Back to Details

skill-from-notebook

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Skill from Notebook

基于NotebookLM生成Skill

Extract actionable methodologies from learning materials (documents, articles, videos) or quality examples (blog posts, designs, code) to generate reusable Skills.
Core Philosophy: NotebookLM helps you understand. This skill helps you do.
从学习材料（文档、文章、视频）或优质示例（博客文章、设计、代码）中提取可落地的方法论，以生成可复用的Skill。
核心理念：NotebookLM帮助你理解知识，而本Skill帮助你实践。

When to Use

使用场景

When users want to turn knowledge into executable skills:
  • "I just read this article about code review, help me create a skill from it"
  • "Here's a great technical blog post, extract the writing methodology"
  • "Turn this PDF guide into a skill I can reuse"
  • "Learn from this example and create a skill to produce similar output"
当用户希望将知识转化为可执行的Skill时：
  • "我刚读了一篇关于代码评审的文章，帮我从中创建一个Skill"
  • "这是一篇很棒的技术博客，提取它的写作方法论"
  • "把这份PDF指南转化为我可以复用的Skill"
  • "从这个示例中学习，创建一个能生成类似输出的Skill"

Supported Input Types

支持的输入类型

TypeHow to Process
Local filesPDF, Word, Markdown - Read directly
Web URLWebFetch to extract content
YouTubeUse yt-dlp for subtitles, Whisper if unavailable
NotebookLM linkBrowser automation to extract notes/summaries
Example/OutputReverse engineer the methodology
类型处理方式
本地文件直接读取PDF、Word、Markdown文件
网页URL使用WebFetch提取内容
YouTube优先用yt-dlp获取字幕，无字幕时使用Whisper
NotebookLM链接通过浏览器自动化提取笔记/摘要
示例/输出成果逆向推导方法论

Step 0: Identify Input Type

步骤0：确定输入类型

Critical first step - Determine which processing path to use:
User Input
    │
    ├─ Has teaching intent? ("how to", "steps", "guide")
    │   └─ YES → Path A: Methodology Document
    │
    ├─ Is a finished work? (article, design, code, proposal)
    │   └─ YES → Path B: Example (Reverse Engineering)
    │
    └─ Neither? → Tell user this content is not suitable
Path A indicators (Methodology Document):
  • Contains words like "how to", "steps", "method", "guide"
  • Has numbered lists or step sequences
  • Written with teaching intent
  • Describes "what to do"
Path B indicators (Example/Output):
  • Is a complete work/artifact
  • No teaching intent
  • Is "the thing itself" rather than "how to make the thing"
  • Examples: a well-written blog post, a polished proposal, a code project
关键第一步 - 确定要使用的处理路径：
用户输入
    │
    ├─ 是否具有教学意图？（包含"how to"、"steps"、"guide"等词汇）
    │   └─ 是 → 路径A：方法论文档
    │
    ├─ 是否为成品？（文章、设计、代码、提案等）
    │   └─ 是 → 路径B：示例（逆向工程）
    │
    └─ 都不是？ → 告知用户该内容不适用
路径A的判定指标（方法论文档）：
  • 包含"how to"、"steps"、"method"、"guide"等词汇
  • 带有编号列表或步骤序列
  • 以教学为创作目的
  • 描述了"要做什么"
路径B的判定指标（示例/输出成果）：
  • 是完整的作品/成果物
  • 无教学意图
  • 是"事物本身"而非"如何制作事物"
  • 示例：一篇优秀的博客文章、一份打磨后的提案、一个代码项目

Path A: Extract from Methodology Document

路径A：从方法论文档提取

A1: Validate Document Suitability

A1：验证文档适用性

Check if the document is suitable for skill generation (must meet at least 2):
  • Has clear goal/outcome
  • Has repeatable steps/process
  • Has quality criteria
  • Has context/scenario description
If not suitable: Tell user honestly and explain why.
检查文档是否适合生成Skill（需满足至少2项）：
  • 有明确的目标/成果
  • 包含可重复的步骤/流程
  • 有质量判定标准
  • 有适用场景/上下文描述
若不适用：如实告知用户并说明原因。

A2: Identify Skill Type

A2：确定Skill类型

TypeCharacteristicsExamples
How-toClear step sequence, input→outputDeploy Docker, Configure CI/CD
DecisionConditions, trade-offs, choicesChoose database, Select framework
FrameworkMental model, analysis dimensionsSWOT, 5W1H, First Principles
ChecklistVerification list, pass/fail criteriaCode review checklist, Launch checklist
类型特征示例
操作指南型清晰的步骤序列，输入→输出明确部署Docker、配置CI/CD
决策型包含条件、权衡、选择数据库选型、框架选择
框架模型型心智模型、分析维度SWOT、5W1H、第一性原理
检查清单型验证列表、通过/不通过标准代码评审检查清单、上线检查清单

A3: Extract Structure by Type

A3：按类型提取结构

For How-to:
  • Prerequisites
  • Step sequence (with expected output per step)
  • Final expected result
  • Common errors
For Decision:
  • Decision factors
  • Options with pros/cons
  • Decision tree/flowchart
  • Recommended default
For Framework:
  • Core concepts
  • Analysis dimensions
  • Application method
  • Limitations
For Checklist:
  • Check items with criteria
  • Priority levels
  • Commonly missed items
操作指南型：
  • 前置条件
  • 步骤序列（含每步预期输出）
  • 最终预期结果
  • 常见错误
决策型：
  • 决策因素
  • 各选项的优缺点
  • 决策树/流程图
  • 推荐默认选项
框架模型型：
  • 核心概念
  • 分析维度
  • 应用方法
  • 局限性
检查清单型：
  • 带判定标准的检查项
  • 优先级层级
  • 常被遗漏的项

A4: Generate Skill

A4：生成Skill

Use this template:
markdown
undefined
使用以下模板：
markdown
undefined

Applicable Scenarios

适用场景

[When to use this skill]
[何时使用该Skill]

Prerequisites

前置条件

  • [What's needed before starting]
  • [开始前需要准备的内容]

Steps

步骤

  1. [Step 1] - [Expected outcome]
  2. [Step 2] - [Expected outcome] ...
  1. [步骤1] - [预期成果]
  2. [步骤2] - [预期成果] ...

Quality Checkpoints

质量检查点

  • [Checkpoint 1]
  • [Checkpoint 2]
  • [检查点1]
  • [检查点2]

Common Pitfalls

常见陷阱

  • [Pitfall 1]: [How to avoid]
  • [陷阱1]：[如何避免]

Source

来源

  • Document: [name/URL]
  • Extracted: [timestamp]

---
  • 文档：[名称/URL]
  • 提取时间：[时间戳]

---

Path B: Reverse Engineer from Example

路径B：从示例逆向推导

When input is a finished work (not a tutorial), reverse engineer the methodology.
当输入为成品（非教程类内容）时，逆向推导其方法论。

B1: Identify Output Type

B1：确定输出类型

What kind of artifact is this?
  • Technical blog post
  • Product proposal/PRD
  • Academic paper
  • Code architecture
  • Design document
  • Other: [specify]
这是什么类型的成果物？
  • 技术博客文章
  • 产品提案/PRD
  • 学术论文
  • 代码架构
  • 设计文档
  • 其他：[具体说明]

B2: Analyze Structure

B2：分析结构

Break down the example:
Structure Analysis:
├── [Part 1]: [Function] - [Proportion %]
├── [Part 2]: [Function] - [Proportion %]
├── [Part 3]: [Function] - [Proportion %]
└── [Part N]: [Function] - [Proportion %]
Questions to answer:
  • How many parts does it have?
  • What's the function of each part?
  • What's the order and proportion?
拆解示例：
结构分析：
├── [部分1]：[功能] - [占比%]
├── [部分2]：[功能] - [占比%]
├── [部分3]：[功能] - [占比%]
└── [部分N]：[功能] - [占比%]
需要回答的问题：
  • 包含多少个部分？
  • 每个部分的功能是什么？
  • 各部分的顺序和占比如何？

B3: Extract Quality Characteristics

B3：提取质量特征

What makes this example good?
DimensionQuestions
StructureHow is content organized?
StyleTone, word choice, expression?
TechniqueWhat methods make it effective?
LogicHow does information flow?
DetailsSmall but important touches?
是什么让这个示例如此优秀？
维度问题
结构内容如何组织？
风格语气、用词、表达方式？
技巧哪些方法使其有效？
逻辑信息如何流转？
细节有哪些重要的小细节？

B4: Reverse Engineer the Process

B4：逆向推导流程

Deduce: To create this output, what steps are needed?
markdown
undefined
推断：要生成此类输出，需要哪些步骤？
markdown
undefined

Deduced Production Steps

推导的制作步骤

  1. [Step 1]: [What to do] - [Key point]
  2. [Step 2]: [What to do] - [Key point] ...
  1. [步骤1]：[要做什么] - [关键点]
  2. [步骤2]：[要做什么] - [关键点] ...

Key Decisions

关键决策

  • [Decision 1]: [Options] - [This example chose X because...]
  • [决策1]：[可选方案] - [本示例选择X的原因是...]

Reusable Techniques

可复用技巧

  • [Technique 1]: [How to apply]
  • [Technique 2]: [How to apply]
undefined
  • [技巧1]：[如何应用]
  • [技巧2]：[如何应用]
undefined

B5: Generate Skill

B5：生成Skill

Use this template for reverse-engineered skills:
markdown
undefined
使用以下模板生成逆向推导的Skill：
markdown
undefined

Output Type

输出类型

[What kind of artifact this produces]
[该Skill可生成的成果物类型]

Applicable Scenarios

适用场景

[When to create this type of output]
[何时需要创建此类输出]

Structure Template

结构模板

  1. [Part 1]: [Function] - [~X%]
  2. [Part 2]: [Function] - [~X%] ...
  1. [部分1]：[功能] - [约X%]
  2. [部分2]：[功能] - [约X%] ...

