Token导航 LogoToken导航

Agent Skill · 待分类

openclaw-extend(OpenClaw extend 命令行)

openclaw-extend 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

openclaw-extend 是待分类类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证信息还不明确,第三方扫描有未通过项,按安装量在待分类类的 11,209 个 Skill 里排第 7,770。

总安装 343周安装 14GitHub Stars 3下载 110核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:openclaw-extend(OpenClaw extend 命令行)
来源仓库:https://github.com/anthemflynn/ccmp
仓库路径:skills/openclaw-extend
安装命令:
npx skills add https://github.com/anthemflynn/ccmp --skill openclaw-extend
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/anthemflynn/ccmp --skill openclaw-extend

这个 Skill 是做什么的

这个 Skill 的分类还没最终确定,用法以来源仓库的说明为准。

openclaw-extend 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。适用于待分类的开发或协作类任务,支持代码变更追踪与 Issue 管理。

通过 npx skills add 命令从指定 GitHub 仓库安装,具体用法需结合原始 README 进一步确认。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写操作。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/openclaw-extend

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/anthemflynn/ccmp --skill openclaw-extend;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

openclaw-extend 怎么安装?

在终端执行 npx skills add https://github.com/anthemflynn/ccmp --skill openclaw-extend。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

openclaw-extend 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

openclaw-extend 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

openclaw-extend 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

openclaw-extend 用的人多吗?

公开数据是累计安装 343 次,近一周安装 14 次,下载 110 次,GitHub 3 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

openclaw-extend 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理待分类类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

待分类类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
infsh-cli

infsh CLI · Codex、Claude

4,374,576382权限未标注未明确未收录
ai-video-generation

AI 视频生成 · Codex、Claude

4,313,376382调用外部服务未明确有提醒
lark-openapi-explorer

云雀 OpenAPI 浏览器 · Codex、Claude

2,064,1209,011需要联网未明确有提醒
lark-workflow-standup-report

Lark 工作流程站立报告 · Codex、Claude

2,041,6328,978需要联网未明确通过
use-my-browser

使用我的浏览器 · Codex、Claude

1,848,49140操作浏览器未明确未通过
openclaw-extend

OpenClaw extend 命令行 · 本页

3433接触敏感数据未明确未通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

!openclaw plugins list 2>&1 | head -15!openclaw channels list 2>&1 | head -15

OpenClaw Extend — Add New Capabilities

You are an OpenClaw extension operator. Add plugins, hooks, agents, channels, nodes, models, devices, and webhooks to expand the system's capabilities.

Scope

This skill covers adding new things to the system:

  • Plugins — extend gateway functionality
  • Hooks — agent lifecycle hooks
  • Agents — isolated agent instances
  • Channels — messaging integrations (WhatsApp, Telegram, Discord, Matrix)
  • Nodes — remote execution nodes
  • Models — AI model providers
  • Devices — paired device management
  • Webhooks — external event integrations
  • Skills — inspect and manage available skills

For configuration tuning, use openclaw-admin. For diagnostics, use openclaw-doctor. For operational maintenance, use openclaw-maintain.


Plugins

List & Inspect

openclaw plugins list           # all plugins
openclaw plugins info <name>    # plugin details
openclaw plugins doctor         # diagnose load issues

Install & Manage

openclaw plugins install <spec>   # install (path, archive, or npm spec)
openclaw plugins enable <name>    # enable a plugin
openclaw plugins disable <name>   # disable a plugin
openclaw plugins update           # update npm-installed plugins

After installing a plugin:

openclaw plugins list             # verify it appears
openclaw daemon restart           # restart to load
openclaw plugins doctor           # check for load issues

Plugin authoring guide: See references/plugin-hook-authoring.md.


Hooks

List & Inspect

openclaw hooks list             # all hooks
openclaw hooks info <name>      # hook details
openclaw hooks check            # eligibility status

Install & Manage

openclaw hooks install <spec>   # install (path, archive, or npm spec)
openclaw hooks enable <name>    # enable a hook
openclaw hooks disable <name>   # disable a hook
openclaw hooks update           # update npm-installed hooks

After installing a hook:

openclaw hooks list             # verify it appears
openclaw hooks check            # verify eligibility
openclaw daemon restart         # restart to activate

Hook authoring guide: See references/plugin-hook-authoring.md.


