Back to Details

extract

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

/si:extract — Create Skills from Patterns

/si:extract — 从模式创建Skill

Transforms a recurring pattern or debugging solution into a standalone, portable skill that can be installed in any project.
将重复出现的模式或调试解决方案转换为可独立移植的Skill，可在任何项目中安装。

Usage

使用方法

/si:extract <pattern description>                  # Interactive extraction
/si:extract <pattern> --name docker-m1-fixes       # Specify skill name
/si:extract <pattern> --output ./skills/            # Custom output directory
/si:extract <pattern> --dry-run                     # Preview without creating files
/si:extract <pattern description>                  # 交互式提取
/si:extract <pattern> --name docker-m1-fixes       # 指定Skill名称
/si:extract <pattern> --output ./skills/            # 自定义输出目录
/si:extract <pattern> --dry-run                     # 预览而不创建文件

When to Extract

何时提取

A learning qualifies for skill extraction when ANY of these are true:
CriterionSignal
RecurringSame issue across 2+ projects
Non-obviousRequired real debugging to discover
Broadly applicableNot tied to one specific codebase
Complex solutionMulti-step fix that's easy to forget
User-flagged"Save this as a skill", "I want to reuse this"
当满足以下任一条件时，就可以将经验提炼为Skill：
标准信号
重复出现2个以上项目中出现相同问题
非显而易见需要实际调试才能发现
广泛适用不绑定到特定代码库
解决方案复杂多步骤修复，容易遗忘
用户标记“将这个保存为Skill”、“我想复用这个”

Workflow

工作流程

Step 1: Identify the pattern

步骤1：识别模式

Read the user's description. Search auto-memory for related entries:
bash
MEMORY_DIR="$HOME/.claude/projects/$(pwd | sed 's|/|%2F|g; s|%2F|/|; s|^/||')/memory"
grep -rni "<keywords>" "$MEMORY_DIR/"
If found in auto-memory, use those entries as source material. If not, use the user's description directly.
阅读用户描述。在自动记忆中搜索相关条目：
bash
MEMORY_DIR="$HOME/.claude/projects/$(pwd | sed 's|/|%2F|g; s|%2F|/|; s|^/||')/memory"
grep -rni "<keywords>" "$MEMORY_DIR/"
如果在自动记忆中找到，使用这些条目作为源材料。如果没有，直接使用用户描述。

Step 2: Determine skill scope

步骤2：确定Skill范围

Ask (max 2 questions):
  • "What problem does this solve?" (if not clear)
  • "Should this include code examples?" (if applicable)
最多问2个问题：
  • “这解决了什么问题？”（如果不明确）
  • “是否应包含代码示例？”（如果适用）

Step 3: Generate skill name

步骤3：生成Skill名称

Rules for naming:
  • Lowercase, hyphens between words
  • Descriptive but concise (2-4 words)
  • Examples: 
    docker-m1-fixes
    , 
    api-timeout-patterns
    , 
    pnpm-workspace-setup
命名规则：
  • 小写，单词间用连字符连接
  • 描述性但简洁（2-4个单词）
  • 示例：
    docker-m1-fixes
    , 
    api-timeout-patterns
    , 
    pnpm-workspace-setup

Step 4: Create the skill files

步骤4：创建Skill文件

Spawn the 
skill-extractor
agent for the actual file generation.
The agent creates:
<skill-name>/
├── SKILL.md            # Main skill file with frontmatter
├── README.md           # Human-readable overview
└── reference/          # (optional) Supporting documentation
    └── examples.md     # Concrete examples and edge cases
启动
skill-extractor
Agent 来实际生成文件。
Agent会创建：
<skill-name>/
├── SKILL.md            # 包含前置元数据的主Skill文件
├── README.md           # 人类可读的概述
└── reference/          # (可选) 支持文档
    └── examples.md     # 具体示例和边缘情况

Step 5: SKILL.md structure

步骤5：SKILL.md结构

The generated SKILL.md must follow this format:
markdown
---
name: <skill-name>
description: "<one-line description>. Use when: <trigger conditions>."
---
生成的SKILL.md必须遵循以下格式：
markdown
---
name: <skill-name>
description: "<一行描述>。适用场景：<触发条件>。"
---

<Skill Title>

<Skill标题>

One-line summary of what this skill solves.
关于此Skill解决问题的一行摘要。

Quick Reference

快速参考

ProblemSolution
{{problem 1}}{{solution 1}}
{{problem 2}}{{solution 2}}
问题解决方案
{{problem 1}}{{solution 1}}
{{problem 2}}{{solution 2}}

The Problem

问题说明

{{2-3 sentences explaining what goes wrong and why it's non-obvious.}}
{{2-3句话解释问题是什么以及为什么它非显而易见。}}

Solutions

解决方案

Option 1: {{Name}} (Recommended)

选项1：{{名称}}（推荐）

{{Step-by-step with code examples.}}
{{带代码示例的分步说明。}}

Option 2: {{Alternative}}

选项2：{{替代方案}}

{{For when Option 1 doesn't apply.}}
{{当选项1不适用时的方案。}}

Trade-offs

权衡对比

ApproachProsCons
Option 1{{pros}}{{cons}}
Option 2{{pros}}{{cons}}
方法优点缺点
选项1{{pros}}{{cons}}
选项2{{pros}}{{cons}}

Edge Cases

边缘情况

  • {{edge case 1 and how to handle it}}
  • {{edge case 2 and how to handle it}}
undefined
  • {{边缘情况1及其处理方法}}
  • {{边缘情况2及其处理方法}}
undefined

Step 6: Quality gates

步骤6：质量检查

Before finalizing, verify:
  • SKILL.md has valid YAML frontmatter with 
    name
    and 
    description
  • name
    matches the folder name (lowercase, hyphens)
  • Description includes "Use when:" trigger conditions
  • Solutions are self-contained (no external context needed)
  • Code examples are complete and copy-pasteable
  • No project-specific hardcoded values (paths, URLs, credentials)
  • No unnecessary dependencies
最终确定前，验证以下内容：
  • SKILL.md包含有效的YAML前置元数据，带有
    name
    和
    description
  • name
    与文件夹名称匹配（小写，连字符连接）
  • 描述中包含“适用场景：”触发条件
  • 解决方案是自包含的（无需外部上下文）
  • 代码示例完整且可直接复制粘贴
  • 没有项目特定的硬编码值（路径、URL、凭证）
  • 没有不必要的依赖

Step 7: Report

步骤7：报告

✅ Skill extracted: {{skill-name}}

Files created:
  {{path}}/SKILL.md          ({{lines}} lines)
  {{path}}/README.md         ({{lines}} lines)
  {{path}}/reference/examples.md  ({{lines}} lines)

Install: /plugin install (copy to your skills directory)
Publish: clawhub publish {{path}}

Source: MEMORY.md entries at lines {{n, m, ...}} (retained — the skill is portable, the memory is project-specific)
✅ Skill已提取：{{skill-name}}

已创建文件：
  {{path}}/SKILL.md          ({{lines}} 行)
  {{path}}/README.md         ({{lines}} 行)
  {{path}}/reference/examples.md  ({{lines}} 行)

安装：/plugin install（复制到你的skills目录）
发布：clawhub publish {{path}}

来源：MEMORY.md中第{{n, m, ...}}行的条目（已保留 — Skill是可移植的，记忆是项目特定的）

Examples

示例

Extracting a debugging pattern

提取调试模式

/si:extract "Fix for Docker builds failing on Apple Silicon with platform mismatch"
Creates 
docker-m1-fixes/SKILL.md
with:
  • The platform mismatch error message
  • Three solutions (build flag, Dockerfile, docker-compose)
  • Trade-offs table
  • Performance note about Rosetta 2 emulation
/si:extract "Fix for Docker builds failing on Apple Silicon with platform mismatch"
创建
docker-m1-fixes/SKILL.md
，包含：
  • 平台不匹配的错误消息
  • 三种解决方案（构建标志、Dockerfile、docker-compose）
  • 权衡对比表
  • 关于Rosetta 2模拟的性能说明

Extracting a workflow pattern

提取工作流模式

/si:extract "Always regenerate TypeScript API client after modifying OpenAPI spec"
Creates 
api-client-regen/SKILL.md
with:
  • Why manual regen is needed
  • The exact command sequence
  • CI integration snippet
  • Common failure modes
/si:extract "Always regenerate TypeScript API client after modifying OpenAPI spec"
创建
api-client-regen/SKILL.md
，包含：
  • 为什么需要手动重新生成
  • 确切的命令序列
  • CI集成代码片段
  • 常见失败模式

Tips

提示

  • Extract patterns that would save time in a different project
  • Keep skills focused — one problem per skill
  • Include the error messages people would search for
  • Test the skill by reading it without the original context — does it make sense?
  • 提取能在其他项目中节省时间的模式
  • 保持Skill聚焦 — 一个Skill解决一个问题
  • 包含人们会搜索的错误消息
  • 通过脱离原始上下文阅读来测试Skill — 它是否有意义？