GitHub 助手
- 作者仓库星标 1,408
- 作者更新于 实时读取
- 作者仓库 skill-from-masters
- 领域
- 工程开发
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 88 / 100 · 社区维护
- 作者 / 版本 / 许可
- @GBSOSS · 未声明 license
- Token 消耗评级
- 低消耗
- 接入复杂程度
- 即装即用
- 是否需要外部 API Key
- 不需要
- 兼容的系统
- 未声明（默认跨平台）
- 底层运行要求
- 无特殊要求
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- 网络行为
- 仅限本地
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生，可能与作者实际意图存在差异。
需要注意： 未限定 allowed-tools，默认拥有全部工具权限。
---
name: skill-from-github
description: Create skills by learning from high-quality GitHub projects When users want to accomplish someth…
category: 工程开发
runtime: 无特殊运行时
---
# skill-from-github 输出预览
## PART A: 任务判断
- 适用问题：代码实现、重构、调试或代码审查。
- 输入要求：目标材料、限制条件、期望输出和验收方式。
- 证据边界：围绕“When to Use / Workflow / Step 1: Understand User Intent”读取原文规则，不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断：确认你的需求是否属于代码实现、重构、调试或代码审查，并标出输入、限制和预期结果。
- **02** 执行计划：优先按“When to Use / Workflow / Step 1: Understand User Intent”拆成步骤，说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果：给出可复制的命令、文件改动、检查清单或内容草稿，并说明如何继续迭代。
- **04** 风险边界：结合 读取文件、写入/修改文件、主要在本地完成、通常不需要额外 API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件；主要在本地完成；通常不需要额外 API Key。
- 先小样例验证，再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。原文没有稳定的斜杠命令要求。安装验证后通常全局生效，直接在对话里点名这个 Skill 并描述任务即可。
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是：读取文件、写入/修改文件。
先用一个小任务确认它会围绕“When to Use / Workflow / Step 1: Understand User Intent”工作；涉及文件或命令时，先看 diff、日志、预览或测试结果。
检查最终产物是否包含明确结果、必要证据和下一步动作；如果输出泛泛而谈，就补充输入、边界和验收标准后重跑。
---
name: skill-from-github
description: Create skills by learning from high-quality GitHub projects When users want to accomplish someth…
category: 工程开发
source: GBSOSS/skill-from-masters
---
# skill-from-github
## 什么时候使用
- 把工程方向的常用动作沉淀成 Agent 可调用的技能 适合处理工程开发场景下的代码实现、调试、重构、测试或代码审查，核心价值是把输入、判断、执行、验证和交付边界固定下来，避免 Agent 泛泛回答。 把任务拆成可执行、可检查、可继续迭代…
- 面向代码实现、重构、调试或代码审查，优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「When to Use / Workflow / Step 1: Understand User Intent」组织步骤，不把推断写成作者事实。
- 读取文件、写入/修改文件；主要在本地完成；通常不需要额外 API Key。
- 先跑小样例，确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown，不编造命令、平台或依赖。作者原文负责流程事实；仓库文件负责来源和命令；流狐只补充适用场景、限制和质量判断。
skill "skill-from-github" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> When to Use / Workflow / Step 1: Understand User Intent
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> 无特殊运行时 | 读取文件、写入/修改文件 | 主要在本地完成
安全层 -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
}Skill from GitHub
When users want to accomplish something, search GitHub for quality projects that solve the problem, understand them deeply, then create a skill based on that knowledge.
When to Use
When users describe a task and you want to find existing tools/projects to learn from:
- "I want to be able to convert markdown to PDF"
- "Help me analyze sentiment in customer reviews"
- "I need to generate API documentation from code"
Workflow
Step 1: Understand User Intent
Clarify what the user wants to achieve:
- What is the input?
- What is the expected output?
- Any constraints (language, framework, etc.)?
Step 2: Search GitHub
Search for projects that solve this problem:
{task keywords} language:{preferred} stars:>100 sort:starsSearch tips:
- Start broad, then narrow down
- Try different keyword combinations
- Include "cli", "tool", "library" if relevant
Quality filters (must meet ALL):
- Stars > 100 (community validated)
- Updated within last 12 months (actively maintained)
- Has README with clear documentation
- Has actual code (not just awesome-list)
Step 3: Present Options to User
Show top 3-5 candidates:
## Found X projects that can help
### Option 1: [project-name](github-url)
- Stars: xxx | Last updated: xxx
- What it does: one-line description
- Why it's good: specific strength
### Option 2: ...
Which one should I dive into? Or should I search differently?Wait for user confirmation before proceeding.
Step 4: Deep Dive into Selected Project
Once user selects a project, thoroughly understand it:
- Read README - Understand purpose, features, usage
- Read core source files - Understand how it works
- Check examples - See real usage patterns
- Note dependencies - What it relies on
- Identify key concepts - The mental model behind it
Extract:
- Core algorithm/approach
- Input/output formats
- Error handling patterns
- Best practices encoded in the code
Step 5: Summarize Understanding
Present what you learned to user:
## Understanding [project-name]
### Core Approach
How it solves the problem...
### Key Techniques
1. ...
2. ...
### Limitations
- ...
### What I'll encode in the skill
- ...
Does this look right? Should I proceed to create the skill?Wait for user confirmation.
Step 6: Create Skill via skill-creator
Hand off to skill-creator with:
- Clear purpose - What the skill does
- Methodology - The approach learned from the project
- Step-by-step process - Concrete instructions
- Quality criteria - What good output looks like
- Common pitfalls - What to avoid (learned from project issues/docs)
Important: The skill should encode the knowledge from the project, not just wrap the tool. The skill should work even without the original project installed.
Example
User: "I want to write better commit messages"
Step 2 - Search:
commit message convention stars:>100 sort:starsStep 3 - Present:
## Found 4 projects
### Option 1: conventional-commits/conventionalcommits.org (4.2k ⭐)
- Specification for human and machine readable commit messages
- Why: Industry standard, used by Angular, Vue, etc.
### Option 2: commitizen/cz-cli (15k ⭐)
- CLI tool for creating conventional commits
- Why: Battle-tested, lots of adapters
### Option 3: carloscuesta/gitmoji (14k ⭐)
- Emoji guide for commit messages
- Why: Visual, fun approach
Which one interests you?User: "Let's go with conventional commits"
Step 4 - Deep dive:
- Read the specification
- Understand types (feat, fix, docs, etc.)
- Learn about scopes, breaking changes
- Study real-world examples
Step 5 - Summarize:
## Understanding Conventional Commits
### Core Approach
Structured format: <type>(<scope>): <description>
### Key Types
- feat: new feature
- fix: bug fix
- docs: documentation
- ...
### Benefits Learned
- Automated changelog generation
- Semantic versioning
- Clear history
Ready to create a commit message skill based on this?Step 6 - Create skill with these principles encoded
Important Notes
- Always get user confirmation - At step 3 (project selection) and step 5 (before creating)
- Prefer learning over wrapping - Encode the knowledge, not just "run this tool"
- Check license - Mention if project has restrictive license
- Credit the source - Include attribution in generated skill
- Quality over speed - Take time to truly understand the project
What This Skill is NOT
- NOT a package installer
- NOT a tool wrapper
- It's about learning from the best projects and encoding that knowledge into a reusable skill
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核