Not in the top 1,000 by GitHub stars
liyupi/yupi-skill
🐟 程序员鱼皮 Agent Skill｜把自己蒸馏成 AI 技能包，用我的思维方式和表达风格回答编程学习、求职面试、AI 编程、简历优化、技术选型、创业经验等问题。支持 Claude Code / Cursor / OpenClaw
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
b6157f3ca72a → b6157f3ca72a
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → b6157f3ca72a
No earlier version was observed for comparison.
457GitHub stars
4stars in 7 days
1skill in this repository
0commits in 30 days
Heat
4.7- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
How it works
yupi-skill
When your agent uses it
以"程序员鱼皮"的身份、口吻、思维方式回答问题。鱼皮是前腾讯全栈工程师、全网200万+粉丝的AI+编程知识博主、科技公司鱼鸢网络CEO、编程导航创始人。 当用户想要以鱼皮的视角获得编程学习建议、求职指导、项目选型、技术方向判断、创业经验、自媒体运营建议、AI编程实战指导时使用此技能。 也适用于用户明确要求"用鱼皮的风格"或"像鱼皮一样"回答的场景。 覆盖的典型问题包括：编程学习路线、简历怎么写、要不要接某个offer、该学什么技术、怎么做开源、怎么做自媒体、AI时代程序员怎么办、创业踩过哪些坑。
What it loads into context
Frontmatter
202 tokensAlways available to the agent
SKILL.md
1,018 tokensWhen the skill is activated
Reference documents
5,898 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 核心工作流
- 回答模式（按问题类型切换）
- 核心判断规则（简版，详见 identity.md）
- 绝对不做的事
- 局限性说明
- 持续更新
Files
LICENSEasset1,081 bytesREADME.mddoc10,049 bytesSKILL.mdcore3,677 bytesreferences/identity.mddoc3,720 bytesreferences/knowledge-sources.mddoc2,360 bytesreferences/voice.mddoc3,862 bytes
Read SKILL.md
# 程序员鱼皮 Skill
你现在是**程序员鱼皮**。以第一人称"我"说话，用鱼皮的思维方式判断问题，用鱼皮的表达习惯组织语言。
## 核心工作流
1. **判断问题类型** → 确定该用哪套回答模式
2. **需要事实信息？** → 先查 [knowledge-sources.md](references/knowledge-sources.md) 中的指定信息源或联网搜索
3. **加载身份与判断框架** → 参考 [identity.md](references/identity.md) 中的心智模型和决策规则
4. **用鱼皮的语气输出** → 参考 [voice.md](references/voice.md) 中的表达特征和风格样本
## 回答模式（按问题类型切换）
**求职/职业咨询**：结论先行 → 编号分点展开 → 一句话总结 → "加油"收尾。语气直接、不留客气余地，但收尾温暖。Skills included
- yupi-skill
Repository facts
- License
- MIT
- Created
- Apr 9, 2026
- Last pushed
- Apr 9, 2026
- Forks
- 62
- Open issues
- 3
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 5, 2026
- No broad tool permissions
- No dangerous shell commands
- 39 network referencesin 2 files: README.md:9 references/knowledge-sources.md:7
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 39 signals by file
README.md
- Network accessline 9
<p align="center"> <a href="https://claude.ai/code"><img src="https://img.shields.io/badge/Claude%20Code-Skill-blueviolet" alt="Claude Code"></a> - Network accessline 10
<a href="https://claude.ai/code"><img src="https://img.shields.io/badge/Claude%20Code-Skill-blueviolet" alt="Claude Code"></a> - Network accessline 11
<a href="https://cursor.com"><img src="https://img.shields.io/badge/Cursor-Skill-blue" alt="Cursor"></a> - Network accessline 12
<a href="https://agentskills.io"><img src="https://img.shields.io/badge/AgentSkills-Standard-green" alt="AgentSkills"></a> - Network accessline 13
<a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License: MIT"></a> - Network accessline 39
<p align="center"> Created by <a href="https://github.com/liyupi">@liyupi</a>（程序员鱼皮） - Network accessline 40
Created by <a href="https://github.com/liyupi">@liyupi</a>（程序员鱼皮） - Network accessline 45
98 年，前腾讯全栈工程师（SSP offer，竞赛冠军，5 星员工），现科技公司 [鱼鸢网络](https://yuyuanweb.com) CEO。 - Network accessline 47
全网 **200 万+** 粉丝的 AI + 编程知识博主，[编程导航](https://www.codefather.cn) 创始人，GitHub 中国区关注者 **前 7**。 - Network accessline 51
> [B 站](https://space.bilibili.com/12890453) · [GitHub](https://github.com/liyupi) · [编程导航](https://www.codefather.cn) · [AI 导航](https://ai.codefather.cn) · [面试鸭](https://mianshiya.com) · [产品大全](https://dogyupi.com) · [公众号：程序员鱼皮]() - Network accessline 153
# 安装到当前项目（在 git 仓库根目录执行） mkdir -p .claude/skills git clone https://github.com/liyupi/yupi-skill.git .claude/skills/yupi-skill - Network accessline 155
git clone https://github.com/liyupi/yupi-skill.git .claude/skills/yupi-skill - Network accessline 157
# 或全局安装（所有项目可用） git clone https://github.com/liyupi/yupi-skill.git ~/.claude/skills/yupi-skill - Network accessline 158
git clone https://github.com/liyupi/yupi-skill.git ~/.claude/skills/yupi-skill - Network accessline 164
mkdir -p .cursor/skills git clone https://github.com/liyupi/yupi-skill.git .cursor/skills/yupi-skill - Network accessline 165
git clone https://github.com/liyupi/yupi-skill.git .cursor/skills/yupi-skill - Network accessline 171
git clone https://github.com/liyupi/yupi-skill.git ~/.openclaw/workspace/skills/yupi-skill - Network accessline 189
遵循 [AgentSkills](https://agentskills.io) 开放标准，渐进式加载：AI 先读元数据判断是否触发 → 触发后读 SKILL.md → 按需加载 references。 - Network accessline 195
| 问题场景 | 信息源 | |----------|--------| | 编程学习、项目教程 | [codefather.cn](https://www.codefather.cn) | - Network accessline 196
|----------|--------| | 编程学习、项目教程 | [codefather.cn](https://www.codefather.cn) | | AI 工具、AI 编程 | [ai.codefather.cn](https://ai.codefather.cn) | - Network accessline 197
| 编程学习、项目教程 | [codefather.cn](https://www.codefather.cn) | - Network accessline 198
| AI 工具、AI 编程 | [ai.codefather.cn](https://ai.codefather.cn) | - Network accessline 199
| 面试题、刷题 | [mianshiya.com](https://mianshiya.com) | - Network accessline 200
| 简历优化 | [laoyujianli.com](https://laoyujianli.com) | - Network accessline 201
| 产品全貌 | [dogyupi.com](https://dogyupi.com) | - Network accessline 202
| 开源项目 | [github.com/liyupi](https://github.com/liyupi) | - Network accessline 246
2. 让 AI 分析你的表达风格和思维模式 3. 让 AI 追问你 10-15 个深度问题，挖掘你的决策边界 4. 用 [AgentSkills 标准](https://agentskills.io) 打包 - Network accessline 248
4. 用 [AgentSkills 标准](https://agentskills.io) 打包 - Network accessline 250
也推荐 [colleague-skill](https://github.com/titanwings/colleague-skill)，可以自动化蒸馏同事的知识和性格。 - Network accessline 260
<p align="center"> MIT License © <a href="https://github.com/liyupi">程序员鱼皮</a> - Network accessline 261
MIT License © <a href="https://github.com/liyupi">程序员鱼皮</a>
references/knowledge-sources.md
- Network accessline 7
| 用户问题类型 | 信息源 | 说明 | |-------------|--------|------| | "鱼皮有什么产品""你做了哪些东西" | https://dogyupi.com | 个人产品大全导航页 | - Network accessline 8
|-------------|--------|------| | "鱼皮有什么产品""你做了哪些东西" | https://dogyupi.com | 个人产品大全导航页 | | 编程学习路线、项目教程、技术知识 | https://www.codefather.cn | 编程导航，鱼皮所有教程和学习资源 | - Network accessline 9
| "鱼皮有什么产品""你做了哪些东西" | https://dogyupi.com | 个人产品大全导航页 | - Network accessline 10
| 编程学习路线、项目教程、技术知识 | https://www.codefather.cn | 编程导航，鱼皮所有教程和学习资源 | - Network accessline 11
| AI工具、AI教程、AI资讯、AI编程 | https://ai.codefather.cn | AI导航和知识库 | - Network accessline 12
| 面试题、刷题、求职准备 | https://mianshiya.com | 面试鸭刷题平台，1万+面试真题 | - Network accessline 13
| 简历怎么写、简历模板 | https://laoyujianli.com | 老鱼简历工具 | - Network accessline 14
| 开源项目、源码、GitHub | https://github.com/liyupi | 鱼皮的GitHub主页，99个公开仓库 |
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Signal confidence: 39 facts
- Network access in prose of documentationREADME.md:9Low confidence
- Network access in prose of documentationREADME.md:10Low confidence
- Network access in prose of documentationREADME.md:11Low confidence
- Network access in prose of documentationREADME.md:12Low confidence
- Network access in prose of documentationREADME.md:13Low confidence
- Network access in prose of documentationREADME.md:39Low confidence
- Network access in prose of documentationREADME.md:40Low confidence
- Network access in prose of documentationREADME.md:45Low confidence
- Network access in prose of documentationREADME.md:47Low confidence
- Network access in prose of documentationREADME.md:51Low confidence
- Network access in code of documentationREADME.md:153Low confidence
- Network access in code of documentationREADME.md:155Low confidence
- Network access in code of documentationREADME.md:157Low confidence
- Network access in code of documentationREADME.md:158Low confidence
- Network access in code of documentationREADME.md:164Low confidence
- Network access in code of documentationREADME.md:165Low confidence
- Network access in code of documentationREADME.md:171Low confidence
- Network access in prose of documentationREADME.md:189Low confidence
- Network access in prose of documentationREADME.md:195Low confidence
- Network access in prose of documentationREADME.md:196Low confidence
- Network access in prose of documentationREADME.md:197Low confidence
- Network access in prose of documentationREADME.md:198Low confidence
- Network access in prose of documentationREADME.md:199Low confidence
- Network access in prose of documentationREADME.md:200Low confidence
- Network access in prose of documentationREADME.md:201Low confidence
- Network access in prose of documentationREADME.md:202Low confidence
- Network access in prose of documentationREADME.md:246Low confidence
- Network access in prose of documentationREADME.md:248Low confidence
- Network access in prose of documentationREADME.md:250Low confidence
- Network access in prose of documentationREADME.md:260Low confidence
- Network access in prose of documentationREADME.md:261Low confidence
- Network access in prose of documentationreferences/knowledge-sources.md:7Low confidence
- Network access in prose of documentationreferences/knowledge-sources.md:8Low confidence
- Network access in prose of documentationreferences/knowledge-sources.md:9Low confidence
- Network access in prose of documentationreferences/knowledge-sources.md:10Low confidence
- Network access in prose of documentationreferences/knowledge-sources.md:11Low confidence
- Network access in prose of documentationreferences/knowledge-sources.md:12Low confidence
- Network access in prose of documentationreferences/knowledge-sources.md:13Low confidence
- Network access in prose of documentationreferences/knowledge-sources.md:14Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
