use it with any model. Pretty Skills 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 Pretty Skills in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/huangrichao2020/pretty-skills/tree/main/tools/pretty-skills. 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 Pretty Skills?

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 Pretty Skills?

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

Is the Pretty Skills AI skill free?

Yes. It is published on GitHub by huangrichao2020 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 👇