What Are OpenClaw Tools and Skills? Complete Guide (25 Tools + 53 Skills)

Complete guide to OpenClaw's 25 tools and 53+ skills. Learn what each tool does, how to enable/disable them, install community skills, and create custom workflows.

Ashley Innocent

Ashley Innocent

5 March 2026

What Are OpenClaw Tools and Skills? Complete Guide (25 Tools + 53 Skills)

TL;DR

OpenClaw uses Tools and Skills to take action. Tools are low-level capabilities (read files, run commands, search web). Skills are pre-built workflows that combine multiple tools (code review, meeting summary). This guide explains all 25 default tools, 53+ community skills, how to enable/disable them, and how to create custom skills.

Tools vs Skills: Understanding the Difference

OpenClaw's power comes from two systems working together:

Tools = What OpenClaw CAN do (capabilities)
Skills = What OpenClaw KNOWS how to do (workflows)

Think of tools as organs and skills as learned behaviors. Tools give OpenClaw the ability to read files or execute commands. Skills teach it how to use those tools for specific tasks like reviewing code or summarizing meetings.

Example: Code Review

Without Skills (Tools Only):

You: "Review this pull request"
OpenClaw: "I can read files and search the web, but I don't know how to review code. Can you be more specific?"

With Skills:

You: "Review this pull request"
OpenClaw: [Uses code_review skill]
- Reads the changed files (read tool)
- Checks for common mistakes (analysis)
- Searches for similar issues (web_search tool)
- Posts comments (github tool)

Skills orchestrate tools to accomplish complex tasks.

The 25 Default Tools

Tools are built into OpenClaw. You enable or disable them based on what you trust OpenClaw to do.

File System Tools

1. read

What it does: Reads file contents
Use cases: View code, check configs, analyze logs
Security: Read-only, can't modify files
Example:

You: "Read package.json"
OpenClaw: [Shows file contents]

2. write

What it does: Creates or modifies files
Use cases: Generate code, update configs, create documents
Security: Can overwrite files—use carefully
Example:

You: "Create a file called test.txt with 'Hello World'"
OpenClaw: "Done. Created test.txt"

3. list

What it does: Lists files and directories
Use cases: Explore project structure, find files
Security: Read-only
Example:

You: "List files in src/"
OpenClaw: "src/ contains:
- api/
- components/
- utils/
- index.js"

What it does: Searches file contents (like grep)
Use cases: Find code patterns, locate functions
Security: Read-only
Example:

You: "Search for 'TODO' in all JavaScript files"
OpenClaw: "Found 12 matches:
- src/api/users.js:45
- src/utils/helpers.js:23
..."

Execution Tools

5. exec

What it does: Runs shell commands
Use cases: Run tests, build projects, deploy code
Security: HIGH RISK—can execute any command
Example:

You: "Run npm test"
OpenClaw: [Executes tests and shows results]

Security Note: Only enable exec if you trust OpenClaw completely. It can run destructive commands like rm -rf.

6. python

What it does: Executes Python code
Use cases: Data analysis, scripting, automation
Security: Can run arbitrary Python code
Example:

You: "Calculate the average of [10, 20, 30, 40]"
OpenClaw: [Runs Python] "Average: 25"

7. node

What it does: Executes Node.js code
Use cases: JavaScript scripting, API calls
Security: Can run arbitrary JavaScript
Example:

You: "Fetch data from https://api.example.com/users"
OpenClaw: [Runs Node.js fetch] "Retrieved 50 users"

Web Tools

8. web_search

What it does: Searches the internet (Google, Bing)
Use cases: Research, fact-checking, finding docs
Security: Low risk—read-only
Example:

You: "Search for OpenClaw documentation"
OpenClaw: "Found:
1. docs.openclaw.ai - Official docs
2. github.com/openclaw - Repository
..."

9. web_fetch

What it does: Downloads web page content
Use cases: Scrape data, read articles, monitor sites
Security: Low risk—read-only
Example:

You: "Fetch the content of https://example.com"
OpenClaw: [Downloads and shows page content]

10. web_screenshot

What it does: Captures screenshots of web pages
Use cases: Visual testing, monitoring, documentation
Security: Low risk
Example:

You: "Screenshot https://myapp.com"
OpenClaw: "Saved screenshot to screenshots/myapp.png"

Memory Tools

11. memory

What it does: Stores and retrieves information across sessions
Use cases: Remember preferences, save context
Security: Low risk—local storage only
Example:

You: "Remember that I prefer TypeScript over JavaScript"
OpenClaw: "Saved to memory."

[Later]
You: "Generate a new API endpoint"
OpenClaw: "Creating TypeScript endpoint..." [Uses remembered preference]

12. context

What it does: Manages conversation context
Use cases: Track multi-step tasks, maintain state
Security: Low risk
Example:

You: "I'm working on the user authentication feature"
OpenClaw: "Noted. I'll keep this context for our conversation."

