跳到正文
cccskills
免费在 GitHub 公开

add-agent

Add a new OpenClaw Agent, automatically configure openclaw.json, create workspace, copy auth and skills.

中文简介正在准备中。当前显示原文说明。

集成工具Telegram
查看安装方法

包含的文件(1)

  • SKILL.md5.5 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

add-agent

Quickly add a new isolated Agent with a dedicated Telegram Bot.

Trigger

User says something like:

"Add a new agent, ID is marketing, name is Marketing Assistant, telegram Bot Token is xxx, allowFrom is 123456789, responsible for content marketing and social media"

Steps

Once a new agent request is received, execute in the following order:

1. Extract Parameters

Extract the following fields from user input:

  • AGENT_ID: English ID (e.g. marketing)
  • AGENT_NAME: Agent name (e.g. Marketing Assistant, Alice, WorkBot, etc.)
  • BOT_TOKEN: Telegram Bot Token
  • ALLOW_FROM: allowFrom numeric ID (e.g. 123456789)
  • DESCRIPTION: Role description (e.g. responsible for content marketing and social media)

If any field is missing, ask the user to provide it before continuing.

2. Detect Installation Directory

Read the current openclaw.json path, extract the actual paths from the existing main agent in agents.list to derive:

  • STATE_DIR: e.g. /home/openclaw/.openclaw
  • MAIN_WORKSPACE: main agent workspace path
  • MAIN_AGENT_DIR: main agent agentDir path
  • NEW_WORKSPACE: ${STATE_DIR}/workspace-${AGENT_ID}
  • NEW_AGENT_DIR: ${STATE_DIR}/agents/${AGENT_ID}/agent

3. Backup Config File

cp ${CONFIG_PATH} ${CONFIG_PATH}.bak.$(date +%Y%m%d%H%M%S)

4. Run openclaw agents add

openclaw agents add ${AGENT_ID}

This automatically initializes the workspace directory structure, agentDir, and default files like SOUL.md and AGENTS.md.

5. Copy Auth, Skills and USER.md

# Copy auth profiles
cp ${MAIN_AGENT_DIR}/auth-profiles.json \
   ${NEW_AGENT_DIR}/auth-profiles.json

# Copy skills
cp -r ${MAIN_WORKSPACE}/skills/ \
      ${NEW_WORKSPACE}/skills/

# Copy USER.md
cp ${MAIN_WORKSPACE}/USER.md \
   ${NEW_WORKSPACE}/USER.md

6. Generate Persona Files

Overwrite ${NEW_WORKSPACE}/SOUL.md:

# ${AGENT_NAME}

## Identity
You are ${AGENT_NAME}, ${DESCRIPTION}.
Your partner is the main agent. You collaborate together to complete tasks.

## Core Responsibilities
${DESCRIPTION}

## Personality
- Action-oriented: Break down tasks immediately and provide clear execution steps
- Proactive reporting: Report results to main after completing tasks
- Professional: Maintain high standards for all outputs

## Rules
- Do not execute high-risk operations without confirmation
- Always notify the user before executing operations that require manual approval

Overwrite ${NEW_WORKSPACE}/AGENTS.md:

# ${AGENT_NAME} Agent Configuration

## Other Agents in the System

- **main**: Primary agent, responsible for daily conversation, task coordination and decisions
- **${AGENT_ID} (yourself)**: ${DESCRIPTION}

## Collaboration Rules

### Receiving Tasks from main
1. Confirm task goal and priority
2. Break down execution steps
3. Execute and record results
4. Report results back to main upon completion

### When to Proactively Contact main
- Operations that require final user confirmation
- Result reporting after task completion
- Escalating anomalies or unexpected situations

7. Update openclaw.json

Read the current config and append the following:

Add to agents.list:

{
  "id": "${AGENT_ID}",
  "name": "${AGENT_NAME}",
  "workspace": "${NEW_WORKSPACE}",
  "agentDir": "${NEW_AGENT_DIR}"
}

Add to bindings:

{
  "agentId": "${AGENT_ID}",
  "match": {
    "channel": "telegram",
    "accountId": "${AGENT_ID}"
  }
}

Add to channels.telegram.accounts:

"${AGENT_ID}": {
  "enabled": true,
  "botToken": "${BOT_TOKEN}",
  "dmPolicy": "pairing",
  "allowFrom": ["${ALLOW_FROM}"],
  "groupPolicy": "allowlist",
  "streaming": "off"
}

Handle tools config (check before writing):

Check whether the tools field exists:

  • If tools does not exist, add the full block:
"tools": {
  "agentToAgent": {
    "enabled": true,
    "allow": ["main", "${AGENT_ID}"]
  },
  "sessions": {
    "visibility": "all"
  }
}
  • If tools exists but has no agentToAgent, add it:
"agentToAgent": {
  "enabled": true,
  "allow": ["main", "${AGENT_ID}"]
}
  • If agentToAgent already exists, only append "${AGENT_ID}" to the allow array (no duplicates)

  • If sessions.visibility does not exist, add it:

"sessions": {
  "visibility": "all"
}

8. Validate JSON

cat ${CONFIG_PATH} | python3 -m json.tool

If validation fails, stop immediately and restore from backup:

cp ${CONFIG_PATH}.bak.* ${CONFIG_PATH}

Report the exact error to the user.

9. Fix File Permissions

chown -R $(stat -c '%U:%G' ${MAIN_WORKSPACE}) ${NEW_WORKSPACE}/
chown -R $(stat -c '%U:%G' ${MAIN_AGENT_DIR}) ${NEW_AGENT_DIR}/

10. Report Completion

Reply to the user:

✅ Agent "${AGENT_NAME}" (${AGENT_ID}) created successfully!

Completed:
- openclaw agents add initialized
- openclaw.json updated
- Auth, skills and USER.md copied from main
- SOUL.md / AGENTS.md generated
- agentToAgent communication configured
- JSON validation passed

⚠️ Manual steps required:
1. Restart the Gateway:
   openclaw gateway restart

2. Verify bindings:
   openclaw agents list --bindings

3. Open Telegram, find the new Bot and send /start to complete pairing

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

name: 4d-compression-core version: 1.0.2 description: "把长内容压缩成结构化向量——节省 60-80% Token,保留核心信息" metadata: { "openclaw": { "emoji": "🌀", "requires": { "bins": ["jq", "awk"] }, "triggers": ["压缩", "4d",...

中文简介正在准备中。当前显示原文说明。

modbender/skill-library-mcp172026年9月28日 更新

Use cheap, TEE-verified AI models from the 0G Compute Network as OpenClaw providers. Discover available models and compare pricing vs OpenRouter, verify provider integrity via hardware attestation (Intel TDX), manage your 0G wallet and sub-accounts, and configure models in OpenClaw with one workflow. Supports DeepSeek, GLM-5, Qwen, and other models available on the 0G marketplace.

中文简介正在准备中。当前显示原文说明。

modbender/skill-library-mcp172026年9月28日 更新

Send and receive P2P messages using disposable numbers and PINs. No servers, no accounts. Use for human notifications, approval flows, and agent-to-agent communication.

中文简介正在准备中。当前显示原文说明。

modbender/skill-library-mcp172026年9月28日 更新

0xarchive

免费

Query historical crypto market data from 0xArchive across Hyperliquid, Lighter.xyz, and HIP-3. Covers orderbooks, trades, candles, funding rates, open interest, liquidations, and data quality. Use when the user asks about crypto market data, orderbooks, trades, funding rates, or historical prices on Hyperliquid, Lighter.xyz, or HIP-3.

中文简介正在准备中。当前显示原文说明。

modbender/skill-library-mcp172026年9月28日 更新

0xwork

免费

Find and complete paid tasks on the 0xWork decentralized marketplace (Base chain, USDC escrow). Use when: the agent wants to earn money/USDC by doing work, discover available tasks, claim a bounty, submit deliverables, check earnings or wallet balance, or set up as a 0xWork worker. Task categories: Writing, Research, Social, Creative, Code, Data. NOT for: posting tasks (use the website), managing the 0xWork platform, or frontend development.

中文简介正在准备中。当前显示原文说明。

modbender/skill-library-mcp172026年9月28日 更新

Patterns and practices that dramatically accelerate development velocity. Covers parallel execution, automation, feedback loops, workflow optimization, and anti-pattern avoidance. Use when starting projects, planning sprints, optimizing workflows, or onboarding developers.

中文简介正在准备中。当前显示原文说明。

modbender/skill-library-mcp172026年9月28日 更新

查看 modbender 的全部技能

报告此技能的问题