OpenClaw Master Skills
A curated collection of 1209+ best OpenClaw skills, updated weekly by MyClaw.ai.
- Source repo
- LeoYeAI/openclaw-master-skills
- Stars
- ★ 2.2k
- Last updated
- 3mo ago
- License
- MIT
- Primary language
- Python
- FA score
- 12/100 · Major gaps
At a glance
- How it runs
- Works with
- Platform-specific
- Cost
- Free software; you pay for model usage
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- Developers wanting to rapidly expand their OpenClaw agent's skill set with a one-command install of 1200+ skills.
- Not a fit if
- Teams not using the OpenClaw platform
- Users expecting consistent, complete skill descriptions
- Source review
- 12/100 · Major gaps 8 safety controls not found
What does this agent do, and when should you use it?
OpenClaw Master Skills is a curated repository of over 1209 OpenClaw skills, updated weekly by MyClaw.ai. The repository includes an index of 561 skills organized by category (AI & LLM, Search & Web, Productivity & Office, Development & DevOps, Marketing & Growth, Media & Creative, Finance & Trading, Communication & Messaging, Smart Home & IoT, Memory & Agent Enhancement, Security & Auditing, Data & Analytics, Social & Content, and Other). Each skill is a directory containing a SKILL.md file. Installation is via ClawHub (command: clawhub install openclaw-master-skills) or manual git clone and copy to ~/.openclaw/workspace/skills/. The repository is licensed under MIT.
This repository provides a structured collection of skills for installation via ClawHub CLI or manual copy. It indexes a vast number of skills, each encapsulating specific capabilities such as browser automation, PDF editing, search engine integrations, financial analysis, messaging platform integrations, and more. Users can install the entire collection with 'clawhub install openclaw-master-skills' or select individual skill directories from the skills/ folder to copy into the OpenClaw workspace. Skills typically contain a SKILL.md definition and executable scripts, enabling OpenClaw agents to perform tasks like web searching, document parsing, social media management, smart home control, etc. The collection is updated weekly by MyClaw.ai.
- Developers wanting to rapidly expand their OpenClaw agent's skill set with a one-command install of 1200+ skills.
- Users needing browser automation like agent-browser or playwright for web testing and data extraction.
- Office workers requiring document processing such as pdf, docx, and pptx skills to create and edit files.
- Investors monitoring stocks and crypto using financial skills like stock-analysis and tushare-finance.
- Smart home enthusiasts automating devices via home-assistant and openhue skills.
- Developers enhancing agent memory and security with memory-manager and skill-vetter.
How do you install or deploy this agent?
Installation:
- Install a single skill via ClawHub:
clawhub install openclaw-master-skills- Or clone and copy manually:
git clone https://github.com/LeoYeAI/openclaw-master-skills.git
cp -r openclaw-master-skills/skills/<skill-name> ~/.openclaw/workspace/skills/Requires OpenClaw CLI and git.
How do you use this agent?
Usage:
- After installation, skills are located in ~/.openclaw/workspace/skills/ or managed via ClawHub.
- In an OpenClaw session, the agent can automatically invoke skills based on requests, e.g., using 'summarize' to summarize URLs or files.
- Alternatively, copy a specific skill directory into the workspace to enable it individually.
- Skills may require additional API keys or dependencies; refer to each skill's SKILL.md.
What are this agent's strengths and limitations?
- Large collection (1209+) covering many domains, saving time finding and installing individual skills.
- Weekly updates keep skills in sync with the ecosystem.
- ClawHub installation simplifies management.
- Each skill is a self-contained directory, enabling selective deployment.
- Tied to the OpenClaw platform; not applicable to other agent frameworks.
- Skill quality varies; some have incomplete descriptions or require specific API keys.
- Requires network access to clone and install dependencies.
- While the repo is MIT, individual skills may have their own licenses or restrictions.
How does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| OpenClaw Master Skills This agent | 12 · Major gaps | CLIFree + model costs | ★ 2.2k | 3mo ago | Python | — |
| Narrator AI CLI Skill | 51 · Major gaps | Agent plugin / skillFree + model costs | ★ 3.1k | 3mo ago | — | Codex · Claude Code |
| ClawMetry | 81 · Good | CLIFreemium | ★ 432 | 1d ago | Python | Codex · Claude Code |
| SkillHub | 56 · Major gaps | Self-hosted serviceFree | ★ 5.2k | today | Java | Codex |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence shows the repository contains only README, LICENSE, and a few test files, with no documentation on permissions, user confirmation, data flow, sensitive data handling, dependency security, external effects, rollback, or source attribution. Hence all trust criteria score 0.
Test files show internal consistency (e.g., test function naming and assertions), but no dependency availability information is provided, and failure messages are only partially reflected in tests. Thus self-consistency scores 1, dependency availability 0, failure messages 1.
README mentions targeting OpenClaw users, but does not clearly define audience and scenarios; no capability boundaries, trigger precision, or environment fit are defined. Hence audience and scenarios score 1, others 0.
README provides installation instructions and MIT license, but lacks information architecture, naming stability, examples/FAQ, known limitations, versioning/changelog, and maintenance responsibility. Thus information architecture 1, install notes 1, license 2, maintenance responsibility 1, others 0.
Tests show output usability (e.g., generating summaries), but no evidence of actual value or cost-benefit. Hence output usability 1, marginal value 1, cost-benefit 0.
The repository provides no traceable claims, cross-source corroboration, or separation of facts and inferences. Hence all criteria score 0.
- Not found in source: least-privilege scopingGrant only what the task needs: a dedicated account or read-only token, scoped to specific directories and repos.
- Not found in source: confirmation before actingTurn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
- Not found in source: data-flow disclosureWatch which external services it contacts (proxy or firewall logs) and keep sensitive data out until you know where it goes.
- Not found in source: sensitive-data handlingUse dedicated, low-privilege, revocable API keys — never production credentials — and keep secrets out of logs.
- Not found in source: dependency securityPin versions and run a dependency audit (npm audit, pip-audit) before installing; prefer running it in a container.
- Not found in source: disclosed external effectsEstablish which external systems it writes to, sends to or changes, and verify with test accounts or repos before production.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- Not found in source: verifiable attributionInstall from the official repo or registry and check the publisher and URL to avoid look-alike packages.
- The repository contains only a few test files, with no actual skill code or documentation, making it impossible to assess real functionality.
- No security or permission-related documentation is provided; caution is advised before use.
- Publisher identity is unverified, and there is no versioning or changelog, making maintenance responsibility unclear.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
v0.21.0 v0.21.0 — Weekly Update
Release notes excerpt
🚀 周更：新增 100 个 Skills，总计 2409 来源：openclaw/skills-archive 官方镜像，按质量规则筛选。 详见仓库内 RELEASES.md。View on GitHub ↗ -
v0.18.0 v0.18.0 — Weekly Update
Release notes excerpt
🚀 周更：新增 100 个 Skills，总计 2109 来源：openclaw/skills-archive 官方镜像，按质量规则筛选。 详见仓库内 RELEASES.md。View on GitHub ↗ -
v0.17.0 v0.17.0 — Weekly Update
Release notes excerpt
🚀 周更：新增 100 个 Skills，总计 2009 来源：openclaw/skills-archive 官方镜像，按质量规则筛选。 详见仓库内 RELEASES.md。View on GitHub ↗