Skip to main content
ClaudeWave
EN, English
Skill5.1k repo starsupdated 2mo ago

agent-info

The agent-info skill queries all agents (employees) accessible to the current user and returns their identifiers, names, descriptions, and types. Use this skill when generating code that requires a specific agentId or when users ask which agents or employees are available to them.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/dtyq/magic /tmp/agent-info && cp -r /tmp/agent-info/backend/super-magic/agents/skills/agent-info ~/.claude/skills/agent-info
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

<!--zh
# 查询可用员工列表
-->

# List Available Agents

<!--zh
查询当前用户可访问的所有员工(Agent),返回每个员工的 code(agentId)、名称、描述和类型。
-->

Query all agents accessible to the current user. Returns each agent's code (agentId), name, description and type.

<!--zh
## 核心能力
-->

## Core Capabilities

<!--zh
- 获取用户所有可用员工列表(包括内置、自定义、公开员工)
- 支持按名称模糊过滤
- 返回 code 字段即 agentId,可直接用于 `createTopicAndSend` 等 API 调用
-->

- Get all available agents for the user (including built-in, custom, and public)
- Support fuzzy filtering by name
- The returned `code` field is the agentId, usable directly in `createTopicAndSend` and similar APIs

<!--zh
## 快速开始
-->

## Quick Start

<!--zh
### 典型工作流
```
1. 查询全部员工 (list.py)
   ↓ 获取 code / name / type
2. 在代码生成中直接使用 code 作为 agentId
```
-->

### Typical Workflow

```
1. Query all agents (list.py)
   ↓ Get code / name / type
2. Use code directly as agentId in code generation
```

<!--zh
## 可用脚本
-->

## Available Scripts

---

<!--zh
### list.py - 查询员工列表
-->

### list.py - List Agents

<!--zh
查询当前用户可用的所有员工列表。
-->

Query all agents available to the current user.

**SYNOPSIS**

```bash
python scripts/list.py [OPTIONS]
```

**OPTIONS**

<!--zh
|选项|类型|必填|说明|
|---|---|---|---|
|`--name-filter <keyword>`|string|否|按员工名称模糊过滤(不区分大小写)|
|`--type-filter <type>`|string|否|按类型过滤:official / custom / public|
-->

| Option | Type | Required | Description |
| --- | --- | --- | --- |
| `--name-filter <keyword>` | string | No | Fuzzy filter by agent name (case-insensitive) |
| `--type-filter <type>` | string | No | Filter by type: official / custom / public |

**OUTPUT**

<!--zh
成功返回 JSON:
```json
{
  "total": 5,
  "agents": [
    {
      "code": "SMA-xxxx",
      "name": "数据分析师",
      "description": "专业的数据分析助手",
      "type": "custom"
    }
  ]
}
```

- `code` 即 agentId,可直接传入 `window.Magic.project.createTopicAndSend(msg, {agentId: code})`
- `type` 取值:official(内置官方)、custom(用户自定义)、public(团队/公开共享)
-->

On success, returns JSON:
```json
{
  "total": 5,
  "agents": [
    {
      "code": "SMA-xxxx",
      "name": "Data Analyst",
      "description": "Professional data analysis assistant",
      "type": "custom"
    }
  ]
}
```

- `code` is the agentId, pass directly to `window.Magic.project.createTopicAndSend(msg, {agentId: code})`
- `type` values: official (built-in), custom (user-created), public (team/public shared)

**EXAMPLES**

```bash
# 查询全部员工
python scripts/list.py

# 按名称过滤
python scripts/list.py --name-filter "数据分析"

# 按类型过滤
python scripts/list.py --type-filter custom
```

---

<!--zh
## 使用场景
-->

## Use Cases

<!--zh
### 1. 微应用代码生成中获取真实 agentId

在生成需要派发任务给员工的微应用代码前,先运行脚本获取员工列表,再将真实 code 写入代码:

```bash
python scripts/list.py --name-filter "研究员"
```

返回结果中的 `code` 即可直接用于:
```javascript
const { topicId } = await window.Magic.project.createTopicAndSend(
  message,
  { agentId: "SMA-xxxx" }  // 从 list.py 获取的真实 code
);
```

### 2. 用户询问可用员工

当用户问"我有哪些员工"或"帮我看看有什么可用的 Agent"时,运行脚本即可获取完整列表。
-->

### 1. Get real agentId for micro-app code generation

Before generating micro-app code that dispatches tasks to agents, run the script to get the agent list, then use the real code in generated code:

```bash
python scripts/list.py --name-filter "researcher"
```

Use the returned `code` directly:
```javascript
const { topicId } = await window.Magic.project.createTopicAndSend(
  message,
  { agentId: "SMA-xxxx" }  // real code from list.py
);
```

### 2. User asks about available agents

When user asks "what agents do I have" or "show me available agents", run the script to get the full list.
ai-card-generatorSkill

|

antd-style-to-tailwindSkill

Migrate existing antd-style CSS-in-JS (createStyles) components to Tailwind CSS utility classes with full dark mode support, following the project's style system transition strategy. Use when the user asks to migrate, convert, or rewrite antd-style components to Tailwind, or when working on new components in files that already use antd-style.

browserSkill

Open and operate webpages in a real browser: navigate, read rendered content, inspect interactive elements, click, type, submit forms, press keys, select options, check boxes, hover, scroll, upload files, wait for page changes, manage pages, take and save screenshots, analyze visual layout, and inspect page errors and network activity.

canvas-designerSkill

Core canvas design skill covering project management, multimedia principles, AI image generation, web image search, and design marker processing. Load for any canvas design task. CRITICAL - When user message contains [@design_canvas_project:...] or [@design_marker:...] mentions, or when the user wants to generate video/animation/clip on a canvas project, you MUST load this skill first before any operations.

chat-historySkill

Use when details may have been lost after context compaction, or when the Agent needs to inspect earlier compacted messages or previously created sub-agents.

cli-managerSkill

Manage persistence for user-installed third-party CLI tools in the Super Magic sandbox. Use when the user wants to install, configure, adopt, restore, inspect, or remove a CLI, or when an external skill, webpage, or installer asks to run CLI install commands such as curl|sh, npm install -g, pipx install, uv tool install, go install, cargo install, or brew install. Do not persist runtime-provided CLIs.

code-review-expertSkill

Expert code review of current git changes with a senior engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements.

compact-chat-historySkill

Summarize and compress the current conversation history into a structured context snapshot, then call compact_chat_history to save it. Read this skill only when the user explicitly asks to compact/summarize — system-triggered compaction injects the instructions directly without requiring a skill read.