Quality Characteristics (Learned from Example)

从示例中学到的质量特征

  • [Characteristic 1]: [How it manifests]
  • [Characteristic 2]: [How it manifests]
  • [特征1]：[具体表现]
  • [特征2]：[具体表现]

Production Steps

制作步骤

  1. [Step 1]: [What to do] - [Tips]
  2. [Step 2]: [What to do] - [Tips] ...
  1. [步骤1]：[要做什么] - [提示]
  2. [步骤2]：[要做什么] - [提示] ...

Checklist

检查清单

  • [Check item 1]
  • [Check item 2]
  • [检查项1]
  • [检查项2]

Reference Example

参考示例

  • Source: [name/URL]
  • Analyzed: [timestamp]

---
  • 来源：[名称/URL]
  • 分析时间：[时间戳]

---

Example: Path A (Methodology Document)

示例：路径A（方法论文档）

User: "Extract a skill from this article about writing good commit messages"
Process:
  1. Read the article
  2. Identify: This is a How-to type (has steps, teaching intent)
  3. Extract:
    • Goal: Write clear, useful commit messages
    • Steps: Use conventional format, separate subject/body, etc.
    • Quality criteria: Subject < 50 chars, imperative mood, etc.
  4. Generate skill with steps and checklist
用户：“从这篇关于撰写优质提交信息的文章中提取一个Skill”
流程：
  1. 阅读文章
  2. 判定：这是操作指南型Skill（包含步骤，有教学意图）
  3. 提取内容：
    • 目标：撰写清晰、有用的提交信息
    • 步骤：使用规范格式、分离主题与正文等
    • 质量标准：主题不超过50字符、使用祈使语气等
  4. 结合步骤和检查清单生成Skill

Example: Path B (Reverse Engineering)

示例：路径B（逆向工程）

User: "Here's a great technical blog post. Learn from it and create a skill for writing similar posts."
Process:
  1. Identify: This is an example (finished work, no teaching intent)
  2. Analyze structure: 
    ├── Hook: Real pain point (2-3 sentences)
├── Problem: 3 sentences on the core issue
├── Solution: Conclusion first, then details
├── Code: Each snippet < 20 lines, with comments
├── Pitfalls: 3 common errors
└── Summary: One-line takeaway
  3. Extract quality characteristics:
    • Title = specific tech + problem solved
    • One idea per paragraph
    • Code:text ratio ~40:60
    • Personal anecdotes for credibility
  4. Reverse engineer steps:
    • Start with a real problem you solved
    • Write the solution first, then the setup
    • Add code samples progressively
    • etc.
  5. Generate skill: "How to Write a Technical Blog Post"
用户：“这是一篇很棒的技术博客。从中学习并创建一个撰写同类博客的Skill。”
流程：
  1. 判定：这是一个示例（成品，无教学意图）
  2. 分析结构： 
    ├── 钩子：真实痛点（2-3句话）
├── 问题：用3句话阐述核心问题
├── 解决方案：先给出结论，再展开细节
├── 代码：每个代码片段不超过20行，带注释
├── 常见陷阱：3个常见错误
└── 总结：一句话核心要点
  3. 提取质量特征：
    • 标题 = 具体技术点 + 解决的问题
    • 每段只讲一个观点
    • 代码与文本比例约40:60
    • 加入个人经历提升可信度
  4. 逆向推导步骤：
    • 从你解决过的真实问题入手
    • 先写解决方案，再补充背景
    • 逐步添加代码示例
    • 等等
  5. 生成Skill：“如何撰写技术博客文章”

Advanced: Multi-Example Learning

进阶：多示例学习

When user provides multiple examples of the same type:
Example A ──┐
Example B ──┼──> Extract commonalities ──> Core methodology
Example C ──┘           │
                        ▼
                  Analyze differences ──> Style variants / Optional techniques
This produces more robust, generalizable skills.
当用户提供多个同类型示例时：
示例A ──┐
示例B ──┼──> 提取共性 ──> 核心方法论
示例C ──┘           │
                        ▼
                  分析差异 ──> 风格变体 / 可选技巧
这种方式生成的Skill更健壮、更具通用性。

Important Notes

重要注意事项

  1. Always validate first - Not all content is suitable for skill extraction
  2. Identify the path early - Methodology doc vs Example require different approaches
  3. Be specific - Vague skills are useless; include concrete steps and criteria
  4. Preserve the source - Always credit where the knowledge came from
  5. Ask for clarification - If unsure about user intent, ask before proceeding
  6. Quality over speed - Take time to truly understand the content
  1. 始终先验证 - 并非所有内容都适合提取Skill
  2. 尽早确定路径 - 方法论文档与示例需要不同的处理方式
  3. 内容要具体 - 模糊的Skill毫无用处；需包含具体步骤和判定标准
  4. 保留来源信息 - 始终注明知识的来源
  5. 及时请求澄清 - 若不确定用户意图，先询问再继续
  6. 质量优先于速度 - 花时间真正理解内容

What This Skill is NOT

本Skill不具备的能力

  • NOT a summarizer (that's NotebookLM's job)
  • NOT a document converter
  • It's about extracting actionable methodology that can be repeatedly executed
  • 不是摘要生成工具（这是NotebookLM的工作）
  • 不是文档转换器
  • 它专注于提取可落地的方法论，以便重复执行