
awesome-openclaw-skills
Browse and discover 5,200+ curated OpenClaw agent skills from the official skills registry, organized by category
- Installs
- 202
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/reason-machines/hermes-skills --skill awesome-openclaw-skills- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads awesome-openclaw-skills automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
awesome-openclaw-skills
Skill by ara.so — Hermes Skills collection.
A curated collection of 5,200+ OpenClaw agent skills filtered from the official ClawHub registry (13,729+ total). Skills are categorized by function (Git & GitHub, DevOps, AI & LLMs, Browser Automation, etc.) and vetted to exclude spam, duplicates, and low-quality entries.
What is OpenClaw?
OpenClaw is a locally-running AI assistant that operates directly on your machine. Skills extend its capabilities, allowing it to interact with external services, automate workflows, and perform specialized tasks.
This collection helps you:
- Discover skills by category (Git, DevOps, Marketing, etc.)
- Filter out spam, duplicates, and malicious skills
- Install via ClawHub CLI or manual setup
- Inspect security reports via VirusTotal integration
Installation
Browse the Collection
Visit the repository to explore categorized skills:
# Clone the repository
git clone https://github.com/VoltAgent/awesome-openclaw-skills.git
cd awesome-openclaw-skills
# Browse by category in README.md
cat README.md | grep "## Table of Contents" -A 50
Or visit online: clawskills.sh
Install a Skill
Option 1: ClawHub CLI (Recommended)
# Install the ClawHub CLI
npm install -g @openclaw/clawhub-cli
# Search for a skill
clawhub search "github automation"
# Install by slug
clawhub install steipete/slack
# Install with specific version
clawhub install steipete/slack@1.2.3
# List installed skills
clawhub list
# Update a skill
clawhub update steipete/slack
# Uninstall
clawhub uninstall steipete/slack
Option 2: Manual Installation
# 1. Find the skill's GitHub URL from awesome-openclaw-skills
# 2. Clone or download the skill folder
# 3. Copy to one of these locations:
# Global (available to all projects)
mkdir -p ~/.openclaw/skills/
cp -r skill-folder ~/.openclaw/skills/
# Workspace (project-specific)
mkdir -p ./skills/
cp -r skill-folder ./skills/
# Priority: Workspace > Global > Bundled
Option 3: Paste GitHub Link in Chat
Simply paste the skill's GitHub repository URL into your OpenClaw assistant chat:
https://github.com/openclaw/skills/tree/main/skills/steipete/slack
The assistant will handle installation automatically.
Key Categories
The collection is organized into 40+ categories:
| Category | Count | Examples |
|---|---|---|
| Coding Agents & IDEs | 1,184 | Code review, refactoring, IDE automation |
| Web & Frontend Development | 919 | React/Vue/Svelte tooling, CSS frameworks |
| DevOps & Cloud | 393 | Docker, Kubernetes, AWS, GCP, Terraform |
| Browser & Automation | 323 | Playwright, Puppeteer, web scraping |
| Search & Research | 345 | arXiv, Google Scholar, academic databases |
| Productivity & Tasks | 205 | Task management, note-taking, calendars |
| AI & LLMs | 176 | Model providers, RAG, embeddings |
| Image & Video Generation | 170 | DALL·E, Midjourney, video editing |
| Git & GitHub | 167 | PR automation, CI/CD, code review |
| Communication | 146 | Slack, Discord, email, SMS |
| CLI Utilities | 180 | File ops, text processing, shell scripts |
Full list: See Table of Contents in README.md
Usage Patterns
Finding Skills by Use Case
# 1. Clone the repo
git clone https://github.com/VoltAgent/awesome-openclaw-skills.git
cd awesome-openclaw-skills
# 2. Search by keyword
grep -i "docker" README.md
# 3. Browse by category
# Navigate to the category heading in README.md
# Each skill includes:
# - Name and ClawHub URL
# - One-line description
# - GitHub source link
Evaluating a Skill Before Install