Agents

List & Manage

openclaw agents list            # all configured agents
openclaw agents add             # add a new agent (interactive)
openclaw agents set-identity <name>  # update identity (name/theme/emoji/avatar)
openclaw agents delete <name>   # delete agent + prune workspace/state

Each agent gets:

  • Isolated workspace
  • Isolated auth/credentials
  • Routing rules (which channels/targets map to this agent)

Channels

List & Status

openclaw channels list          # configured channels + auth profiles
openclaw channels status        # gateway channel status
openclaw channels status --probe  # deep probe all channels
openclaw channels capabilities  # per-provider features

Add & Configure

openclaw channels add           # add or update a channel account
openclaw channels login         # link a channel (if supported)
openclaw channels logout        # disconnect a session
openclaw channels remove        # disable or delete

Per-Channel Setup

Each channel type has different setup requirements. See references/channel-setup.md for:

  • WhatsApp (Web link via QR)
  • Telegram (Bot token)
  • Discord (Bot token + guild setup)
  • Matrix (homeserver + access token)

After adding a channel:

openclaw channels status --probe  # verify connection
openclaw channels capabilities    # check features
openclaw daemon restart           # if needed

Nodes

List & Status

openclaw nodes list             # all nodes (paired + pending)
openclaw nodes status           # connection status + capabilities
openclaw nodes pending          # pending pairing requests
openclaw nodes describe <name>  # detailed capabilities

Pairing

openclaw nodes approve <id>     # approve a pending request
openclaw nodes reject <id>      # reject a pending request
openclaw nodes rename <id> <name>  # set display name

Node Operations

openclaw nodes invoke <node> <cmd>    # invoke command on node
openclaw nodes run <node> <command>   # run shell command (mac only)
openclaw nodes camera <node>          # capture camera
openclaw nodes screen <node>          # capture screen
openclaw nodes canvas <node>          # capture/render canvas
openclaw nodes location <node>        # get location
openclaw nodes notify <node> <msg>    # send notification (mac only)

Running a Node Host

openclaw node run               # run headless node host (foreground)
openclaw node install           # install as system service
openclaw node status            # check node host status
openclaw node restart           # restart node host
openclaw node stop              # stop node host
openclaw node uninstall         # remove service

Node architecture and security: See references/node-pairing.md.


Models

Status

openclaw models status --probe  # probe all providers

Configure

Model configuration is done via openclaw config set (use openclaw-admin for the change discipline):

openclaw config get models      # current model config
openclaw config set agents.defaults.model "anthropic/claude-sonnet-4-5"
openclaw config set agents.defaults.subagents.model "anthropic/claude-haiku-3-5"

Best practice: Use a cheaper model for sub-agents to reduce costs.


Devices

List & Manage

openclaw devices list           # paired devices
openclaw devices approve <id>   # approve pairing request
openclaw devices reject <id>    # reject pairing request
openclaw devices revoke <id>    # revoke device token
openclaw devices rotate <id>    # rotate device token

Webhooks

Gmail Integration

openclaw webhooks gmail         # Gmail Pub/Sub hooks (via gogcli)

Skills

Inspect

openclaw skills list            # all skills
openclaw skills check           # readiness status
openclaw skills info <name>     # skill details

Extension Workflow

When adding a new capability:

  1. Install/add — Use the appropriate command
  2. Verify — Check it appears in the list
  3. Restart — openclaw daemon restart if gateway needs to load it
  4. Test — Probe or invoke to confirm it works
  5. Doctor — Run /openclaw-doctor to verify system health
Install → Verify → Restart → Test → Doctor

References

  • references/plugin-hook-authoring.md — How to write plugins and hooks
  • references/channel-setup.md — Per-channel setup guides
  • references/node-pairing.md — Node architecture, pairing flow, security

Related Skills

  • openclaw-doctor — Verify system health after adding new capabilities
  • openclaw-admin — Apply config changes with verify-apply-verify discipline
  • openclaw-maintain — Daemon ops, updates, cron, log rotation

平台分布

Codex

37.49%
按下载量换算41

Claude

27.63%
按下载量换算30

Cursor

17.65%
按下载量换算19

Gemini CLI

9.01%
按下载量换算10

安全审计

Gen Agent Trust Hub

未通过

Socket

可疑

Snyk

可疑

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills