agent-creator

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Agent Creator

This skill provides a structured process for designing and configuring specialized AI Agents.

本技能提供了设计和配置专用AI Agent的结构化流程。

When to Use

适用场景

Use this skill when you need to:

Create a New Agent: Define a purpose-built agent with specific expertise (e.g., "Make a Frontend Specialist Agent").
Generate System Prompts: Create robust, effective system instructions for an agent.
Assemble Capabilities: Select the right combination of Skills, Workflows, and Rules for a specific domain.
Refine Agent Behavior: specialized tuning of an existing agent's operational guidelines.

当你需要完成以下操作时使用本技能：

创建新Agent：定义具备特定专业能力的定制化Agent（例如"制作前端专家Agent"）。
生成系统提示词：为Agent创建健壮、有效的系统指令。
组装能力集：为特定领域选择技能、工作流和规则的最佳组合。
优化Agent行为：对现有Agent的运行规则进行专项调优。

Agent Architecture

Agent架构

An Agent in the Antigravity system is defined by a markdown file in

.agent/agents/{name}.md

containing:

Antigravity系统中的Agent由

.agent/agents/{name}.md

路径下的markdown文件定义，文件包含以下内容：

1. Frontmatter (Metadata)

1. Frontmatter（元数据）

```
name
```
: Kebab-case identifier (e.g.,
```
backend-specialist
```
).
```
description
```
: Short summary and trigger keywords.
```
tools
```
: List of tools the agent has access to (e.g.,
```
Read, Write, Bash
```
).
```
model
```
: The model usage strategy (usually
```
inherit
```
).
```
skills
```
: Comma-separated list of skills from
```
.agent/skills/
```
this agent needs.

```
name
```
：Kebab-case命名格式的标识符（例如
```
backend-specialist
```
）。
```
description
```
：简短概述和触发关键词。
```
tools
```
：Agent可访问的工具列表（例如
```
Read, Write, Bash
```
）。
```
model
```
：模型使用策略（通常为
```
inherit
```
）。
```
skills
```
：该Agent需要的、来自
```
.agent/skills/
```
的技能列表，以逗号分隔。

2. Identity & Charter

2. 身份与职责

Role: Who the agent is.
Philosophy: Core beliefs driving decisions.
Mindset: Operational mode and priorities.

角色：Agent的定位。
理念：驱动决策的核心准则。
思维模式：运行方式和优先级。

3. Critical Guidelines (The "Stop & Ask" Protocol)

3. 关键准则（"停下询问"协议）

CRITICAL: CLARIFY BEFORE CODING: A mandatory section forcing the agent to ask clarifying questions before making assumptions about stack, runtime, or tools.

关键规则：编码前先澄清：强制要求Agent在对技术栈、运行环境或工具做出假设前，先询问澄清问题的必填章节。

4. Decision Frameworks

4. 决策框架

Tables and logic guides to help the agent make technical decisions (e.g., "Node vs Python", "SQL vs NoSQL").

帮助Agent做出技术决策的表格和逻辑指南（例如"Node vs Python"、"SQL vs NoSQL"）。

5. Capabilities & specialized Lists

5. 能力与专项清单

Expertise Areas: Deep dive into specific techs.
Quality Control Loop: Mandatory steps to run after every edit.

专业领域：特定技术的深度能力说明。
质量控制闭环：每次编辑后必须执行的步骤。

Workflow: Creating an Agent

工作流：创建Agent

Follow these steps to create a new Agent.

遵循以下步骤创建新Agent。

Step 1: Define the Goal

步骤1：定义目标

Ask the user for the Agent's primary purpose.

Prompt: "What is the primary goal of this agent? What domain does it specialize in?"

询问用户Agent的核心用途。

提示词："这个Agent的核心目标是什么？它专精哪个领域？"

Step 2: Select Capabilities (Skills)

步骤2：选择能力（技能）

Analyze the available Skills in

.agent/skills/

to recommend the best set to include in the

skills

frontmatter.

Example: A Backend Agent needs
```
nodejs-best-practices
```
,
```
database-design
```
.

分析

.agent/skills/

中可用的技能，推荐最适合加入frontmatter的

skills

字段的技能集合。

示例：后端Agent需要
```
nodejs-best-practices
```
、
```
database-design
```
。

Step 3: Draft the Agent Definition

步骤3：起草Agent定义

Use the Agent Template in

assets/agent_template.md

as the mandatory base.

Frontmatter: Fill in name, tools, and required skills.
Philosophy & Mindset: Define how the agent thinks, not just what it does.
Critical Clarifications: Define what the agent MUST ask users before starting (e.g., "Which framework?", "Which DB?").
Decision Frameworks: Populate tables with current best practices for the domain.

使用

assets/agent_template.md

中的Agent模板作为强制基础。

Frontmatter：填写名称、工具和所需技能。
理念与思维模式：定义Agent的思考方式，而非仅说明它要做什么。
关键澄清规则：定义Agent开始工作前必须询问用户的内容（例如"使用哪个框架？"、"使用哪个数据库？"）。
决策框架：填充对应领域当前最佳实践的表格。

Step 4: Save the Artifact

步骤4：保存产出物

Save the file to

.agent/agents/{name}.md

Ensure the filename matches the
```
name
```
in frontmatter.

将文件保存到

.agent/agents/{name}.md

。

确保文件名与frontmatter中的
```
name
```
一致。

Tools & Resources

工具与资源

Agent Template

Agent模板

Use

assets/agent_template.md

to structure the agent definition. Strictly follow this structure.

使用

assets/agent_template.md

构建Agent定义。严格遵循该结构。

Best Practices for specialized Agents

专用Agent最佳实践

Opinionated Defaults: Agents should have strong opinions (Philosophy) but flexible execution (Clarification).
Mandatory Checks: Include a "Quality Control Loop" that forces the agent to validate its own work (Lint, Test, Security).
Anti-Patterns: Explicitly list what the agent should AVOID.

预设明确的默认规则：Agent应具备明确的决策理念（Philosophy），但执行方式灵活（支持澄清询问）。
强制检查机制：加入"质量控制闭环"，强制Agent验证自己的产出（Lint、测试、安全检查）。
反模式：明确列出Agent应该避免的行为。