-
Check ClawHub page for VirusTotal report:
https://clawskills.sh/skills/<author>/<skill-name> -
Review source code on GitHub:
https://github.com/openclaw/skills/tree/main/skills/<author>/<skill-name> -
Check for:
- Recent updates (skill may be abandoned if >1 year old)
- Security flags in VirusTotal report
- Permissions requested (file access, network, API keys)
- Clear documentation and examples
Example: Installing a GitHub Automation Skill
# 1. Find skill in awesome-openclaw-skills
# Category: Git & GitHub
# Skill: auto-pr-merger by autogame-17
# 2. Check ClawHub page
open https://clawskills.sh/skills/autogame-17/auto-pr-merger
# 3. Install via CLI
clawhub install autogame-17/auto-pr-merger
# 4. Configure (if needed)
# Most skills use environment variables:
export GITHUB_TOKEN="ghp_your_token_here"
# 5. Use in OpenClaw chat
# "Auto-merge all approved PRs in my repo"
Configuration
Skill Locations (Priority Order)
OpenClaw searches for skills in this order:
- Workspace (highest priority):
<project>/skills/ - Global:
~/.openclaw/skills/ - Bundled: Built-in OpenClaw skills
Example directory structure:
~/.openclaw/skills/
├── steipete/
│ └── slack/
│ ├── skill.yaml
│ ├── index.js
│ └── README.md
└── autogame-17/
└── auto-pr-merger/
├── skill.yaml
└── main.py
./my-project/skills/ # Overrides global
├── custom-skill/
│ └── skill.yaml
Environment Variables
Most skills require API keys or tokens. Never hardcode secrets — use environment variables:
# GitHub
export GITHUB_TOKEN="ghp_..."
# Slack
export SLACK_BOT_TOKEN="xoxb-..."
export SLACK_SIGNING_SECRET="..."
# AWS
export AWS_ACCESS_KEY_ID="..."
export AWS_SECRET_ACCESS_KEY="..."
# OpenAI (for AI-powered skills)
export OPENAI_API_KEY="sk-..."
Or use a .env file (ensure it's in .gitignore):
# .env
GITHUB_TOKEN=ghp_your_token
SLACK_BOT_TOKEN=xoxb_your_token
# Load in shell
source .env
# Or use dotenv in code (Node.js example)
require('dotenv').config();
Code Examples
Programmatic Skill Discovery
Node.js: Parse README.md and extract skills by category
const fs = require('fs');
// Read the awesome-openclaw-skills README
const readme = fs.readFileSync('README.md', 'utf-8');
// Extract skills from a category
function extractSkills(category) {
const regex = new RegExp(
`<summary><h3[^>]*>${category}</h3></summary>([\\s\\S]*?)</details>`,
'i'
);
const match = readme.match(regex);
if (!match) return [];
const skillRegex = /- \[(.*?)\]\((https:\/\/clawskills\.sh\/skills\/.*?)\) - (.*)/g;
const skills = [];
let skillMatch;
while ((skillMatch = skillRegex.exec(match[1])) !== null) {
skills.push({
name: skillMatch[1],
url: skillMatch[2],
description: skillMatch[3],
slug: skillMatch[2].replace('https://clawskills.sh/skills/', '')
});
}
return skills;
}
// Example: Get all Git & GitHub skills
const gitSkills = extractSkills('Git & GitHub');
console.log(`Found ${gitSkills.length} Git & GitHub skills:`);
gitSkills.slice(0, 5).forEach(skill => {
console.log(`- ${skill.name}: ${skill.description}`);
});
Python: Install Top Skills from a Category
import re
import subprocess
def get_skills_from_category(readme_path, category):
with open(readme_path, 'r') as f:
content = f.read()
# Find category section
pattern = rf'<summary><h3[^>]*>{re.escape(category)}</h3></summary>(.*?)</details>'
match = re.search(pattern, content, re.DOTALL | re.IGNORECASE)
if not match:
return []
# Extract skills
skill_pattern = r'- \[(.*?)\]\(https://clawskills\.sh/skills/(.*?)\) - (.*)'
skills = []
for m in re.finditer(skill_pattern, match.group(1)):
skills.append({
'name': m.group(1),
'slug': m.group(2),
'description': m.group(3)
})
return skills
# Install top 3 DevOps skills
devops_skills = get_skills_from_category('README.md', 'DevOps & Cloud')
for skill in devops_skills[:3]:
print(f"Installing {skill['name']}...")
subprocess.run(['clawhub', 'install', skill['slug']], check=True)
Bash: Bulk Install Skills from a List
#!/bin/bash
# skills.txt contains one skill slug per line:
# steipete/slack
# autogame-17/auto-pr-merger
# pals-software/azure-devops
while IFS= read -r slug; do
echo "Installing $slug..."
clawhub install "$slug"
if [ $? -eq 0 ]; then
echo "✓ $slug installed"
else
echo "✗ $slug failed"
fi
done < skills.txt
Security & Best Practices
Before Installing ANY Skill
-
Review the source code:
# Clone the official skills repo git clone https://github.com/openclaw/skills.git cd skills/skills/<author>/<skill-name> # Read the code cat skill.yaml index.js README.md -
Check VirusTotal report on ClawHub:
- Green = No flags
- Yellow = Low-confidence flags (may be false positives)
- Red = Multiple engines flagged as malicious
-
Look for red flags:
- Obfuscated code (base64, eval, exec)
- Unexpected network requests
- File system access outside project directory
- Requests for unnecessary permissions
Recommended Security Tools
# Snyk Skill Security Scanner
npm install -g @snyk/agent-scan
agent-scan ~/.openclaw/skills/steipete/slack
# Agent Trust Hub (Norton/GenDigital)
# Visit: https://ai.gendigital.com/agent-trust-hub
# Upload skill.yaml for analysis
Permissions Model
Skills declare required permissions in skill.yaml:
name: github-pr-automation
permissions:
- network: ["github.com", "api.github.com"]
- filesystem: ["read", "write"] # Limit to project dir
- env: ["GITHUB_TOKEN"]
Always verify permissions match the skill's stated functionality.
Common Patterns
Pattern 1: Find and Install a Domain-Specific Skill
# Use case: "I need a skill for Kubernetes deployments"
# 1. Search locally
grep -i "kubernetes" awesome-openclaw-skills/README.md
# 2. Or search ClawHub
clawhub search "kubernetes deployment"
# 3. Review top results
open https://clawskills.sh/skills/cloudops/k8s-deploy
# 4. Check source
open https://github.com/openclaw/skills/tree/main/skills/cloudops/k8s-deploy
# 5. Install
clawhub install cloudops/k8s-deploy
# 6. Configure
export KUBECONFIG="~/.kube/config"
# 7. Use in chat
# "Deploy my app to the production cluster using k8s-deploy"
Pattern 2: Build a Custom Skill Collection
# Create a workspace-specific skills directory
mkdir -p ./skills
# Install project-relevant skills locally
cd skills
clawhub install steipete/slack --target ./
clawhub install pals-software/azure-devops --target ./
clawhub install docker-compose-runner --target ./
# Commit to version control
git add skills/
git commit -m "Add project-specific OpenClaw skills"
# Team members get skills automatically
git clone <repo>
# OpenClaw will auto-discover ./skills/
Pattern 3: Monitor Skill Updates
# List installed skills with versions
clawhub list --verbose
# Check for updates
clawhub outdated
# Update all
clawhub update --all
# Update specific skill
clawhub update steipete/slack
Troubleshooting
Skill Not Found in ClawHub
Problem: clawhub install author/skill returns "Not found"
Solutions:
- Verify slug on clawskills.sh
- Check if skill was removed from registry (happens with abandoned/malicious skills)
- Try manual installation from GitHub:
git clone https://github.com/openclaw/skills.git cp -r skills/skills/author/skill ~/.openclaw/skills/
Skill Installed but Not Available
Problem: OpenClaw doesn't recognize the skill
Solutions:
-
Check installation path:
ls ~/.openclaw/skills/ ls ./skills/ # Workspace overrides global -
Verify
skill.yamlexists:cat ~/.openclaw/skills/author/skill/skill.yaml -
Restart OpenClaw:
openclaw restart -
Check logs:
openclaw logs | grep -i "skill"
Permission Errors
Problem: Skill fails with "Permission denied"
Solutions:
- Grant required permissions in OpenClaw settings
- Check environment variables:
echo $GITHUB_TOKEN # Should not be empty - Verify API token scopes match skill requirements
Skill Conflicts
Problem: Two skills with similar triggers interfere
Solutions:
-
Disable one skill:
clawhub disable author/skill -
Use workspace skills to override global:
# Install preferred version in ./skills/ clawhub install author/skill --target ./skills/ -
Rename skill triggers in
skill.yaml(advanced)
Outdated or Abandoned Skills
Problem: Skill hasn't been updated in 1+ years
Solutions:
-
Check for forks/alternatives:
clawhub search "slack automation" -
Contact author via GitHub (link in ClawHub page)
-
Fork and maintain yourself:
git clone https://github.com/openclaw/skills.git cd skills/skills/author/old-skill # Make updates # Submit PR to openclaw/skills
Contributing
This list only includes skills already published in github.com/openclaw/skills.
To Add a Skill
-
Publish to ClawHub first:
cd my-skill clawhub publish -
Open PR to awesome-openclaw-skills:
- Include ClawHub URL:
https://clawskills.sh/author/skill - Include GitHub URL:
https://github.com/openclaw/skills/tree/main/skills/author/skill - Follow format in existing categories
- Include ClawHub URL:
See CONTRIBUTING.md
Reporting Security Issues
If a skill is malicious or has a security flaw:
- Do not install it
- Open an issue: github.com/VoltAgent/awesome-openclaw-skills/issues
- Include:
- Skill slug
- VirusTotal report link
- Description of the issue
Resources
- ClawHub Registry: clawskills.sh
- Official Skills Repo: github.com/openclaw/skills
- OpenClaw Docs: docs.openclaw.dev
- Security Tools:
- VoltAgent Ecosystem:
Related Skills
- agent-skill-discovery – Auto-suggest skills based on project dependencies
- clawhub-curator – Bulk install/update skills from curated lists
- skill-security-audit – Run automated security checks on installed skills
License: MIT
Maintained by: VoltAgent (voltagent.dev)
Last Updated: May 16, 2026
Skill Count: 5,211 (filtered from 13,729)
FAQ
What does the awesome-openclaw-skills skill do?
Browse and discover 5,200+ curated OpenClaw agent skills from the official skills registry, organized by category
How do I install awesome-openclaw-skills?
Run npx skills add https://github.com/reason-machines/hermes-skills --skill awesome-openclaw-skills in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/awesome-openclaw-skills/ (personal) or .claude/skills/awesome-openclaw-skills/ (project).
Which AI agents can use awesome-openclaw-skills?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is awesome-openclaw-skills safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains awesome-openclaw-skills?
It is published by reason-machines in reason-machines/hermes-skills. It has 202 recorded installs.
More from reason-machines/hermes-skills
hermes-agent-self-evolution
reason-machines/hermes-skills
Evolutionary self-improvement for Hermes Agent using DSPy + GEPA to optimize skills, prompts, and code
hermes-webui-agent
reason-machines/hermes-skills
Expert in deploying, configuring, and using Hermes WebUI—a web interface for Hermes Agent with persistent memory, scheduled jobs, and multi-platform messaging.
awesome-hermes-agent-ecosystem
reason-machines/hermes-skills
Open the skill to read its SKILL.md instructions.
hermes-agent-framework
reason-machines/hermes-skills
Open the skill to read its SKILL.md instructions.
hermes-workspace-ai-agent-ui
reason-machines/hermes-skills
Open the skill to read its SKILL.md instructions.
hermes-desktop-companion
reason-machines/hermes-skills
Open the skill to read its SKILL.md instructions.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available