Token导航 LogoToken导航TokenDH.com
前端设计需要联网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

198

周安装

8

GitHub Stars

2

下载量

62
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/monkey1sai/openai-cli
仓库路径:skills/skill-creator
安装命令:
npx skills add https://github.com/monkey1sai/openai-cli --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/monkey1sai/openai-cli --skill skill-creator

简介

用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。

  • 适合在需要围绕仓库状态、代码变更或协作事项进行整理时使用。
  • 可结合来源仓库和原始 README 核验具体用法,建议确认权限范围和维护状态。
  • 安装命令:npx skills add https://github.com/monkey1sai/openai-cli --skill skill-creator
  • 适用于 Codex、Claude、Cursor、Gemini CLI,通过 GitHub 安装

SKILL.md

Skill Creator

Generate production-ready Claude Code skills following established conventions.

Core Workflow

  1. Define skill purpose: Clear name, description, and use cases
  2. Determine category: Place in correct folder (foundation, frontend, backend, etc.)
  3. Create SKILL.md: Main skill file with frontmatter and content
  4. Add references: Optional templates.md, conventions.md, or patterns.md
  5. Include examples: Production-ready code samples
  6. Write checklist: Output verification checklist

Skill Categories

CategoryPathPurpose
Foundationfoundation/Project setup, dev environment, git, docs
Frontendfrontend/React, Vue, UI components, styling, UX
Backendbackend/APIs, auth, server logic, services
AI Engineeringai-engineering/LLMs, RAG, agents, prompts
Architecturearchitecture/System design, ADRs, tech decisions
CI/CDci-cd/Automation, deployments, pipelines
Databasedatabase-management/Migrations, queries, data engineering
Testingtesting/Unit tests, integration, e2e, mocks
Securitysecurity/Vulnerabilities, auth, hardening
Performanceperformance/Observability, monitoring, optimization

SKILL.md Template

---
name: skill-name-in-kebab-case
description: One-line description of what the skill does and when to use it. Include trigger phrases like "use when users request X, Y, or Z".
---

# Skill Title

Brief tagline explaining the skill's value proposition.

## Core Workflow

1. **Step one**: Description
2. **Step two**: Description
3. **Step three**: Description
   ...

## [Main Content Sections]

### Section with Code Examples

\`\`\`typescript
// Production-ready code example
\`\`\`

### Patterns / Templates

Document reusable patterns with examples.

## Best Practices

- Practice one
- Practice two
- Practice three

## Output Checklist

Every output should include:

- [ ] Item one
- [ ] Item two
- [ ] Item three

Reference Files Structure

When skills need supplementary documentation:

skill-name/
├── SKILL.md              # Main skill file (required)
└── references/            # Optional reference materials
    ├── templates.md       # Code/file templates
    ├── conventions.md     # Standards and conventions
    └── patterns.md        # Reusable patterns

Frontmatter Requirements

---
name: kebab-case-skill-name # Must match folder name
description: >
  Clear description including:
  - What the skill does
  - When to use it
  - Trigger phrases ("use when X", "create Y", "generate Z")
---

Content Guidelines

Code Examples

  • Must be production-ready, not pseudocode
  • Include TypeScript types where applicable
  • Show complete, working examples
  • Use modern syntax and best practices

Sections to Include

  1. Core Workflow: Numbered steps for using the skill
  2. Main Content: Patterns, templates, examples
  3. Best Practices: Industry-proven recommendations
  4. Output Checklist: Verification items

Writing Style

  • Active voice, imperative mood
  • Concise, scannable formatting
  • Tables for structured comparisons
  • Code blocks for all technical content

Skill Quality Criteria

Completeness

  • Solves a specific, well-defined problem
  • Includes working code examples
  • Has clear trigger phrases in description
  • Provides output verification checklist

Consistency

  • Follows naming conventions (kebab-case)
  • Uses standard section headings
  • Matches existing skill format
  • Placed in correct category folder

Usefulness

  • Examples are copy-paste ready
  • Covers common use cases
  • Anticipates edge cases
  • References external docs where helpful

Example: Creating a New Skill

Step 1: Define the Skill

Name: api-rate-limiter
Category: backend
Purpose: Implement rate limiting for APIs
Triggers: "add rate limiting", "protect API", "throttle requests"

Step 2: Create Folder Structure

mkdir -p backend/api-rate-limiter
touch "backend/api-rate-limiter/SKILL.md"

Step 3: Write SKILL.md

---
name: api-rate-limiter
description: Implements rate limiting for APIs using token bucket, sliding window, or fixed window algorithms. Use when users request "add rate limiting", "protect API from abuse", or "throttle requests".
---

# API Rate Limiter

Protect your APIs from abuse with production-ready rate limiting.

## Core Workflow

...

Step 4: Add References (if needed)

mkdir -p backend/api-rate-limiter/references
touch backend/api-rate-limiter/references/algorithms.md

Output Checklist

When creating a new skill:

  • Skill name is kebab-case
  • Description includes trigger phrases
  • Placed in correct category folder
  • SKILL.md follows template structure
  • Code examples are production-ready
  • Includes Core Workflow section
  • Has Output Checklist section
  • Reference files added if needed

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

37.59%
按下载量换算23

Claude

29.05%
按下载量换算18

Cursor

20.5%
按下载量换算13

Gemini CLI

10.55%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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