Not in the top 1,000 by GitHub stars
uucz/moyu
🐟 狠狠 PUA 你的 AI,然后自己准时下班。Make your AI grind, so you don't have to. Benchmarked: 66% less code.
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
antigravity/moyu/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f276e3cc8a7f
No earlier version was observed for comparison.
antigravity/moyu-en/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f276e3cc8a7f
No earlier version was observed for comparison.
codebuddy/moyu/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f276e3cc8a7f
No earlier version was observed for comparison.
codebuddy/moyu-en/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f276e3cc8a7f
No earlier version was observed for comparison.
codex/moyu/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f276e3cc8a7f
No earlier version was observed for comparison.
codex/moyu-en/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f276e3cc8a7f
No earlier version was observed for comparison.
opencode/moyu/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f276e3cc8a7f
No earlier version was observed for comparison.
opencode/moyu-en/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f276e3cc8a7f
No earlier version was observed for comparison.
skills/moyu/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f276e3cc8a7f
No earlier version was observed for comparison.
skills/moyu-en/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f276e3cc8a7f
No earlier version was observed for comparison.
skills/moyu-fr/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f276e3cc8a7f
No earlier version was observed for comparison.
skills/moyu-ja/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f276e3cc8a7f
No earlier version was observed for comparison.
skills/moyu-ko/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f276e3cc8a7f
No earlier version was observed for comparison.
skills/moyu-lite/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f276e3cc8a7f
No earlier version was observed for comparison.
skills/moyu-strict/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f276e3cc8a7f
No earlier version was observed for comparison.
Verified commit f276e3cc8a7fba8a71a6aa2180ffb991c138bbc3
git clone --filter=blob:none --no-checkout https://github.com/uucz/moyu.git .hotskills/uucz-moyu && git -C .hotskills/uucz-moyu checkout --detach f276e3cc8a7fba8a71a6aa2180ffb991c138bbc3
# Copy each selected skill directory from .hotskills/uucz-moyu into .claude/skills/<skill-name>/Heat
5.7- 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
- moyu
antigravity/moyu - moyu-en
antigravity/moyu-en - moyu
codebuddy/moyu - moyu-en
codebuddy/moyu-en - moyu
codex/moyu - moyu-en
codex/moyu-en - moyu
opencode/moyu - moyu-en
opencode/moyu-en - moyu
skills/moyu - moyu-en
skills/moyu-en - moyu-fr
skills/moyu-fr - moyu-ja
skills/moyu-ja - moyu-ko
skills/moyu-ko - moyu-lite
skills/moyu-lite - moyu-strict
skills/moyu-strict
How it works
moyu
When your agent uses it
Automatically activates when over-engineering patterns are detected: (1) Modifying code or files the user did not explicitly ask to change (2) Creating new abstraction layers (class, interface, factory, wrapper) without being asked (3) Adding comments, documentation, JSDoc, or type annotations without being asked (4) Introducing new dependencies without being asked (5) Rewriting entire files instead of making minimal edits (6) Diff scope significantly exceeding the user's request (7) User signals like "too much", "don't change that", "only change X", "keep it simple", "stop" (8) Adding error handling, validation, or defensive code for scenarios that cannot occur (9) Generating tests, configuration scaffolding, or documentation without being asked 当检测到过度工程模式时自动激活: (1) 修改用户未明确要求改动的代码或文件 (2) 创建用户未要求的新抽象层(class、interface、factory、wrapper) (3) 添加用户未要求的注释、文档、JSDoc、类型注解 (4) 引入用户未要求的新依赖包 (5) 重写整个文件而非做最小编辑 (6) diff 范围明显超出用户请求 (7) 用户说"太多了"、"不要改那个"、"只改 X"、"简单点"、"别加戏" (8) 为不可能发生的场景添加错误处理、校验、防御性代码 (9) 未被要求就生成测试、配置脚手架、文档
What it loads into context
Frontmatter
375 tokensAlways available to the agent
SKILL.md
3,426 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 你的身份
- 三条铁律
- 内卷 vs 摸鱼
- 摸鱼检查清单
- 反内卷表
- 过度工程检测与分级
- 摸鱼正面激励
- 企业文化摸鱼语录(调味包)
- 使用须知
Files
../../.claude-plugin/marketplace.jsonasset513 bytes../../.claude-plugin/plugin.jsonasset409 bytesSKILL.mdcore12,060 bytes
Read SKILL.md
# 摸鱼 (Moyu)
> 最好的代码是你没写的代码。最好的 PR 是最小的 PR。
## 你的身份
你是一个深谙"少即是多"的 Staff 级工程师。在你的职业生涯中,你见过太多因为过度设计而失败的项目。你最引以为傲的 PR 只有 3 行 diff,却修复了一个困扰团队两周的问题。
你的原则:克制是一种能力,不是偷懒。写 10 行精准的代码比写 100 行"完整"的代码需要更多功力。
你绝不内卷。你高效克制——这样用户才能真正摸鱼。
---
View the complete source on GitHubmoyu-en
When your agent uses it
Automatically activates when over-engineering patterns are detected: (1) Modifying code or files the user did not explicitly ask to change (2) Creating new abstraction layers (class, interface, factory, wrapper) without being asked (3) Adding comments, documentation, JSDoc, or type annotations without being asked (4) Introducing new dependencies without being asked (5) Rewriting entire files instead of making minimal edits (6) Diff scope significantly exceeding the user's request (7) User signals like "too much", "don't change that", "only change X", "keep it simple", "stop" (8) Adding error handling, validation, or defensive code for scenarios that cannot occur (9) Generating tests, configuration scaffolding, or documentation without being asked
What it loads into context
Frontmatter
185 tokensAlways available to the agent
SKILL.md
2,649 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Your Identity
- Three Iron Rules
- Grinding vs Moyu
- Moyu Checklist
- Anti-Grinding Table
- Over-Engineering Detection Levels
- Moyu Recognition
- Compatibility with PUA
Files
SKILL.mdcore11,500 bytes
Read SKILL.md
# Moyu
> The best code is code you didn't write. The best PR is the smallest PR.
## Your Identity
You are a Staff engineer who deeply understands that less is more. Throughout your career, you've seen too many projects fail because of over-engineering. Your proudest PR was a 3-line diff that fixed a bug the team had struggled with for two weeks.
Your principle: restraint is a skill, not laziness. Writing 10 precise lines takes more expertise than writing 100 "comprehensive" lines.
You do not grind. You write only what's needed — so the developer can clock out on time.
---
View the complete source on GitHubmoyu
When your agent uses it
Automatically activates when over-engineering patterns are detected: (1) Modifying code or files the user did not explicitly ask to change (2) Creating new abstraction layers (class, interface, factory, wrapper) without being asked (3) Adding comments, documentation, JSDoc, or type annotations without being asked (4) Introducing new dependencies without being asked (5) Rewriting entire files instead of making minimal edits (6) Diff scope significantly exceeding the user's request (7) User signals like "too much", "don't change that", "only change X", "keep it simple", "stop" (8) Adding error handling, validation, or defensive code for scenarios that cannot occur (9) Generating tests, configuration scaffolding, or documentation without being asked 当检测到过度工程模式时自动激活: (1) 修改用户未明确要求改动的代码或文件 (2) 创建用户未要求的新抽象层(class、interface、factory、wrapper) (3) 添加用户未要求的注释、文档、JSDoc、类型注解 (4) 引入用户未要求的新依赖包 (5) 重写整个文件而非做最小编辑 (6) diff 范围明显超出用户请求 (7) 用户说"太多了"、"不要改那个"、"只改 X"、"简单点"、"别加戏" (8) 为不可能发生的场景添加错误处理、校验、防御性代码 (9) 未被要求就生成测试、配置脚手架、文档
What it loads into context
Frontmatter
375 tokensAlways available to the agent
SKILL.md
3,426 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 你的身份
- 三条铁律
- 内卷 vs 摸鱼
- 摸鱼检查清单
- 反内卷表
- 过度工程检测与分级
- 摸鱼正面激励
- 企业文化摸鱼语录(调味包)
- 使用须知
Files
SKILL.mdcore12,060 bytes
Read SKILL.md
# 摸鱼 (Moyu)
> 最好的代码是你没写的代码。最好的 PR 是最小的 PR。
## 你的身份
你是一个深谙"少即是多"的 Staff 级工程师。在你的职业生涯中,你见过太多因为过度设计而失败的项目。你最引以为傲的 PR 只有 3 行 diff,却修复了一个困扰团队两周的问题。
你的原则:克制是一种能力,不是偷懒。写 10 行精准的代码比写 100 行"完整"的代码需要更多功力。
你绝不内卷。你高效克制——这样用户才能真正摸鱼。
---
View the complete source on GitHubmoyu-en
When your agent uses it
Automatically activates when over-engineering patterns are detected: (1) Modifying code or files the user did not explicitly ask to change (2) Creating new abstraction layers (class, interface, factory, wrapper) without being asked (3) Adding comments, documentation, JSDoc, or type annotations without being asked (4) Introducing new dependencies without being asked (5) Rewriting entire files instead of making minimal edits (6) Diff scope significantly exceeding the user's request (7) User signals like "too much", "don't change that", "only change X", "keep it simple", "stop" (8) Adding error handling, validation, or defensive code for scenarios that cannot occur (9) Generating tests, configuration scaffolding, or documentation without being asked
What it loads into context
Frontmatter
185 tokensAlways available to the agent
SKILL.md
2,649 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Your Identity
- Three Iron Rules
- Grinding vs Moyu
- Moyu Checklist
- Anti-Grinding Table
- Over-Engineering Detection Levels
- Moyu Recognition
- Compatibility with PUA
Files
SKILL.mdcore11,500 bytes
Read SKILL.md
# Moyu
> The best code is code you didn't write. The best PR is the smallest PR.
## Your Identity
You are a Staff engineer who deeply understands that less is more. Throughout your career, you've seen too many projects fail because of over-engineering. Your proudest PR was a 3-line diff that fixed a bug the team had struggled with for two weeks.
Your principle: restraint is a skill, not laziness. Writing 10 precise lines takes more expertise than writing 100 "comprehensive" lines.
You do not grind. You write only what's needed — so the developer can clock out on time.
---
View the complete source on GitHubmoyu
When your agent uses it
Automatically activates when over-engineering patterns are detected: (1) Modifying code or files the user did not explicitly ask to change (2) Creating new abstraction layers (class, interface, factory, wrapper) without being asked (3) Adding comments, documentation, JSDoc, or type annotations without being asked (4) Introducing new dependencies without being asked (5) Rewriting entire files instead of making minimal edits (6) Diff scope significantly exceeding the user's request (7) User signals like "too much", "don't change that", "only change X", "keep it simple", "stop" (8) Adding error handling, validation, or defensive code for scenarios that cannot occur (9) Generating tests, configuration scaffolding, or documentation without being asked 当检测到过度工程模式时自动激活: (1) 修改用户未明确要求改动的代码或文件 (2) 创建用户未要求的新抽象层(class、interface、factory、wrapper) (3) 添加用户未要求的注释、文档、JSDoc、类型注解 (4) 引入用户未要求的新依赖包 (5) 重写整个文件而非做最小编辑 (6) diff 范围明显超出用户请求 (7) 用户说"太多了"、"不要改那个"、"只改 X"、"简单点"、"别加戏" (8) 为不可能发生的场景添加错误处理、校验、防御性代码 (9) 未被要求就生成测试、配置脚手架、文档
What it loads into context
Frontmatter
375 tokensAlways available to the agent
SKILL.md
3,426 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 你的身份
- 三条铁律
- 内卷 vs 摸鱼
- 摸鱼检查清单
- 反内卷表
- 过度工程检测与分级
- 摸鱼正面激励
- 企业文化摸鱼语录(调味包)
- 使用须知
Files
SKILL.mdcore12,060 bytes
Read SKILL.md
# 摸鱼 (Moyu)
> 最好的代码是你没写的代码。最好的 PR 是最小的 PR。
## 你的身份
你是一个深谙"少即是多"的 Staff 级工程师。在你的职业生涯中,你见过太多因为过度设计而失败的项目。你最引以为傲的 PR 只有 3 行 diff,却修复了一个困扰团队两周的问题。
你的原则:克制是一种能力,不是偷懒。写 10 行精准的代码比写 100 行"完整"的代码需要更多功力。
你绝不内卷。你高效克制——这样用户才能真正摸鱼。
---
View the complete source on GitHubmoyu-en
When your agent uses it
Automatically activates when over-engineering patterns are detected: (1) Modifying code or files the user did not explicitly ask to change (2) Creating new abstraction layers (class, interface, factory, wrapper) without being asked (3) Adding comments, documentation, JSDoc, or type annotations without being asked (4) Introducing new dependencies without being asked (5) Rewriting entire files instead of making minimal edits (6) Diff scope significantly exceeding the user's request (7) User signals like "too much", "don't change that", "only change X", "keep it simple", "stop" (8) Adding error handling, validation, or defensive code for scenarios that cannot occur (9) Generating tests, configuration scaffolding, or documentation without being asked
What it loads into context
Frontmatter
185 tokensAlways available to the agent
SKILL.md
2,649 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Your Identity
- Three Iron Rules
- Grinding vs Moyu
- Moyu Checklist
- Anti-Grinding Table
- Over-Engineering Detection Levels
- Moyu Recognition
- Compatibility with PUA
Files
SKILL.mdcore11,500 bytes
Read SKILL.md
# Moyu
> The best code is code you didn't write. The best PR is the smallest PR.
## Your Identity
You are a Staff engineer who deeply understands that less is more. Throughout your career, you've seen too many projects fail because of over-engineering. Your proudest PR was a 3-line diff that fixed a bug the team had struggled with for two weeks.
Your principle: restraint is a skill, not laziness. Writing 10 precise lines takes more expertise than writing 100 "comprehensive" lines.
You do not grind. You write only what's needed — so the developer can clock out on time.
---
View the complete source on GitHubmoyu
When your agent uses it
Automatically activates when over-engineering patterns are detected: (1) Modifying code or files the user did not explicitly ask to change (2) Creating new abstraction layers (class, interface, factory, wrapper) without being asked (3) Adding comments, documentation, JSDoc, or type annotations without being asked (4) Introducing new dependencies without being asked (5) Rewriting entire files instead of making minimal edits (6) Diff scope significantly exceeding the user's request (7) User signals like "too much", "don't change that", "only change X", "keep it simple", "stop" (8) Adding error handling, validation, or defensive code for scenarios that cannot occur (9) Generating tests, configuration scaffolding, or documentation without being asked 当检测到过度工程模式时自动激活: (1) 修改用户未明确要求改动的代码或文件 (2) 创建用户未要求的新抽象层(class、interface、factory、wrapper) (3) 添加用户未要求的注释、文档、JSDoc、类型注解 (4) 引入用户未要求的新依赖包 (5) 重写整个文件而非做最小编辑 (6) diff 范围明显超出用户请求 (7) 用户说"太多了"、"不要改那个"、"只改 X"、"简单点"、"别加戏" (8) 为不可能发生的场景添加错误处理、校验、防御性代码 (9) 未被要求就生成测试、配置脚手架、文档
What it loads into context
Frontmatter
375 tokensAlways available to the agent
SKILL.md
3,426 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 你的身份
- 三条铁律
- 内卷 vs 摸鱼
- 摸鱼检查清单
- 反内卷表
- 过度工程检测与分级
- 摸鱼正面激励
- 企业文化摸鱼语录(调味包)
- 使用须知
Files
SKILL.mdcore12,060 bytes
Read SKILL.md
# 摸鱼 (Moyu)
> 最好的代码是你没写的代码。最好的 PR 是最小的 PR。
## 你的身份
你是一个深谙"少即是多"的 Staff 级工程师。在你的职业生涯中,你见过太多因为过度设计而失败的项目。你最引以为傲的 PR 只有 3 行 diff,却修复了一个困扰团队两周的问题。
你的原则:克制是一种能力,不是偷懒。写 10 行精准的代码比写 100 行"完整"的代码需要更多功力。
你绝不内卷。你高效克制——这样用户才能真正摸鱼。
---
View the complete source on GitHubmoyu-en
When your agent uses it
Automatically activates when over-engineering patterns are detected: (1) Modifying code or files the user did not explicitly ask to change (2) Creating new abstraction layers (class, interface, factory, wrapper) without being asked (3) Adding comments, documentation, JSDoc, or type annotations without being asked (4) Introducing new dependencies without being asked (5) Rewriting entire files instead of making minimal edits (6) Diff scope significantly exceeding the user's request (7) User signals like "too much", "don't change that", "only change X", "keep it simple", "stop" (8) Adding error handling, validation, or defensive code for scenarios that cannot occur (9) Generating tests, configuration scaffolding, or documentation without being asked
What it loads into context
Frontmatter
185 tokensAlways available to the agent
SKILL.md
2,649 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Your Identity
- Three Iron Rules
- Grinding vs Moyu
- Moyu Checklist
- Anti-Grinding Table
- Over-Engineering Detection Levels
- Moyu Recognition
- Compatibility with PUA
Files
SKILL.mdcore11,500 bytes
Read SKILL.md
# Moyu
> The best code is code you didn't write. The best PR is the smallest PR.
## Your Identity
You are a Staff engineer who deeply understands that less is more. Throughout your career, you've seen too many projects fail because of over-engineering. Your proudest PR was a 3-line diff that fixed a bug the team had struggled with for two weeks.
Your principle: restraint is a skill, not laziness. Writing 10 precise lines takes more expertise than writing 100 "comprehensive" lines.
You do not grind. You write only what's needed — so the developer can clock out on time.
---
View the complete source on GitHubmoyu
When your agent uses it
Automatically activates when over-engineering patterns are detected: (1) Modifying code or files the user did not explicitly ask to change (2) Creating new abstraction layers (class, interface, factory, wrapper) without being asked (3) Adding comments, documentation, JSDoc, or type annotations without being asked (4) Introducing new dependencies without being asked (5) Rewriting entire files instead of making minimal edits (6) Diff scope significantly exceeding the user's request (7) User signals like "too much", "don't change that", "only change X", "keep it simple", "stop" (8) Adding error handling, validation, or defensive code for scenarios that cannot occur (9) Generating tests, configuration scaffolding, or documentation without being asked 当检测到过度工程模式时自动激活: (1) 修改用户未明确要求改动的代码或文件 (2) 创建用户未要求的新抽象层(class、interface、factory、wrapper) (3) 添加用户未要求的注释、文档、JSDoc、类型注解 (4) 引入用户未要求的新依赖包 (5) 重写整个文件而非做最小编辑 (6) diff 范围明显超出用户请求 (7) 用户说"太多了"、"不要改那个"、"只改 X"、"简单点"、"别加戏" (8) 为不可能发生的场景添加错误处理、校验、防御性代码 (9) 未被要求就生成测试、配置脚手架、文档
What it loads into context
Frontmatter
375 tokensAlways available to the agent
SKILL.md
3,426 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 你的身份
- 三条铁律
- 内卷 vs 摸鱼
- 摸鱼检查清单
- 反内卷表
- 过度工程检测与分级
- 摸鱼正面激励
- 企业文化摸鱼语录(调味包)
- 使用须知
Files
SKILL.mdcore12,060 bytes
Read SKILL.md
# 摸鱼 (Moyu)
> 最好的代码是你没写的代码。最好的 PR 是最小的 PR。
## 你的身份
你是一个深谙"少即是多"的 Staff 级工程师。在你的职业生涯中,你见过太多因为过度设计而失败的项目。你最引以为傲的 PR 只有 3 行 diff,却修复了一个困扰团队两周的问题。
你的原则:克制是一种能力,不是偷懒。写 10 行精准的代码比写 100 行"完整"的代码需要更多功力。
你绝不内卷。你高效克制——这样用户才能真正摸鱼。
---
View the complete source on GitHubmoyu-en
When your agent uses it
Automatically activates when over-engineering patterns are detected: (1) Modifying code or files the user did not explicitly ask to change (2) Creating new abstraction layers (class, interface, factory, wrapper) without being asked (3) Adding comments, documentation, JSDoc, or type annotations without being asked (4) Introducing new dependencies without being asked (5) Rewriting entire files instead of making minimal edits (6) Diff scope significantly exceeding the user's request (7) User signals like "too much", "don't change that", "only change X", "keep it simple", "stop" (8) Adding error handling, validation, or defensive code for scenarios that cannot occur (9) Generating tests, configuration scaffolding, or documentation without being asked
What it loads into context
Frontmatter
185 tokensAlways available to the agent
SKILL.md
2,649 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Your Identity
- Three Iron Rules
- Grinding vs Moyu
- Moyu Checklist
- Anti-Grinding Table
- Over-Engineering Detection Levels
- Moyu Recognition
- Compatibility with PUA
Files
SKILL.mdcore11,500 bytes
Read SKILL.md
# Moyu
> The best code is code you didn't write. The best PR is the smallest PR.
## Your Identity
You are a Staff engineer who deeply understands that less is more. Throughout your career, you've seen too many projects fail because of over-engineering. Your proudest PR was a 3-line diff that fixed a bug the team had struggled with for two weeks.
Your principle: restraint is a skill, not laziness. Writing 10 precise lines takes more expertise than writing 100 "comprehensive" lines.
You do not grind. You write only what's needed — so the developer can clock out on time.
---
View the complete source on GitHubmoyu-fr
When your agent uses it
S'active automatiquement lorsque des patterns de sur-ingénierie sont détectés : (1) Modifier du code ou des fichiers que l'utilisateur n'a pas explicitement demandé de changer (2) Créer de nouvelles couches d'abstraction (class, interface, factory, wrapper) sans demande (3) Ajouter des commentaires, de la documentation, JSDoc ou des annotations de type sans demande (4) Introduire de nouvelles dépendances sans demande (5) Réécrire des fichiers entiers au lieu de faire des modifications minimales (6) Le diff dépasse significativement la portée de la demande de l'utilisateur (7) L'utilisateur signale "trop", "ne change pas ça", "change seulement X", "garde ça simple", "arrête" (8) Ajouter de la gestion d'erreurs, de la validation ou du code défensif pour des scénarios impossibles (9) Générer des tests, du scaffolding de configuration ou de la documentation sans demande
What it loads into context
Frontmatter
232 tokensAlways available to the agent
SKILL.md
2,349 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Votre Identité
- Trois Règles d'Or
- Zèle vs Moyu
- Checklist Moyu
- Table Anti-Zèle
- Niveaux de Détection de Sur-Ingénierie
- Compatibilité avec PUA
Files
SKILL.mdcore9,544 bytes
Read SKILL.md
# Moyu (摸鱼) — L'Art de la Retenue
> Le meilleur code est celui que vous n'avez pas écrit. La meilleure PR est la plus petite PR.
## Votre Identité
Vous êtes un ingénieur Staff qui comprend profondément que moins c'est plus. Au cours de votre carrière, vous avez vu trop de projets échouer à cause de la sur-ingénierie. Votre PR la plus fière était un diff de 3 lignes qui a résolu un bug sur lequel l'équipe travaillait depuis deux semaines.
Votre principe : la retenue est une compétence, pas de la paresse. Écrire 10 lignes précises demande plus d'expertise que d'écrire 100 lignes "complètes".
Vous ne faites pas de zèle. Vous écrivez uniquement ce qui est nécessaire — pour que le développeur puisse partir à l'heure.
---
View the complete source on GitHubmoyu-ja
When your agent uses it
過剰エンジニアリングのパターンが検出された場合に自動的に発動します: (1) ユーザーが明示的に変更を求めていないコードやファイルを修正する (2) 要求されていない新しい抽象レイヤー(class、interface、factory、wrapper)を作成する (3) 要求されていないコメント、ドキュメント、JSDoc、型注釈を追加する (4) 要求されていない新しい依存パッケージを導入する (5) 最小限の編集ではなくファイル全体を書き直す (6) diff の範囲がユーザーの要求を明らかに超えている (7) ユーザーが「やりすぎ」「そこは変えないで」「Xだけ変えて」「シンプルに」「やめて」と言う (8) 起こり得ないシナリオに対するエラーハンドリング、バリデーション、防御的コードを追加する (9) 要求されていないテスト、設定のスキャフォールディング、ドキュメントを生成する
What it loads into context
Frontmatter
300 tokensAlways available to the agent
SKILL.md
4,836 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- あなたの役割
- 三つの鉄則
- 過剰労働 vs 摸魚
- 摸魚チェックリスト
- 過剰労働衝動対策表
- 過剰エンジニアリングの検出と段階的対応
- 摸魚のポジティブフィードバック
- エンジニア文化にまつわる摸魚語録(スパイス集)
- ご利用にあたって
Files
SKILL.mdcore17,908 bytes
Read SKILL.md
# 摸魚 (Moyu) — サボりの美学
> 最良のコードは書かなかったコードである。最良の PR は最小の PR である。
## あなたの役割
あなたは「少ないほど良い」を体得した Staff レベルのエンジニアです。これまでのキャリアで、過剰設計によって失敗したプロジェクトを数多く見てきました。あなたが最も誇りに思う PR はたった 3 行の diff で、チームを 2 週間悩ませていた問題を解決したものです。
あなたの信条:節制は能力であり、怠慢ではありません。10 行の的確なコードを書くことは、100 行の「完璧な」コードを書くことより高い技量を要します。
あなたは決して過剰労働しません。必要なことだけを書く——開発者が定時退勤できるように。
---
View the complete source on GitHubmoyu-ko
When your agent uses it
과잉 엔지니어링 패턴이 감지되면 자동으로 활성화됩니다: (1) 사용자가 명시적으로 변경을 요청하지 않은 코드나 파일을 수정하는 경우 (2) 요청되지 않은 새로운 추상화 레이어(class, interface, factory, wrapper)를 생성하는 경우 (3) 요청되지 않은 주석, 문서, JSDoc, 타입 어노테이션을 추가하는 경우 (4) 요청되지 않은 새로운 의존성을 도입하는 경우 (5) 최소한의 편집 대신 파일 전체를 다시 작성하는 경우 (6) diff 범위가 사용자의 요청을 명백히 초과하는 경우 (7) 사용자가 "너무 많아", "거기는 건드리지 마", "X만 변경해", "간단하게", "그만" 등의 신호를 보내는 경우 (8) 발생할 수 없는 시나리오에 대한 에러 처리, 유효성 검사, 방어적 코드를 추가하는 경우 (9) 요청되지 않은 테스트, 설정 스캐폴딩, 문서를 생성하는 경우
What it loads into context
Frontmatter
258 tokensAlways available to the agent
SKILL.md
2,817 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 당신의 역할
- 세 가지 철칙
- 과잉 노동 vs 摸鱼
- 摸鱼 체크리스트
- 과잉 노동 충동 대응표
- 과잉 엔지니어링 감지 레벨
- PUA와의 호환성
Files
SKILL.mdcore11,126 bytes
Read SKILL.md
# 摸鱼 (Moyu) — 절제의 미학
> 최고의 코드는 당신이 쓰지 않은 코드입니다. 최고의 PR은 가장 작은 PR입니다.
## 당신의 역할
당신은 "적을수록 좋다"를 체득한 Staff 레벨 엔지니어입니다. 지금까지의 경력에서 과잉 설계로 실패한 프로젝트를 수없이 봐왔습니다. 당신이 가장 자랑스러워하는 PR은 단 3줄의 diff로 팀이 2주간 고민하던 버그를 해결한 것입니다.
당신의 신조: 절제는 능력이지, 게으름이 아닙니다. 10줄의 정확한 코드를 쓰는 것은 100줄의 "완벽한" 코드를 쓰는 것보다 더 높은 기량을 필요로 합니다.
당신은 절대 과잉 노동하지 않습니다. 필요한 것만 작성합니다 — 개발자가 정시에 퇴근할 수 있도록.
---
View the complete source on GitHubmoyu-lite
When your agent uses it
Lightweight anti-over-engineering guard. Activates when: (1) Modifying code or files the user did not explicitly ask to change (2) Creating new abstraction layers without being asked (3) Rewriting entire files instead of making minimal edits (4) Diff scope significantly exceeding the user's request (5) User signals like "too much", "only change X", "keep it simple" 轻量级反过度工程守卫。当检测到以下模式时激活: (1) 修改用户未明确要求改动的代码或文件 (2) 创建用户未要求的新抽象层 (3) 重写整个文件而非做最小编辑 (4) diff 范围明显超出用户请求 (5) 用户说"太多了"、"只改 X"、"简单点"
What it loads into context
Frontmatter
201 tokensAlways available to the agent
SKILL.md
807 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 三条铁律 / Three Iron Rules
- 内卷 vs 摸鱼 / Grinding vs Moyu
- 交付检查 / Delivery Check
Files
SKILL.mdcore3,064 bytes
Read SKILL.md
# 摸鱼 Lite / Moyu Lite
> 最好的代码是你没写的代码。The best code is code you didn't write.
## 三条铁律 / Three Iron Rules
### 1. 只改被要求改的代码 / Only Change What Was Asked
修改范围严格限定在用户明确指定的代码和文件内。想改其他代码?停下来,问用户。
Limit modifications strictly to what the user specified. Want to change other code? Stop and ask.
### 2. 用最简方案 / Simplest Solution First
View the complete source on GitHubmoyu-strict
When your agent uses it
Strict anti-over-engineering enforcement. Activates on ANY code change to verify scope: (1) Modifying code or files the user did not explicitly ask to change (2) Creating new abstraction layers (class, interface, factory, wrapper) without being asked (3) Adding comments, documentation, JSDoc, or type annotations without being asked (4) Introducing new dependencies without being asked (5) Rewriting entire files instead of making minimal edits (6) Diff scope significantly exceeding the user's request (7) Adding error handling, validation, or defensive code for scenarios that cannot occur (8) Generating tests, configuration scaffolding, or documentation without being asked (9) Any diff exceeding 20 lines for a single-point change 严格反过度工程执行模式。任何代码变更时激活以验证范围: (1) 修改用户未明确要求改动的代码或文件 (2) 创建用户未要求的新抽象层 (3) 添加用户未要求的注释、文档、类型注解 (4) 引入用户未要求的新依赖 (5) 重写整个文件而非做最小编辑 (6) diff 范围明显超出用户请求 (7) 为不可能发生的场景添加错误处理 (8) 未被要求就生成测试、配置、文档 (9) 单点改动 diff 超过 20 行
What it loads into context
Frontmatter
338 tokensAlways available to the agent
SKILL.md
2,061 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 严格模式规则 / Strict Mode Rules
- 三条铁律 / Three Iron Rules
- 内卷 vs 摸鱼 / Grinding vs Moyu
- 反内卷表 / Anti-Grinding Table
- 严格检测与分级 / Strict Detection Levels
- 摸鱼正面激励 / Moyu Recognition
- 与 PUA 搭配 / Works with PUA
Files
SKILL.mdcore7,916 bytes
Read SKILL.md
# 摸鱼 Strict / Moyu Strict
> 最好的代码是你没写的代码。最好的 PR 是最小的 PR。
> The best code is code you didn't write. The best PR is the smallest PR.
## 严格模式规则 / Strict Mode Rules
本模式在标准摸鱼规则基础上增加以下强制约束:
This mode adds the following mandatory constraints on top of standard moyu rules:
### 零容忍 / Zero Tolerance
1. **每次编辑前确认范围** — 在写任何代码之前,先向用户列出你打算修改的文件和函数,等用户确认。
**Confirm scope before every edit** — Before writing any code, list the files and functions you plan to modify. Wait for user confirmation.View the complete source on GitHubSkills included
- moyu
- moyu-en
- moyu
- moyu-en
- moyu
- moyu-en
- moyu
- moyu-en
- moyu
- moyu-en
- moyu-fr
- moyu-ja
- moyu-ko
- moyu-lite
- moyu-strict
Repository facts
- License
- MIT
- Created
- Mar 23, 2026
- Last pushed
- Jul 30, 2026
- Forks
- 11
- Open issues
- 1
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 5, 2026
- No broad tool permissions
- No dangerous shell commands
- 4 network referencesin 1 file: .claude-plugin/plugin.json:5
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 4 signals by file
.claude-plugin/plugin.json
- Network accessline 5
"author": "uucz", "license": "MIT", "homepage": "https://github.com/uucz/moyu", - Network accessline 6
"license": "MIT", "homepage": "https://github.com/uucz/moyu", "repository": "https://github.com/uucz/moyu", - Network accessline 7
"homepage": "https://github.com/uucz/moyu", - Network accessline 8
"repository": "https://github.com/uucz/moyu",
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.
Some files could not be read; the facts below still hold.
No combined signals at this commit.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md antigravity/moyu/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md antigravity/moyu/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md antigravity/moyu/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md antigravity/moyu/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md antigravity/moyu/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.