You: "Add password validation"
OpenClaw: [Knows you're still working on auth] "Adding validation to the auth feature..."

Scheduling Tools

13. schedule

What it does: Creates recurring tasks (cron-like)
Use cases: Daily reports, monitoring, reminders
Security: Medium risk—runs tasks automatically
Example:

You: "Check Hacker News every morning at 8 AM and send me the top 3 posts"
OpenClaw: "Scheduled. I'll run this daily at 8 AM."

14. heartbeat

What it does: Runs background tasks at intervals
Use cases: Monitoring, polling, periodic checks
Security: Medium risk
Example:

You: "Monitor https://api.myapp.com every 5 minutes"
OpenClaw: "Heartbeat started. Checking every 5 minutes."

Communication Tools

15. email

What it does: Sends emails
Use cases: Notifications, reports, alerts
Security: Medium risk—can send emails on your behalf
Example:

You: "Email the team a summary of today's deployments"
OpenClaw: "Sent email to team@company.com"

16. slack

What it does: Posts to Slack channels
Use cases: Team notifications, alerts, updates
Security: Medium risk
Example:

You: "Post to #engineering: 'Deployment complete'"
OpenClaw: "Posted to #engineering"

17. discord

What it does: Sends Discord messages
Use cases: Community updates, bot interactions
Security: Medium risk
Example:

You: "Send a message to #general: 'Server maintenance in 10 minutes'"
OpenClaw: "Message sent to #general"

Integration Tools

18. github

What it does: Interacts with GitHub (repos, PRs, issues)
Use cases: Code reviews, issue management, deployments
Security: Medium risk—can modify repos
Example:

You: "Create an issue: 'Fix login bug on mobile'"
OpenClaw: "Created issue #456 in myapp repo"

19. jira

What it does: Manages Jira tasks
Use cases: Project management, task tracking
Security: Medium risk
Example:

You: "What tasks are assigned to me?"
OpenClaw: "You have 3 tasks:
- PROJ-123: Fix authentication
- PROJ-124: Update docs
- PROJ-125: Code review"

20. database

What it does: Queries databases (SQL, MongoDB)
Use cases: Data analysis, reporting, debugging
Security: HIGH RISK—can modify data
Example:

You: "How many users signed up today?"
OpenClaw: [Queries database] "47 new users today"

Utility Tools

21. calculator

What it does: Performs calculations
Use cases: Math, conversions, estimates
Security: No risk
Example:

You: "Calculate 15% of $1,250"
OpenClaw: "$187.50"

22. date_time

What it does: Handles dates and times
Use cases: Scheduling, time zones, calculations
Security: No risk
Example:

You: "What time is it in Tokyo?"
OpenClaw: "3:45 AM JST (March 6, 2026)"

23. image_gen

What it does: Generates images (DALL-E, Stable Diffusion)
Use cases: Thumbnails, mockups, illustrations
Security: Low risk—costs API credits
Example:

You: "Generate an image of a robot using a computer"
OpenClaw: [Generates image] "Saved to images/robot.png"

24. pdf

What it does: Creates and reads PDFs
Use cases: Reports, documentation, invoices
Security: Low risk
Example:

You: "Convert report.md to PDF"
OpenClaw: "Created report.pdf"

25. zip

What it does: Compresses and extracts files
Use cases: Backups, file transfers, archives
Security: Low risk
Example:

You: "Zip the src/ directory"
OpenClaw: "Created src.zip (2.3 MB)"

Managing Tools

View Enabled Tools

You: "What tools do I have enabled?"
OpenClaw: "Enabled tools:
✓ read, write, list, search
✓ web_search, web_fetch
✓ memory, context
✓ schedule, heartbeat
✗ exec (disabled)
✗ database (disabled)"

Enable a Tool

You: "Enable the exec tool"
OpenClaw: "⚠️ Warning: exec allows running shell commands. This is powerful but risky. Are you sure?"
You: "Yes"
OpenClaw: "Enabled exec tool"

Disable a Tool

You: "Disable the database tool"
OpenClaw: "Disabled database tool. I can no longer query databases."

Security Best Practices

Start Minimal:
Enable only the tools you need. You can always add more later.

High-Risk Tools:

Only enable these if you trust OpenClaw completely.

Medium-Risk Tools:

Enable these when you need automation but monitor their usage.

Low-Risk Tools:

Safe to enable by default.

The 53+ Community Skills

Skills are pre-built workflows. The community has created 53+ skills for common tasks.

Development Skills

code_review

What it does: Reviews code for quality, bugs, and style
Tools used: read, search, web_search, github
Example:

You: "Review PR #42"
OpenClaw: [Analyzes code, checks for issues, posts comments]

debug_assistant

What it does: Helps debug errors
Tools used: read, search, exec, web_search
Example:

You: "Debug this error: TypeError: Cannot read property 'name' of undefined"
OpenClaw: [Analyzes code, suggests fixes]

test_generator

What it does: Generates unit tests
Tools used: read, write, exec
Example:

You: "Generate tests for src/api/users.js"
OpenClaw: [Creates test file with comprehensive tests]

refactor_assistant

What it does: Suggests code improvements
Tools used: read, write, search
Example:

You: "Refactor src/utils/helpers.js"
OpenClaw: [Suggests improvements, applies changes]

Productivity Skills

meeting_summary

What it does: Summarizes meetings and extracts action items
Tools used: memory, context
Example:

You: [Forwards meeting transcript]
OpenClaw: [Generates structured summary with action items]

task_manager

What it does: Manages tasks across tools (Jira, Asana, Trello)
Tools used: jira, memory, schedule
Example:

You: "What's on my plate this week?"
OpenClaw: [Lists all tasks from connected tools]

email_assistant

What it does: Drafts and sends emails
Tools used: email, memory
Example:

You: "Draft an email to the team about tomorrow's deployment"
OpenClaw: [Generates professional email]

Content Skills

blog_writer

What it does: Writes blog posts
Tools used: web_search, write, memory
Example:

You: "Write a blog post about OpenClaw use cases"
OpenClaw: [Researches topic, writes comprehensive post]

social_media_manager

What it does: Creates social media content
Tools used: web_search, memory, slack
Example:

You: "Create a Twitter thread about our new feature"
OpenClaw: [Generates engaging thread]

video_script_writer

What it does: Writes video scripts
Tools used: web_search, write, memory
Example:

You: "Write a 10-minute YouTube script about OpenClaw setup"
OpenClaw: [Generates structured script]

Monitoring Skills

api_monitor

What it does: Monitors API health
Tools used: web_fetch, heartbeat, slack
Example:

You: "Monitor https://api.myapp.com"
OpenClaw: [Checks API every 5 minutes, alerts on issues]

error_tracker

What it does: Tracks and analyzes errors
Tools used: read, search, memory, slack
Example:

You: "Monitor error logs and alert me on new errors"
OpenClaw: [Watches logs, sends alerts]

deployment_watcher

What it does: Monitors deployments
Tools used: github, exec, slack
Example:

You: "Watch for new deployments and run smoke tests"
OpenClaw: [Monitors, tests, reports]

Installing Skills

Browse Available Skills

You: "List available skills"
OpenClaw: "Available skills:

**Development:**
- code_review
- debug_assistant
- test_generator
- refactor_assistant

**Productivity:**
- meeting_summary
- task_manager
- email_assistant

**Content:**
- blog_writer
- social_media_manager
- video_script_writer

**Monitoring:**
- api_monitor
- error_tracker
- deployment_watcher

Use 'install skill [name]' to add a skill."

Install a Skill

You: "Install skill code_review"
OpenClaw: "Installing code_review skill...

Required tools:
✓ read (enabled)
✓ search (enabled)
✓ web_search (enabled)
✗ github (not enabled)

Enable github tool? (y/n)"
You: "y"
OpenClaw: "Enabled github tool
✓ Installed code_review skill

Try it: 'Review PR #42'"

Uninstall a Skill

You: "Uninstall skill blog_writer"
OpenClaw: "Uninstalled blog_writer skill"

Creating Custom Skills

Skills are YAML files that define workflows. You can create your own.

Skill Structure

name: daily_standup
description: Generates daily standup report
tools:
  - jira
  - github
  - slack
steps:
  - action: query_jira
    query: "assignee = currentUser() AND status = 'In Progress'"
  - action: query_github
    query: "author:me is:pr is:open"
  - action: format_report
    template: |
      Daily Standup Report

      **Yesterday:**
      {completed_tasks}

      **Today:**
      {in_progress_tasks}

      **Blockers:**
      {blockers}
  - action: post_slack
    channel: "#standup"
    message: "{report}"

Example: Custom Backup Skill

name: backup_project
description: Backs up project files to cloud storage
tools:
  - zip
  - exec
steps:
  - action: create_zip
    source: "."
    output: "backup-{date}.zip"
    exclude:
      - node_modules
      - .git
  - action: upload
    command: "aws s3 cp backup-{date}.zip s3://my-backups/"
  - action: notify
    message: "✓ Backup complete: backup-{date}.zip"

Install Custom Skill

# Save skill to ~/.openclaw/skills/backup_project.yaml
openclaw skill install ~/.openclaw/skills/backup_project.yaml

Use it:

You: "Run backup_project skill"
OpenClaw: [Executes backup workflow]

Skill Combinations

Combine skills for powerful workflows.

Example: Automated Code Review + Deployment

You: "When a PR is merged to main, review the code, run tests, and deploy to staging"

OpenClaw: "Created workflow:
1. Monitor GitHub for merges to main
2. Run code_review skill
3. Run test_generator skill
4. If tests pass, run deployment_watcher skill
5. Post results to #engineering Slack

Workflow active."
💡
For API-focused projects, you can extend this workflow by integrating Apidog to automatically run API contract tests and update documentation after successful deployments.
button

Example: Content Pipeline

You: "Every Monday at 9 AM, research trending AI topics, write a blog post, and create a Twitter thread"

OpenClaw: "Created workflow:
1. Schedule: Monday 9 AM
2. Run trend_monitor skill
3. Run blog_writer skill
4. Run social_media_manager skill
5. Send draft for approval

Workflow scheduled."

Troubleshooting

Skill Fails to Install

Error: "Missing required tools"

Fix: Enable the required tools first:

You: "Enable tools: github, slack"
OpenClaw: "Enabled github and slack"
You: "Install skill code_review"
OpenClaw: "✓ Installed code_review"

Skill Doesn't Work as Expected

Error: "Skill execution failed"

Fix: Check skill logs:

You: "Show logs for code_review skill"
OpenClaw: [Shows detailed execution logs]

Tool Permission Denied

Error: "Permission denied: exec tool"

Fix: Enable the tool:

You: "Enable exec tool"
OpenClaw: "Enabled exec tool"

Best Practices

1. Start with Safe Tools

Enable read-only tools first:

Add execution tools (exec, write) only when needed.

2. Install Skills Gradually

Don't install all 53 skills at once. Start with 2-3 that solve immediate problems.

3. Review Skill Code

Before installing community skills, review the YAML file to understand what it does.

4. Monitor Usage

Check which tools and skills OpenClaw uses:

You: "Show tool usage stats"
OpenClaw: "Tool usage (last 7 days):
- read: 342 times
- web_search: 89 times
- write: 45 times
- exec: 12 times"

5. Create Skill Aliases

Shorten common commands:

You: "Create alias 'review' for 'run code_review skill'"
OpenClaw: "Alias created. Use 'review' to run code_review."

FAQ

Q: Can I disable all tools?
A: Yes, but OpenClaw won't be able to do much. It needs at least memory and context to function.

Q: Are skills safe?
A: Community skills are reviewed, but always check the code before installing. Malicious skills could misuse tools.

Q: Can I modify existing skills?
A: Yes, copy the skill YAML to ~/.openclaw/skills/ and edit it.

Q: How many skills can I install?
A: No limit, but too many skills slow down OpenClaw. Install only what you use.

Q: Do skills cost money?
A: Skills are free, but they may use tools that cost money (e.g., image_gen uses API credits).

Q: Can I share custom skills?
A: Yes, publish them to the OpenClaw community repository on GitHub.

Q: What if a skill breaks?
A: Uninstall it and report the issue to the skill author.

Q: Can skills access my files?
A: Only if you enable the read or write tools. Skills can't bypass tool permissions.

Conclusion

Tools give OpenClaw capabilities. Skills teach it workflows. Together, they transform OpenClaw from a chatbot into an automation powerhouse.

Start with safe tools (read, web_search, memory). Install a few skills that solve real problems (code_review, meeting_summary). As you gain confidence, enable more powerful tools (exec, database) and create custom skills.

The 25 tools and 53+ skills represent just the beginning. The OpenClaw community adds new capabilities daily. Join the ecosystem, share your custom skills, and help build the future of AI automation.

button

Explore more

Postman Old Pricing vs New Pricing: Did Postman Just Kill Free Teams?

Postman Old Pricing vs New Pricing: Did Postman Just Kill Free Teams?

Postman’s March 2026 pricing update changes the Free plan for teams: Free is now 1 user only. Here’s a clear old vs new pricing breakdown, what changed, and why many teams are looking at Postman alternatives like Apidog, which supports up to 4 users on its free plan.

4 March 2026

Test Suite vs Test Case: What's the Difference?

Test Suite vs Test Case: What's the Difference?

Learn the key differences between test suites and test cases in API testing. Complete guide with examples, best practices, and organization strategies.

4 March 2026

What is Gemini 3.1 Flash-Lite: The Fastest and Most Affordable Gemini Model Yet

What is Gemini 3.1 Flash-Lite: The Fastest and Most Affordable Gemini Model Yet

Gemini 3.1 Flash‑Lite is Google’s fastest, most affordable Gemini model yet—built for high‑volume API workloads. Learn its pricing, speed benchmarks, thinking levels, and real‑world use cases for Apidog, startups, and enterprises looking to cut AI costs without sacrificing quality.

4 March 2026

Practice API Design-first in Apidog

Discover an easier way to build and use APIs