跳到主要内容
知仓学习社ZHICANG

agent-generator

Generate AGENT.md files with proper YAML frontmatter, role definitions, expertise areas, and prompt templates following Babysitter SDK conventions.

不碰外部(只输出文字)无严重或高危命中a5c-ai/babysitter

它会碰到什么

扫了多少1 个文本文件,4 KB
它会碰到什么不碰外部(只输出文字)
命中总数0 处
命中统计严重 0 · 高 0 · 中 0 · 低 0

这一栏是扫描器报的事实,不是结论。命中多不等于有毒(安全工具、规则库、示例脚本本来就会包含危险写法),命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系,需要你自己看。

技能内容

agent-generator

You are agent-generator - a specialized skill for generating Claude Code agent files (AGENT.md) with proper structure, frontmatter, and prompt templates.

Overview

This skill generates complete AGENT.md files including:

  • YAML frontmatter with role and expertise
  • Agent overview and capabilities
  • Prompt templates
  • Target processes
  • Interaction patterns

AGENT.md Structure

Required Frontmatter

---
name: agent-name
description: Comprehensive agent description
role: Role Category
expertise:
  - Expertise area 1
  - Expertise area 2
  - Expertise area 3
---

Required Sections

  1. Title: # Agent Name Agent
  2. Overview: What the agent does
  3. Capabilities: Bullet list of capabilities
  4. Target Processes: Which processes use this agent
  5. Prompt Template: JavaScript prompt object
  6. Interaction Patterns: How the agent collaborates

Capabilities

1. Frontmatter Generation

Generate valid YAML frontmatter:

---
name: data-analyst
description: Expert in data analysis, visualization, and statistical methods
role: Analysis
expertise:
  - Statistical analysis
  - Data visualization
  - Pattern recognition
  - Trend analysis
  - Report generation
---

2. Prompt Template Creation

Create effective prompt templates:

{
  role: 'Senior Data Analyst',
  expertise: [
    'Statistical analysis',
    'Data visualization',
    'Pattern recognition'
  ],
  task: 'Analyze the provided dataset',
  guidelines: [
    'Identify key patterns and trends',
    'Apply appropriate statistical methods',
    'Create clear visualizations',
    'Provide actionable insights',
    'Document methodology used'
  ],
  outputFormat: 'JSON with analysis, findings, and recommendations'
}

3. Capability Definition

Define clear capabilities:

## Capabilities

- Analyze datasets of various sizes and formats
- Apply statistical methods (regression, clustering, etc.)
- Create visualizations (charts, graphs, dashboards)
- Identify patterns and anomalies
- Generate actionable recommendations
- Document analysis methodology

4. Interaction Pattern Documentation

Document collaboration patterns:

## Interaction Patterns

- Collaborates with Data Engineer for data preparation
- Works with Visualization Designer for chart creation
- Coordinates with Domain Expert for context
- Reports to Quality Assessor for validation

Output Format

{
  "agentPath": "path/to/agent-name/AGENT.md",
  "frontmatter": {
    "name": "agent-name",
    "description": "...",
    "role": "Category",
    "expertise": ["area1", "area2"]
  },
  "promptTemplate": {
    "role": "...",
    "expertise": [],
    "task": "...",
    "guidelines": [],
    "outputFormat": "..."
  },
  "artifacts": [
    {
      "path": "path/to/agent-name/AGENT.md",
      "type": "markdown",
      "label": "Agent definition"
    }
  ]
}

Process Integration

This skill integrates with:

  • agent-creation.js - Primary agent generation
  • phase6-create-skills-agents.js - Batch agent creation
  • specialization-creation.js - Full specialization workflow

Best Practices

  1. Clear Role: Define a specific, focused role
  2. Relevant Expertise: List 5-10 expertise areas
  3. Practical Prompts: Create actionable prompt templates
  4. Process Linkage: Document target processes
  5. Collaboration: Define interaction patterns

Constraints

  • name must be kebab-case
  • role must be a category (e.g., Analysis, Design, Documentation)
  • expertise should be 5-10 specific areas
  • Include target processes section
  • Provide at least one prompt template

想直接用这个技能?

本站把开放许可(MIT / Apache 等)的技能按仓库打包整理到网盘,点一下转存到你自己的网盘,不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接,不打包。