agentCLAWHUBUnverified

Agent Add

可能是最好的新增 agent 的技能! 用 AI 新建 agent 往往会碰到各种不可预测的情况,md 文档混乱,目录混乱等等。 但 openclaw 其实已经建立了一整套建立 新agent 的终端命令,能规范的配置 md文件 和 workspace。 这个技能可以让 AI 严格按 OpenClaw 官方规范创建... Skill: Agent Add Owner: yangyangupday Summary: 可能是最好的新增 agent 的技能! 用 AI 新建 agent 往往会碰到各种不可预测的情况,md 文档混乱,目录混乱等等。 但 openclaw 其实已经建立了一整套建立 新agent 的终端命令,能规范的配置 md文件 和 workspace。 这个技能可以让 AI 严格按 OpenClaw 官方规范创建... Tags: latest:1.4.2 Version history: v1.4.2 | 2026-06-24T00:17:26.096Z | user 修复安全审查问题:1) SKILL.md 添加副作用说明(磁盘写入、文件修改、持久化记录);2) 脚本中 eval 替换为数组命令执行,消除 shell 注入风险 v1.0.2 | 2026-06-24T00:16:50.579Z | user 修复安全审查问题:1)

OpenClaw

Rank

62

Safety

84

Downloads

1.1k

Updated

Oct 11, 2026

Version

1.4.2

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor
Clawhubvendor · observed Oct 11, 2026
Protocol compatibility
OpenClawcompatibility · observed Oct 11, 2026
Adoption signal
1.1K downloadsadoption · observed Oct 11, 2026
Latest release
1.4.2release · observed Jun 24, 2026
Handshake status
UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s170vjsar83ky1pjvev2gjcv1186mnvx:agent-add
  1. Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
  2. Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-yangyangupday-agent-add/snapshot"

Documentation

CLAWHUB

89,153 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---

name: agent-add
description: "按照 OpenClaw 官方规范创建新 agent(代理),自动完成问答、配置、workspace 初始化与记录。"
metadata:
  openclaw:
    emoji: 🤖
    requires:
      bins:
    - openclaw

---

# Agent Add — 新建 OpenClaw Agent

这是按照 OpenClaw 官方规范建立新 agent 的技能。全程遵循 `openclaw agents add` CLI 命令的标准化流程,确保新建 agent 后自动生成完整的 workspace 和一系列精炼的 `.md` 引导文档,让 AI 更好地配合人类工作。

> **⚠️ 副作用说明:** 此技能会执行以下磁盘写入操作,请确认后再使用:
>
> - **创建新目录:** 为新 agent 创建独立的 workspace 目录
> - **写入文件:** 创建 AGENTS.md、IDENTITY.md、SOUL.md、USER.md 等模板文件
> - **修改已有文件:** 脚本执行后,会用 `edit` 工具对 IDENTITY.md、SOUL.md、USER.md 做**精准编辑**(替换字段值,保留原始结构)。这些文件如果已存在,其内容会被部分修改
> - **持久化记录:** 在技能目录的 `history/history.md` 中追加一条创建记录(永久保存)
> - **修改 OpenClaw 配置:** 通过 `openclaw agents add` 写入 agent 注册信息
>
> 建议在运行前备份重要 workspace,或在确认汇总后再执行。

## 流程

### 第一步:逐个确认信息(严格一问一答)

用户如果需要添加 agent,务必**严格分开问、一个一个问**。每个问题发出后,**等用户回复并确认**,再问下一个。不要一次性问多个问题,不要把最后一个问题和汇总合并。

> **关键规则:** 每问一个问题 → 等用户回复 → 确认收到 → 再问下一个。4 个问题全部确认完毕后再进入第二步汇总。

#### 问题 1:Agent 名字

> 请给这个 agent 起个名字。这个名字会决定:
>
> - 工作目录的名称
> - 界面中选择 agent 时显示的名字
> - 在群里 @召唤 这个 agent 时使用的名字
>
> **建议:** 尽量简短好记,2-4 个字或英文单词。例如:`助手`、`coder`、`小秘`。

**收到回复后确认:** "好的,agent 名字确定为 `{name}`。"

#### 问题 2:Agent 的定位描述

> 请描述一下这个 agent 的定位。可以参考以下格式:
>
> - **用途:** 这是我的___,用来___
> - **昵称/称呼:** (可选)
> - **性格/风格:** 严谨 / 幽默 / 简洁 / 温暖 / 专业...
> - **图标 emoji:** 选一个代表它的符号
>
> **图标建议(根据 agent 名字 `{name}` 推荐,仅供参考,可以自己选):**
>
> (根据名字的类型动态推荐 5-8 个相关 emoji,不要固定列同一批。例如:
> - 教育/老师类:🎓 📚 ✏️ 🍎 🧑‍🏫
> - 代码/技术类:💻 🔧 ⚙️ 🐛 🖥️
> - 写作/文案类:✍️ 📝 📖 🖊️ 📰
> - 数据/分析类:📊 📈 📉 🔢 🧮
> - 日常/助手类:📋 ✅ ⚡ 🤖 💡
> - 设计/创意类:🎨 🎭 🖼️ ✨ 🎬)
>
> **示例:**
>
> - "这是我的代码审查助手,用来 review PR 和检查 bug,风格严谨简洁,图标用 🔍"
> - "这是我的日常秘书,帮我管理日程和邮件,语气温暖友好,图标用 📋"
> - "这是我的数据分析 agent,处理报表和可视化,专业高效,图标用 📊"

**收到回复后确认:** "好的,定位描述已记录。"

#### 问题 3:模型选择

先用 `session_status` 获取当前会话使用的模型,再从 openclaw.json 读取 `agents.defaults.model.primary` 作为默认模型。

> 请选择这个 agent 使用的模型。可选:
>
> - **当前主 agent 正在使用的模型:** `{currentModel}`(推荐,和现有 agent 一致)
> - **默认模型:** `{defaultModel}`
>
> 先选一个能用的就行,后面随时可以换模型。

**收到回复后确认:** "好的,模型确定为 `{model}`。"

#### 问题 4:Workspace 目录

计算规则(按实际使用方式):
1. 先找到 main agent workspace 的**父目录**
2. 新 agent 的 workspace = `{父目录}/workspace-{agentId}`
3. 也就是和 main 的 workspace **平级**,在同一目录下

例如 main workspace 是 `/data1/.openclaw/workspace`,则:
- 父目录 = `/data1/.openclaw/`
- 新 workspace = `/data1/.openclaw/workspace-{agentId}`

> 新 agent 的 workspace 将创建在以下位置:
>
> ```
> {实际计算出的路径,例如 /data1/.openclaw/workspace-xiaolaoshi}
> ```
>
> 这个目录和 main agent 的 workspace 平级。确认使用这个默认路径,还是指定其他路径?

**收到回复后确认:** "好的,workspace 路径确定为 `{workspacePath}`。"

---

> ⚠️ **注意:问题 4 确认后,等用户回复,再单独进入第二步汇总。不要把问题 4 和汇总合并在一起问。**

### 第二步:汇总确认

**四个问题全部逐个确认后**,给用户展示完整汇总:

```
📋 即将创建的新 Agent:

- Agent ID: {agentId}
- 显示名称: {name}
- 定位: {description}
- 模型: {model}
- Workspace: {workspacePath}
- 图标: {emoji}

确认以上信息?(回复"确认"或指出需要修改的地方)
```

用户确认后,告知即将生成的文档列表:

```
📁 新 agent 的 workspace 中将包含以下 OpenClaw 精炼文档:

这些文档规范了 AI 的行为准则,能让 AI 更好地帮助人类工作。
建议让 AI 按照各自规范自动填充内容,尽量不要手动删除。

| 文件 | 定位 | 核心职责 | 生命周期 |
|------

_meta.json

{
  "ownerId": "kn789p5x1zr9b8ph4x9mycw96586myx4",
  "slug": "agent-add",
  "version": "1.4.2",
  "publishedAt": 1782260246096
}

history/history.md

# Agent 添加记录

skill-card.md

## Description:

Creates new OpenClaw agents by guiding setup questions, running OpenClaw registration, initializing a workspace, and recording the creation.

This skill is ready for commercial/non-commercial use.

## Publisher:

[yangyangupday](https://clawhub.ai/user/yangyangupday)

### License/Terms of Use:

MIT-0

## Use Case:

OpenClaw users and developers use this skill to create a new agent through a guided question flow, register it with OpenClaw, initialize workspace documents, and update identity and persona files.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill can copy private main-agent workspace files into a new agent workspace without redaction or clear isolation controls.

Mitigation: Review the source workspace before installation and use; prefer clean packaged templates and confirm before copying existing workspace files.

Risk: The skill writes files, modifies OpenClaw configuration, and appends creation records during agent setup.

Mitigation: Review the summarized target path and generated document list before execution, and back up important workspaces before creating a new agent.

## Reference(s):

- [Agent Add ClawHub page](https://clawhub.ai/yangyangupday/skills/agent-add)

## Skill Output:

**Output Type(s):** [text, markdown, shell commands, configuration, guidance]

**Output Format:** [Markdown guidance with shell command examples]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Guides interactive agent setup and may execute OpenClaw commands that create or modify local workspace files.]

## Skill Version(s):

1.4.2 (source: server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW
Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW
Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/yangyangupday/skills/agent-add",
      "sourceUrl": "https://clawhub.ai/yangyangupday/skills/agent-add",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-11T11:38:44.662Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-yangyangupday-agent-add/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-yangyangupday-agent-add/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-11T11:38:44.662Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "1.1K downloads",
      "href": "https://clawhub.ai/yangyangupday/agent-add",
      "sourceUrl": "https://clawhub.ai/yangyangupday/agent-add",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-11T11:38:44.662Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "1.4.2",
      "href": "https://clawhub.ai/yangyangupday/agent-add",
      "sourceUrl": "https://clawhub.ai/yangyangupday/agent-add",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-06-24T00:17:26.096Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-yangyangupday-agent-add/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-yangyangupday-agent-add/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 1.4.2",
      "description": "修复安全审查问题:1) SKILL.md 添加副作用说明(磁盘写入、文件修改、持久化记录);2) 脚本中 eval 替换为数组命令执行,消除 shell 注入风险",
      "href": "https://clawhub.ai/yangyangupday/agent-add",
      "sourceUrl": "https://clawhub.ai/yangyangupday/agent-add",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-06-24T00:17:26.096Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 11, 2026.

Sponsored

Ads related to Agent Add and adjacent AI workflows.