Token导航 LogoToken导航

Agent Skill · 研究检索

skill-creator(技能创建器)

skill-creator 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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。

skill-creator 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为调用外部服务;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 45,360。

总安装 855周安装 36GitHub Stars 5下载 247核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

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/breverdbidder/life-os
仓库路径:skills/skill-creator
安装命令:
npx skills add https://github.com/breverdbidder/life-os --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/breverdbidder/life-os --skill skill-creator

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

交互式创建和优化 Claude 技能,提供结构化模板和最佳实践指南。包含 YAML 元数据、Markdown 说明和测试用例生成等必要组件。适用于希望扩展 Agent 功能的开发者,支持迭代改进和性能评估。使用前需准备技能描述和测试提示词,运行验证确保功能达标。输出结果应保留原始路径和命令,避免引入未经验证的依赖项。

来源仓库内路径:skills/skill-creator

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/breverdbidder/life-os --skill skill-creator;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要调用外部服务,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

skill-creator 怎么安装?

在终端执行 npx skills add https://github.com/breverdbidder/life-os --skill skill-creator。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

skill-creator 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

skill-creator 需要什么权限?

权限级别是调用外部服务。该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

skill-creator 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

skill-creator 用的人多吗?

公开数据是累计安装 855 次,近一周安装 36 次,下载 247 次,GitHub 5 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

skill-creator 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
skill-creator

技能创建器 · 本页

8555调用外部服务未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Skill Creator

Interactive guide for creating high-quality Claude skills.

When to Use This Skill

Use this skill when:

  • User wants to create a new Claude skill
  • User wants to update or improve an existing skill
  • User needs guidance on skill structure and best practices
  • User wants to extend Claude's capabilities for specific workflows

Skill Structure

Every skill consists of a required SKILL.md file and optional bundled resources:

skill-name/
├── SKILL.md (required)
│   ├── YAML frontmatter metadata (required)
│   │   ├── name: (required)
│   │   └── description: (required)
│   └── Markdown instructions (required)
└── Bundled Resources (optional)
    ├── scripts/ - Executable code (Python/Bash/etc.)
    ├── references/ - Documentation loaded into context as needed
    └── assets/ - Files used in output (templates, icons, fonts, etc.)

Required Components

Frontmatter (YAML)

---
name: my-skill-name
description: A clear, comprehensive description of what this skill does and when to use it
---

Critical: The description field is how Claude determines when to use the skill. Be specific and comprehensive about:

  • What the skill does
  • When it should be used
  • What types of queries trigger it
  • What output it produces

Body (Markdown)

The markdown content contains:

  • Instructions: Step-by-step guidance for using the skill
  • Examples: Concrete usage examples
  • Guidelines: Best practices and rules
  • Workflows: Detailed procedures

Optional Bundled Resources

1. scripts/

When to include: When the skill needs executable code

Examples:

  • scripts/analyzer.py - Python data analysis script
  • scripts/formatter.sh - Bash formatting utility
  • scripts/validator.js - JavaScript validation tool

Rules:

  • Must be tested before inclusion
  • Should be well-documented
  • Include error handling

2. references/

When to include: When the skill needs detailed reference material that shouldn't bloat SKILL.md

Examples:

  • references/schema.md - Database schema documentation
  • references/api-spec.md - API endpoint reference
  • references/examples.md - Extended examples

Rules:

  • Move detailed info here, keep SKILL.md lean
  • Avoid duplication between SKILL.md and references/
  • Use for schemas, specs, detailed examples

3. assets/

When to include: When the skill needs files used in output

Examples:

  • assets/logo.png - Brand assets
  • assets/template.pptx - PowerPoint templates
  • assets/boilerplate/ - HTML/React starter code
  • assets/fonts/ - Custom typography

Rules:

  • Only for files used in final output
  • Not for documentation (use references/ instead)
  • Templates, images, icons, boilerplate code

Creation Workflow

Step 1: Analyze the Use Case

Ask clarifying questions:

  1. What specific task will this skill handle?
  2. What are 3-5 concrete examples of user queries?
  3. What makes this task repetitive or specialized?
  4. What context or knowledge is required?
  5. Are there existing tools/APIs to integrate?

Step 2: Identify Reusable Resources

For each concrete example, identify:

  • Scripts that would be helpful
  • Reference documentation needed
  • Assets/templates to include

Step 3: Create the Structure

  1. Start with SKILL.md frontmatter
  2. Write clear, comprehensive description
  3. Add instruction sections
  4. Create scripts/ if needed
  5. Add references/ for detailed docs
  6. Include assets/ for templates

Step 4: Test the Skill

  1. Test all scripts to ensure they work
  2. Verify references are complete
  3. Check assets are properly formatted
  4. Validate SKILL.md instructions are clear

Best Practices

Description Writing

✅ Good description: "Analyzes Brevard County foreclosure auctions using 12-stage pipeline. Searches AcclaimWeb for liens, calculates max bid using ARV formula, generates BID/REVIEW/SKIP recommendations. Use when analyzing foreclosure properties, calculating max bids, or generating auction reports."

❌ Bad description: "Helps with foreclosure analysis"

Instruction Writing

  • Be specific and actionable
  • Include concrete examples
  • Define workflows step-by-step
  • Explain when to use vs not use
  • Provide success criteria

Resource Organization

  • Keep SKILL.md focused on procedures
  • Move detailed docs to references/
  • Test all scripts before inclusion
  • Organize assets logically

Common Skill Patterns

1. Domain Expert Skill

Focus: Specialized knowledge in a field Resources: references/ with domain docs, examples Example: foreclosure-analysis, medical-coding

2. Workflow Automation Skill

Focus: Repeatable multi-step processes Resources: scripts/ for automation, templates in assets/ Example: git-workflow, deployment-checklist

3. Integration Skill

Focus: Using external APIs/tools Resources: references/ with API docs, scripts/ for API calls Example: stripe-integration, supabase-setup

4. Template/Boilerplate Skill

Focus: Starting points for projects Resources: assets/ with templates, references/ with docs Example: react-boilerplate, brand-guidelines

Examples

See the following skills as references:

  • frontend-design: Creative workflow with aesthetic guidelines
  • mcp-builder: Technical integration with detailed specs
  • docx: Complex file manipulation with scripts
  • brand-guidelines: Assets and references combination

平台分布

Codex

33.15%
按下载量换算82

Claude

31.51%
按下载量换算78

Cursor

19.4%
按下载量换算48

Gemini CLI

8.86%
按下载量换算22

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

调用外部服务

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

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。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills