Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问许可证需确认审计提醒

openclawOpenClaw 密钥安全

Agent Skill

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

总安装

235

周安装

10

GitHub Stars

公开资料未说明

下载量

82
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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(OpenClaw 密钥安全)
来源仓库:https://github.com/ohmyskyhigh/openclaw-doc
仓库路径:skills/openclaw
安装命令:
npx skills add https://github.com/ohmyskyhigh/openclaw-doc --skill openclaw
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/ohmyskyhigh/openclaw-doc --skill openclaw

简介

用于辅助文档、README、Markdown 和内容稿件的整理与改写。

  • 适合提炼结构、补齐章节、统一术语或检查链接。
  • 使用时应保留项目已有事实和路径,避免写成确定结论。
  • 涉及对外文案时需控制语气,避免过度营销或夸大能力。
  • openclaw 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

OpenClaw Documentation

OpenClaw is a self-hosted gateway that connects chat apps — WhatsApp, Telegram, Discord, iMessage, Slack, and more — to AI coding agents. A single Gateway process runs on your hardware and bridges messaging apps to an always-available AI assistant.

Requirements: Node 22+, an API key (Anthropic recommended), 5 minutes. Config: ~/.openclaw/openclaw.json Default dashboard: http://127.0.0.1:18789/

Quick start

npm install -g openclaw@latest
openclaw onboard --install-daemon
openclaw channels login
openclaw gateway --port 18789

Quick Reference

I want to...Read
Install OpenClawreferences/installation.md
Connect a chat platformreferences/channels-overview.md
Set up WhatsApp, Signal, iMessage, LINE, Telegram, Nostrreferences/channels-messaging-apps.md
Set up Discord, Slack, Teams, Mattermost, Google Chat, IRC, Matrix, Feishureferences/channels-team-platforms.md
Understand core architecture (runtime, workspace, sessions, compaction)references/core-concepts.md
Use the CLIreferences/cli-reference.md
Set up cron jobs, hooks, webhooks, Gmail PubSubreferences/automation.md
Configure agent tools and slash commandsreferences/tools.md
Run multiple agentsreferences/multi-agent.md
Deploy to cloud (exe.dev, Northflank, Fly.io, GCP, DigitalOcean)references/deployment.md
Manage secrets and gateway operationsreferences/gateway-operations.md
Use the web dashboard or TUIreferences/web-ui.md
Extend with plugins or configure model providersreferences/plugins-providers.md
Use macOS app, Voice Wake, or Androidreferences/platforms.md
Build, test, or contributereferences/development-reference.md

Reference files

references/overview.md

Home page: what OpenClaw is, how it works (Gateway as central hub), quick-start install, dashboard access, basic config.

references/core-concepts.md

Agent Runtime (pi-mono embedded runtime, bootstrap files), Agent Workspace (SOUL.md, USER.md, TOOLS.md, HEARTBEAT.md, memory/), System Prompt assembly, Compaction (context window management), Retry Policy (exponential backoff), Memory v2 Research (offline-first architecture).

references/channels-overview.md

Channel index (20+ platforms), Channel Routing (session key formats, routing priority), Groups (group policy, mention gating), Group Messages (WhatsApp-specific), Broadcast Groups (parallel/sequential multi-agent), Channel Location Parsing, Pairing (DM/device pairing, 8-char codes).

references/channels-messaging-apps.md

BlueBubbles/iMessage (tapbacks, effects, voice memos), Signal (signal-cli, QR pairing), LINE (Flex messages, quick replies), grammY/Telegram (webhook + long-poll), Nostr (NIP-04 encrypted DMs).

references/channels-team-platforms.md

Discord (guilds, forums, Components v2, voice, PluralKit), Slack (Socket Mode, Events API, threading, streaming), MS Teams (Azure Bot, Adaptive Cards, SharePoint), Mattermost (chat modes, reactions), Google Chat (HTTP webhooks), Feishu/Lark (WebSocket), Matrix (E2EE, Beeper), IRC (NickServ, per-channel tools), Nextcloud Talk, Synology Chat.

references/automation.md

Cron Jobs (one-shot at, recurring cron/every, isolated sessions), Cron vs Heartbeat decision guide, Hooks (event-driven TypeScript handlers, HOOK.md metadata), Webhooks (/hooks/wake and /hooks/agent), Gmail PubSub, Polls (cross-channel), Auth Monitoring (OAuth expiry, ntfy alerts), Troubleshooting.

references/cli-reference.md

All openclaw <command> subcommands: browser (tab/snapshot/screenshot management), completion (shell completions), dashboard (open Control UI), logs (tail Gateway logs), memory (semantic indexing/search), models (discovery, defaults, auth profiles), nodes (paired devices), status (channel/session diagnostics), system (enqueue events, heartbeat controls, presence).

references/tools.md

Tools Index (all first-class tools: apply_patch, exec, web_search, browser, canvas, nodes, cron, gateway, etc.), Slash Commands (/help, /status, /model, /think, /exec, /tts, /config, /debug, /reset, /stop, etc.), Reactions (cross-channel emoji semantics), Browser Login (Chrome profile auth), ClawHub (public skill registry), LLM Task (JSON-only tasks with schema validation).

references/gateway-operations.md

Heartbeat (periodic agent turns, intervals, HEARTBEAT_OK contract, active hours, visibility), Secrets Management (env/file/exec sources, 1Password/Vault/sops integration).

references/multi-agent.md

Multi-Agent Routing: running multiple isolated agents in one Gateway, routing rules (most-specific-wins bindings), DM splits, per-agent accounts, per-agent sandbox/tool policies.

references/installation.md

Install Overview (Node 22+, npm, curl one-liner, Docker/Podman/Nix/Ansible), Docker (Compose, ClawDock, persistent volumes, agent sandbox), Node.js (nvm/fnm/mise, PATH troubleshooting).

references/deployment.md

exe.dev (VM deploy, nginx proxy, device pairing), Northflank (one-click template, persistent storage).

references/platforms.md

macOS app (Skills via gateway, API key management, remote mode), Voice Wake (wake-word detection, push-to-talk).

references/plugins-providers.md

Plugin Agent Tools (registerTool API, allowlist/denylist), OpenAI Provider (API key, Codex, WebSocket/SSE transport).

references/web-ui.md

Control UI (Vite + Lit SPA: chat, channel status, sessions, cron, skills, nodes, exec approvals, config editing, logs, updates, Tailscale Serve for remote access).

references/development-reference.md

CI Pipeline (push + PR gates, smart scoping), RPC Adapters (JSON-RPC integration), TOOLS.md Template (environment notes), Tests (pnpm test, coverage, E2E, Docker smoke tests), OpenClaw Lore (community history), Onboarding Overview, Scripts.

Key Config Files & Paths

PathPurpose
~/.openclaw/openclaw.jsonMain Gateway configuration
~/.openclaw/credentials/Stored credentials and pairing state
~/.openclaw/agents/<id>/Per-agent workspace, sessions, state
~/.openclaw/hooks/User-managed hook directory
~/.openclaw/cron/Cron job storage (jobs.json)
Workspace: SOUL.mdAgent personality/identity
Workspace: USER.mdUser preferences for the agent
Workspace: TOOLS.mdLocal environment notes (cameras, SSH hosts, etc.)
Workspace: HEARTBEAT.mdChecklist for periodic heartbeat runs
Workspace: BOOT.md / BOOTSTRAP.mdExtra context injected at boot
Workspace: AGENTS.mdMulti-agent configuration
Workspace: memory/Agent memory files
Workspace: skills/Installed skills

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

35.36%
按下载量换算29

Claude

30.89%
按下载量换算25

Cursor

22.44%
按下载量换算18

Gemini CLI

9.29%
按下载量换算8

安全审计

Gen Agent Trust Hub

可疑

Socket

通过

Snyk

可疑

权限和风险

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 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills