跳到主内容
智客 ZICQ

技能库 智客分类:Agent 工作流 create-skill

Create Skill

遵循最佳做法创造有效技能指南。 在创建或更新扩展代理能力的技能时使用.

2798 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

采用最佳做法创造有效技能指南

何时用

创建或更新能够扩展代理能力的技能

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Create Skill、About Skills、What Skills Provide、Progressive Disclosure Principle、Three-Level Loading System、Why Progressive Disclosure Matters。

文件分析

文件分析:除 SKILL.md 外,正文引用了 references/progressive-disclosure.md、references/skill-structure.md、references/examples.md、references/best-practices.md,属于带资源的技能包,这些文件按需再读。

官方 description(原文)

Guide for creating effective skills following best practices. Use when creating or updating skills that extend agent capabilities.

Create SkillAbout SkillsWhat Skills ProvideProgressive Disclosure PrincipleThree-Level Loading SystemWhy Progressive Disclosure MattersSkill StructureCore PrinciplesConcise is KeySet Appropriate Degrees of FreedomTest with All ModelsReferences

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
create-skill
description
Guide for creating effective skills following best practices. Use when creating or updating skills that extend agent capabilities.
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。
指令中引用的文件 · 4
  • references/progressive-disclosure.md
  • references/skill-structure.md
  • references/examples.md
  • references/best-practices.md

以下路径提取自原文;文件是否齐全请以来源仓库中的完整目录为准。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

该技能引用了附属文件,请从来源获取完整目录;仅复制 SKILL.md 可能缺少依赖。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「create-skill」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-6759729cb3f07c8c-%E5%88%9B%E5%BB%BA%E6%8A%80%E8%83%BD.html
请存为 .cursor/skills/create-skill/SKILL.md 或 .claude/skills/create-skill/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
该技能还带 scripts/、references/、assets/ 等文件,请从 https://github.com/siviter-xyz/dot-agent 取完整目录,不要只建一个 SKILL.md。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/siviter-xyz/dot-agent' --list

npx skills add 'https://github.com/siviter-xyz/dot-agent' --skill 'create-skill'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版

name: create-skill description: Guide for creating effective skills following best practices. Use when creating or updating skills that extend agent capabilities.

Create Skill

Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, and tool integrations.

About Skills

Skills are modular, self-contained packages that extend agent capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks.

What Skills Provide

  1. Specialized workflows - Multi-step procedures for specific domains
  2. Tool integrations - Instructions for working with specific file formats or APIs
  3. Domain expertise - Company-specific knowledge, schemas, business logic
  4. Bundled resources - Scripts, references, and assets for complex and repetitive tasks

Progressive Disclosure Principle

The 200-line rule is critical. SKILL.md must be under 200 lines. If you need more, split content into references/ files.

Three-Level Loading System

  1. Metadata (name + description) - Always in context (~100 words)
  2. SKILL.md body - When skill triggers (<200 lines, ideally <500 lines for optimal performance)
  3. Bundled resources - As needed by agent (unlimited)

Why Progressive Disclosure Matters

  • 85% reduction in initial context load
  • Activation times drop from 500ms+ to under 100ms
  • Agent loads only what's needed, when it's needed
  • Skills remain maintainable and focused

Skill Structure

skill-name/
├── SKILL.md (required, <200 lines)
│   ├── YAML frontmatter metadata (required)
│   │   ├── name: (required)
│   │   └── description: (required)
│   └── Markdown instructions (required)
└── Bundled Resources (optional)
    ├── scripts/          - Executable code
    ├── references/       - Documentation loaded as needed
    └── assets/           - Files used in output

Core Principles

Concise is Key

The context window is a shared resource. Your skill shares it with everything else the agent needs. Be concise and challenge each piece of information:

  • Does the agent really need this explanation?
  • Can I assume the agent knows this?
  • Does this paragraph justify its token cost?

Set Appropriate Degrees of Freedom

  • High freedom: Text-based instructions for multiple valid approaches
  • Medium freedom: Pseudocode or scripts with parameters
  • Low freedom: Specific scripts with few/no parameters for fragile operations

Test with All Models

Skills act as additions to models, so effectiveness depends on the underlying model. Test your skill with all models you plan to use it with.

References

For detailed guidance, see:

  • references/progressive-disclosure.md - 200-line rule and references pattern
  • references/skill-structure.md - SKILL.md format and frontmatter details
  • references/examples.md - Good skill examples
  • references/best-practices.md - Comprehensive best practices guide

相关技能

Agent 工作流

Skill Creator

创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.

Agent 工作流

Clawdhub

使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.

Agent 工作流

Agent Team Orchestration

管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.

Agent 工作流

Superpowers

Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…