Token导航 LogoToken导航TokenDH.com
开发只读github未标认证来源可访问许可证需确认审计通过

skill-creator技能创建器

Agent Skill

skill-creator 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

717

周安装

34

GitHub Stars

公开资料未说明

下载量

280
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:skill-creator(技能创建器)
来源仓库:https://github.com/cylixlee/skills
仓库路径:skills/skill-creator
安装命令:
npx skills add https://github.com/cylixlee/skills --skill skill-creator
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/cylixlee/skills --skill skill-creator

简介

skill-creator 引导创建符合规范的 Agent 技能包。

  • 适用于扩展 Agent 能力、封装专业知识或构建可复用工作流。
  • 每个技能需包含 SKILL.md 与必要元数据,支持跨平台部署。
  • 使用前应熟悉技能目录结构与宿主集成方式,避免格式错误。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Skill Creator

This skill guides the creation of new Agent Skills that conform to the Agent Skills specification. Follow these instructions whenever you need to create a new skill for any capability.

When to Use This Skill

  • User asks to create a new skill
  • User requests adding a skill for a specific capability
  • User wants to define or build a skill
  • User needs to package knowledge or workflows as a reusable skill

Agent Skills Core Concepts

Skills are portable, self-documenting packages that extend AI agent capabilities. Each skill is a directory containing a SKILL.md file with instructions.

For complete specification details, see references/spec.md.

Progressive Disclosure Architecture

Skills use a three-tier loading strategy for efficient context management:

TierWhat is LoadedWhenToken Cost
Catalogname + descriptionSession start~50-100 tokens
InstructionsFull SKILL.md bodySkill activated<5000 tokens recommended
ResourcesScripts, references, assetsWhen referencedVaries

Creating a New Skill

Follow these six steps to create a skill:

Step 1: Determine Skill Purpose

Before creating files, clearly define:

  • What capability does this skill provide?
  • When should an agent use this skill?
  • What keywords would trigger this skill?

Step 2: Create Directory Structure

skill-name/
├── SKILL.md          # Required
├── scripts/          # Optional: executable code
├── references/       # Optional: documentation
└── assets/           # Optional: templates, resources

The directory name must match the skill name.

Step 3: Write Frontmatter

The SKILL.md file must start with YAML frontmatter containing required fields.

Required fields:

  • name: Skill identifier (1-64 characters, lowercase letters and hyphens only)
  • description: What the skill does AND when to use it (1-1024 characters)

Optional fields:

  • license: License name or file
  • compatibility: Environment requirements
  • metadata: Additional key-value pairs
  • allowed-tools: Pre-approved tools (experimental)

For detailed field specifications, see references/frontmatter.md.

Step 4: Write Instruction Content

The Markdown body after frontmatter contains skill instructions. There are no format restrictions, but include:

  • When to use this skill
  • Step-by-step instructions
  • Examples of inputs and outputs
  • Common edge cases

For writing guidelines, see references/content.md.

Step 5: Add Optional Resources

If your skill requires scripts, references, or assets, add them to the appropriate subdirectories:

  • scripts/: Executable code that the skill instructions may invoke
  • references/: Supplementary documentation
  • assets/: Templates, data files, or other resources

For script support details, see references/scripts/overview.md.

Step 6: Validate

Verify your skill follows the specification:

npx skills-ref validate ./skill-name

For validation details, see references/spec.md.

Quick Reference

Valid Name Patterns

Valid:   pdf-processing, data-analysis, code-review
Invalid: PDF-Processing (uppercase), -pdf (starts with hyphen), pdf--processing (consecutive hyphens)

Good Description Example

description: Extracts text and tables from PDF files, fills PDF forms, and merges multiple PDFs. Use when working with PDF documents or when the user mentions PDFs, forms, or document extraction.

Additional Resources

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33%
按下载量换算92

Claude

28.46%
按下载量换算80

Cursor

19.93%
按下载量换算56

Gemini CLI

10.21%
按下载量换算29

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills