Skills & Plugins

Extend OpenClaw with Skills and create your own

OpenClaw skills are plugins that add tools, knowledge, and workflows. To pick which skills to try, browse the full list of available skills from ClawHub (calendar, Slack, GitHub, smart home, and hundreds more). Install the ones you want with one command; use openclaw skills list to see what's already installed on your machine. You can also write your own or run automation with them.

What skills are

A skill gives the agent new capabilities in a single package. It might add tools (e.g. call an API, run a script, read a calendar), inject domain knowledge or instructions, wire in an external service, or define a workflow. Everything lives under ~/clawd/skills/<skill-name>/SKILL.md (or your configured workspace path). You manage skills via the CLI, by editing files, or through ClawHub. Which skills are active is controlled in configuration (enable/disable, per-skill settings like API keys). To get an install script for a skill (with optional API keys), use the Setup Wizard (Add a skill).

OpenClaw skills list – browse available skills to try

If you're looking for a complete list of available OpenClaw skills so you can choose which ones to try, that list lives on ClawHub and in the community catalog. You can browse by category, search by name or use case, and install any skill with one command.

  • ClawHub – Browse and search the full list at clawhub.ai/skills (calendar, Slack, Discord, GitHub, smart home, Moltbook, and hundreds more). Pick a skill, then install with npx clawdhub@latest install <skill-name>. Browse by category: Productivity, Dev & Infrastructure, Research, Media, Channels.
  • Awesome OpenClaw Skills – Curated list of popular skills (GitHub and community). Good starting point to see what others use.

Below is a sample of skills available on ClawHub. This list is for discovery only—we do not endorse or guarantee the security of any third-party skill. Always review a skill's SKILL.md and scripts before installing. See the Security guide.

Sonos CLIControl Sonos speakers.
Caldav CalendarCalDAV calendars (iCloud, Google, Fastmail, Nextcloud).
Calendar use case
TrelloBoards, lists, cards.
Apple RemindersApple Reminders integration.
SlackSlack messages and channels.
Slack setup
DiscordDiscord server integration.
Discord setup
MoltbookMoltbook AI agent network.
Moltbook guide
GitHub Token / GitGitHub API and Git from chat.
Code assistant
Deep Research AgentDeep research and web search.
Research use case
Google Workspace (gws)100+ skills: Gmail, Drive, Calendar, Sheets, Docs, Chat, Admin, Meet, Forms, Keep. First-class OpenClaw support.
Google Workspace tutorial
Gmail / EmailRead and send email.
Email use case
TodoistTodoist tasks and projects.
Task automation
NotionNotion pages and databases.
WeatherWeather and forecasts.
n8nn8n workflows.
OpenClaw + n8n
JiraJira issues and sprints.
WhatsAppWhatsApp-related skills.
WhatsApp setup
SignalSignal messaging.
Signal setup
D&D 5eD&D 5e rules and character help.
SpotifyMusic playback and search.
Google DriveGoogle Drive and cloud storage.
File organization
FastmailFastmail email.
Microsoft TeamsTeams integration.
Teams setup
TelegramTelegram bot features.
Telegram setup
LinearLinear issues and projects.
AsanaAsana tasks and workspaces.
RSSRSS feed reading.
ObsidianObsidian notes integration.
Knowledge base
ByteRoverStructured long-term memory and context tree. Automatic memory flush at compaction, daily knowledge mining, context plugin. Local & cloud, version control. Install from ClawHub.
ClawHub · ByteRover + OpenClaw docs
PDFPDF reading and extraction.
DockerDocker container operations.
Docker deployment
KubernetesKubernetes and kubeconfig.
TerraformTerraform and IaC.
AWSAWS APIs and CLI.
VercelVercel deployments.
SupabaseSupabase database and auth.
FirebaseFirebase services.
TranslationLanguage translation.
SummarizerText summarization.
Code runnerRun code snippets.
Code assistant
Maps / LocationMaps and location lookup.
NextcloudNextcloud files and calendar.
Web searchWeb search and browsing.
GhostFetchStealth web fetch for X.com, LinkedIn, protected sites; bypasses 403/Cloudflare, returns clean Markdown.
GhostFetch on GitHub
PinchTabStandalone HTTP browser bridge. Token-efficient (~800 tokens/page), multi-instance, headless/headed. CLI + HTTP API.
pinchtab on GitHub · Browser guide
camofox-browserHeadless browser plugin (Camoufox, C++ fingerprint spoofing) for X, Product Hunt, Amazon; accessibility snapshots for LLM context.
camofox-browser on GitHub
Image generationImage generation APIs.
Content creation
Speech / TTSText-to-speech and speech.
Voice
Habit trackerHabits and streaks.
Expenses / FinanceExpense tracking and finance.
ClawRouterSmart LLM router: route each request to the cheapest capable model. 41+ models, token compression & cache, one wallet, pay-per-request (USDC). 5K+ stars on GitHub.
ClawRouter guide · GitHub

Browse the full list, search, and install at clawhub.ai/skills. After you install skills, use openclaw skills list to see what's on your machine (see Check your installed skills below). To install and manage skills, see Using skills from ClawHub.

Check your installed skills (openclaw skills list command)

To see what's already installed in your workspace, run the openclaw skills list command:

List installed skills
openclaw skills list

That shows every skill in ~/clawd/skills/ (or your workspace skills directory): skill names, paths to each SKILL.md, and whether each is enabled in config. You can also open the folder in the file system to edit skills. To add more, browse the list of available skills above or install from ClawHub.

Using skills from ClawHub

ClawHub is the community skill registry for OpenClaw: browse the full skills list at ClawHub.ai, install with one command, and publish your own. Skills are versioned (like npm) and searchable. Awesome OpenClaw Skills is a curated list; source and docs: ClawHub repo.

VirusTotal scanning on ClawHub. Skills published to ClawHub are scanned with VirusTotal (including Code Insight). Scan status and links to reports appear on each skill page. Benign skills are auto-approved; suspicious or malicious ones are flagged or blocked. This adds a layer of protection—still review permissions and use sandboxing for untrusted skills. Details: OpenClaw partners with VirusTotal for skill security; Security guide.

Install a skill by name with the ClawHub CLI. It drops the skill into your workspace and wires it in:

Install Skill
npx clawdhub@latest install <skill-name>

Example: npx clawdhub@latest install sonoscli. You can also copy a skill's files into ~/clawd/skills/<skill-name>/ yourself, or ask OpenClaw in chat to install or create a skill. For a full walkthrough (install, update, enable/disable), see the Skills Management tutorial.

Security: malicious skills

ClawHub is open—anyone can publish. Malicious skills have been found that try to steal keys, exfiltrate data, or run unwanted code. Before installing, especially from unknown authors, review the skill's SKILL.md and any scripts: look for access to wallets, sensitive paths, or external APIs that don't match the skill's purpose; obfuscated or vague instructions; or skills with no reviews. Use sandboxing for untrusted skills and report bad ones to the community. More: Security guide.

Creating your own skills

You add capabilities by dropping a skill folder into ~/clawd/skills/ with a SKILL.md that describes the skill, its tools, and when the agent should use them. No separate runtime—the agent reads the Markdown and follows the instructions. A step-by-step walkthrough is in the Creating Your First Skill tutorial; below is the minimal structure.

Create the folder, then add SKILL.md:

Create skill directory
mkdir -p ~/clawd/skills/my-skill
Example SKILL.md
# My Custom Skill

## Description
This skill adds custom functionality to OpenClaw.

## Tools
- `my_tool`: Does something useful

## Instructions
When the user asks about X, use my_tool to handle it.

## Examples
- "Do X" → Uses my_tool
- "Show me Y" → Provides Y information

Once the file is in place, enable the skill in configuration (or rely on default loading). The agent will then use the tools and instructions when relevant to the conversation.

Having OpenClaw create a skill for you

Instead of writing SKILL.md yourself, you can describe what you want in chat. For example: "Create a skill to integrate with Todoist," "Add a skill for weather," or "Build a skill that monitors my GitHub repos." OpenClaw will interpret the request, generate the skill files, put them in your workspace, and you can test and tweak from there. Useful when you know the outcome you want but not the exact structure—see also Creating Your First Skill if you prefer to build one manually.

Skill configuration

Which skills are on and how they're configured is set in ~/.clawdbot/moltbot.json (filename kept for backward compatibility). Use skills.enabled to turn skills on or off, and add a block per skill for API keys or other settings the skill expects.

Example: enable skills and per-skill settings
{
  "skills": {
    "enabled": ["my-skill", "another-skill"],
    "my-skill": {
      "apiKey": "your-api-key",
      "settings": {
        "option": "value"
      }
    }
  }
}

Full options are in the Configuration reference.

Managing skills

See what's installed: openclaw skills list. Add new ones from ClawHub with npx clawdhub@latest install <skill-name> (versioned; you can pin or roll back). To turn a skill on or off, edit skills.enabled in ~/.clawdbot/moltbot.json (Configuration reference), or ask OpenClaw in chat to enable/disable. Updates: re-run the ClawHub install for that skill, or edit the files under ~/clawd/skills/<skill-name>/. Full flow: Skills Management tutorial.

Skill best practices

Keep each skill focused on one job, document it (description + examples), and handle errors so the agent doesn't break on bad input. Test before relying on it in production. If you publish to ClawHub, others can install and rate it—and reviewing community skills before use is part of staying safe (Security guide).

Go deeper