Token导航 LogoToken导航

Agent Skill · 开发

meta-agentic-creation(元 Agent 创造)

meta-agentic-creation 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。

meta-agentic-creation 是开发类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在开发类的 21,746 个 Skill 里排第 19,854。

总安装 250周安装 10GitHub Stars 61下载 81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:meta-agentic-creation(元 Agent 创造)
来源仓库:https://github.com/melodic-software/claude-code-plugins
仓库路径:skills/meta-agentic-creation
安装命令:
npx skills add https://github.com/melodic-software/claude-code-plugins --skill meta-agentic-creation
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/melodic-software/claude-code-plugins --skill meta-agentic-creation

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

meta-agentic-creation 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 中围绕仓库状态、代码变更或协作事项进行整理。

通过 npx skills add 命令从指定 GitHub 仓库安装并使用该技能。安装前需确认权限范围、维护状态,注意是否涉及联网、命令执行或文件读写操作。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。

来源仓库内路径:skills/meta-agentic-creation

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/melodic-software/claude-code-plugins --skill m…;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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

meta-agentic-creation 怎么安装?

在终端执行 npx skills add https://github.com/melodic-software/claude-code-plugins --skill meta-agenti…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

meta-agentic-creation 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。

meta-agentic-creation 需要什么权限?

权限级别是只读。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。

meta-agentic-creation 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。

meta-agentic-creation 用的人多吗?

公开数据是累计安装 250 次,近一周安装 10 次,下载 81 次,GitHub 61 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。

meta-agentic-creation 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。
  • 标注为只读权限,试用阶段不容易误改本地文件。

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。
  • 需要处理开发类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

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。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
meta-agentic-creation

元 Agent 创造 · 本页

25061只读未明确通过

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

Meta-Agentic Creation

Guide for creating meta-level agentic components that generate other components.

Core Philosophy

"Build the system that builds the system. Do not work on the application layer."

Meta agentics provide multiplicative leverage:

  • Meta Prompt: 1 prompt that creates N prompts
  • Meta Agent: 1 agent that creates N agents
  • Meta Skill: 1 skill that creates N skills

The Meta-Agentic Hierarchy

┌─────────────────────────────────────────────────────┐
│ Level 3: Meta-Meta (rarely needed)                  │
│          • Generators that create generators        │
└──────────────────────┬──────────────────────────────┘
                       │
┌──────────────────────▼──────────────────────────────┐
│ Level 2: Meta Components                            │
│          • Meta prompts (prompt generators)         │
│          • Meta agents (agent builders)             │
│          • Meta skills (skill scaffolders)          │
└──────────────────────┬──────────────────────────────┘
                       │
┌──────────────────────▼──────────────────────────────┐
│ Level 1: Standard Components                        │
│          • Domain prompts                           │
│          • Specialized agents                       │
│          • Task-specific skills                     │
└──────────────────────┬──────────────────────────────┘
                       │
┌──────────────────────▼──────────────────────────────┐
│ Level 0: Application Layer                          │
│          • End-user features                        │
│          • Business logic                           │
└─────────────────────────────────────────────────────┘

When to Use

  • Scaling agentic layer development (need 4+ similar components)
  • Creating generators or templates for prompts/agents/skills
  • Implementing "build the system that builds the system" patterns
  • Establishing consistent patterns for team/organization
  • Onboarding others to agentic component creation
  • Maximizing leverage through multiplicative returns

Meta Prompt Template

A meta prompt is a prompt that generates other prompts.

---
description: Generate a {type} prompt for {purpose}
argument-hint: <name> [options...]
---

# Meta Prompt: {Type} Generator

Generate well-structured {type} prompts following established patterns.

## Arguments

- `$1`: Name for the generated prompt (required)
- `$2`: Primary purpose/domain (optional)
- `$ARGUMENTS`: Additional context

## Template Structure

The generated prompt will follow this structure:

### YAML Frontmatter

description: {Generated based on purpose} argument-hint: {Appropriate for prompt type}



### Sections to Include

1. **Purpose**: Clear statement of what prompt does
2. **Arguments**: Input parameters with defaults
3. **Workflow**: Step-by-step instructions
4. **Output Format**: Expected deliverable structure
5. **Notes**: Important considerations

## Generation Rules

1. Use imperative mood ("Do X", not "You should do X")
2. Include concrete examples
3. Specify output format explicitly
4. Add validation/verification steps
5. Keep under {line_limit} lines

## Output

Write the generated prompt to: `.claude/commands/{name}.md`

Report:

- Generated prompt name
- Location
- Key sections included

Meta Agent Template

A meta agent creates other agents.

---
name: meta-agent
description: Create new specialized agents following established patterns and best practices.
tools: Read, Write, Glob, Grep
model: opus
---

# Meta Agent: Agent Builder

Create well-structured agents following Claude Code patterns.

## Input Requirements

When invoked, expect:

- Agent name (kebab-case)
- Agent purpose (1-2 sentences)
- Required tools (list)
- Model preference (opus|sonnet|haiku)
- Domain context

## Agent Template

name: {agent-name} description: {Purpose description under 200 chars} tools: {Tool1, Tool2, ...} model: {opus|sonnet|haiku}


{Agent Name}

{Detailed purpose and when to use this agent}

Capabilities

  • Capability 1
  • Capability 2

Workflow

Step 1: {First Step}

{Instructions}

Step 2: {Second Step}

{Instructions}

Output Format

{Expected output structure}

Constraints

  • Constraint 1
  • Constraint 2

## Generation Workflow

1. **Analyze Request**: Understand agent purpose
2. **Select Tools**: Choose minimal required tools
3. **Choose Model**:
   - haiku: Simple, fast tasks
   - sonnet: Balanced reasoning
   - opus: Complex, critical tasks
4. **Design Workflow**: Create step-by-step process
5. **Write Agent**: Generate agent file
6. **Register**: Update plugin.json if needed

## Validation

Before completing:

- [ ] Description under 200 characters
- [ ] Tools are minimal and appropriate
- [ ] Model matches task complexity
- [ ] Workflow is complete and actionable

Meta Skill Template

A meta skill creates other skills.

---
name: meta-skill
description: Create new skills following Claude Code patterns with proper YAML frontmatter, structure, and documentation.
version: 1.0.0
allowed-tools: Read, Write, Glob, Grep
tags: [meta, skill, generator, scaffolder]
---

# Meta Skill: Skill Generator

Create well-structured skills following established patterns.

## Skill Template

name: {skill-name} description: {Clear description of what skill does and when to use it} version: 1.0.0 allowed-tools: {Tool1, Tool2, ...} tags: [{tag1}, {tag2}, ...]


{Skill Name}

{Introduction and purpose}

When to Use

  • Use case 1
  • Use case 2

Key Concepts

Concept 1

{Explanation}

Concept 2

{Explanation}

Patterns

Pattern Name

{Description and example}

Anti-Patterns

Anti-PatternProblemSolution
.........

Related Skills

  • skill-1: Relationship
  • skill-2: Relationship

## Skill Generation Rules

1. **Naming**: Use noun-phrases (kebab-case)
2. **Description**: Under 200 chars, starts with action verb
3. **Tags**: 4-8 relevant keywords
4. **Tools**: Minimal set needed
5. **Structure**: Consistent sections

## Directory Structure

skills/{skill-name}/ SKILL.md # Main skill file references/ # Optional supporting docs scripts/ # Optional automation

Creating Meta Components

Step 1: Identify the Pattern

Before creating a meta component, identify:

  1. What components will it generate?
  2. What's the common structure?
  3. What varies between instances?
  4. What validation is needed?

Step 2: Design the Template

The template should:

  • Capture the invariant structure
  • Mark variable sections clearly
  • Include validation rules
  • Provide examples

Step 3: Build the Generator

The generator should:

  • Parse input parameters
  • Apply template with variables
  • Validate output
  • Write to correct location

Step 4: Test Generation

Validate by:

  1. Generate a simple component
  2. Generate a complex component
  3. Test edge cases
  4. Verify all outputs are valid

When to Create Meta Components

SituationCreate Meta?Reason
Need 1 componentNoDirect creation faster
Need 2-3 similarMaybeDepends on complexity
Need 4+ similarYesMeta pays off
Establishing patternsYesEncodes best practices
Onboarding othersYesEnsures consistency

Anti-Patterns

Anti-PatternProblemSolution
Over-abstractionMeta-meta-metaStop at 2 levels
Rigid templatesCan't handle variationsBuild in flexibility
No examplesUsers don't understandInclude concrete examples
No validationBad outputs generatedAlways validate results

Real-World Meta Components

From agent-experts Repository

.claude/commands/meta_prompt.md    # Creates new prompts
.claude/agents/meta-agent.md       # Creates new agents
.claude/skills/meta-skill/SKILL.md # Creates new skills

TAC Plugin Examples

tac/agents/prompt-generator.md     # Generates prompts
tac/agents/agent-builder.md        # Builds agents
tac/skills/tool-design/SKILL.md    # Designs tools

Leverage Calculation

Meta components provide multiplicative returns:

Without meta:
  10 agents × 30 min each = 300 minutes

With meta:
  1 meta-agent × 60 min + 10 generations × 5 min = 110 minutes

Savings: 63%

The more components you need, the more meta pays off.

Related Skills

  • agent-expert-creation: Self-improving experts
  • template-meta-prompt-creation: Level 6 prompts
  • prompt-level-selection: Choosing prompt complexity

Last Updated: 2025-12-15

Version History

  • v1.0.0 (2025-12-26): Initial release

平台分布

Codex

36.09%
按下载量换算29

Claude

29.64%
按下载量换算24

Cursor

17.73%
按下载量换算14

Gemini CLI

10.32%
按下载量换算8

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。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