Курируемый awesome-список · открыть репозиторий ↗
Источник: awesome-openclaw-skills — синхронизируется из внешнего репозитория как sparse-субмодуль (только список).
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 and install the right skills for your needs. It can also serve as a source of inspiration for OpenClaw use cases.
Skills in this list are sourced from ClawHub (OpenClaw’s public skills registry) and categorized for easier discovery.
openclaw skills install <skill-slug>Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install <skill-slug>Copy the skill folder to one of these locations:
| Location | Path |
|---|---|
| Global | ~/.openclaw/skills/ |
| Workspace | <project>/skills/ |
Priority: Workspace > Local > Bundled
You can also paste the skill’s GitHub repository link directly into your assistant’s chat and ask it to use it. The assistant will handle the setup automatically in the background.
OpenClaw’s public registry (ClawHub) hosts thousands of community-built skills. This awesome list curates the best of them. Here’s what we filtered out:
| Filter | Excluded |
|---|---|
| Possibly spam — bulk accounts, bot accounts, test/junk | 4,065 |
| Duplicate / Similar name | 1,040 |
| Low-quality or non-English descriptions | 851 |
| Crypto / Blockchain / Finance / Trade | 886 |
| Malicious — identified by security audits published by researchers (excluding VirusTotal) | 373 |
| Total not taken from OpenClaw’s official skill registry | 7,215 |
This list only includes skills that are already published on ClawHub, OpenClaw’s public skills registry. We do not accept links to personal repos, gists, or any other external source. If your skill isn’t on ClawHub yet, publish it there first.
Include the ClawHub link for your skill (e.g. https://clawhub.ai/steipete/slack) in your PR description — the clawskills.sh listings are managed by us separately. See CONTRIBUTING.md for details.
You can deploy OpenClaw on any VPS or cloud platform to run your skills securely on your own infrastructure, or use a managed host that handles servers, updates, and isolation for you.
Tip: If you’re self-hosting, pin your OpenClaw Docker image to a specific tag and snapshot your skills volume before upgrades — makes rollbacks painless when a skill update misbehaves.
OpenClaw agents often need fresh, real-world data — search results, product listings, videos, and more. You can scrape and parse it yourself, or use a search API that returns clean, structured data in real time without managing proxies, CAPTCHAs, or HTML parsing.
As you add more skills, custom code, and connected services, your OpenClaw setup accumulates secrets, file access, and tool permissions that are easy to lose track of. You can review these by hand, or run a continuous audit that surfaces misconfigurations and over-broad permissions before they become a problem.
OpenClaw works with 25+ LLM providers out of the box Anthropic, OpenAI and many more. Switch between them with a single config change.
OpenClaw supports gpt-5.4 and gpt-5.4-pro via direct API key or ChatGPT/Codex OAuth. WebSocket transport is enabled by default for lower latency.
openclaw onboard --auth-choice openai-api-key
# or use subscription-based access:
openclaw onboard --auth-choice openai-codex🦞 You can feature your OpenClaw ecosystem tool in the section above.The #1 most visited community resource after the official OpenClaw resource |
Skills in this list are curated, not audited. They may be updated, modified, or replaced by their original maintainers at any time after being added here.
Before installing or using any Agent Skill, review potential security risks and validate the source yourself. OpenClaw has a VirusTotal partnership that provides security scanning for skills, visit a skill’s page on ClawHub and check the VirusTotal report to see if it’s flagged as risky.
Recommended tools:
Agent skills can include prompt injections, tool poisoning, hidden malware payloads, or unsafe data handling patterns. Always review the source code before installing and use skills at your own discretion.
For a broader overview of the ClawHub ecosystem, see Trent AI’s ClawHub by the Numbers.
If you believe a skill in this list should be flagged or has a security concern, please open an issue so we can review it.
| Git & GitHub (167) | Marketing & Sales (107) | Communication (146) |
| Coding Agents & IDEs (1184) | Productivity & Tasks (207) | Speech & Transcription (46) |
| Browser & Automation (323) | AI & LLMs (176) | Smart Home & IoT (41) |
| Web & Frontend Development (920) | Data & Analytics (28) | Shopping & E-commerce (51) |
| DevOps & Cloud (393) | Calendar & Scheduling (66) | |
| Image & Video Generation (170) | Media & Streaming (86) | PDF & Documents (105) |
| Apple Apps & Services (44) | Notes & PKM (69) | Self-Hosted & Automation (33) |
| Search & Research (342) | iOS & macOS Development (29) | Security & Passwords (54) |
| Clawdbot Tools (37) | Transportation (111) | Moltbook (29) |
| CLI Utilities (180) | Personal Development (53) | Gaming (35) |
| Health & Fitness (87) |
You ship products with AI, but every launch still dies quietly because nobody posts about it. EveryFeed plugs your AI assistant into a social workspace that drafts, schedules, and publishes across 35+ channels — no agency, no marketing hire.
Stop building from a blank page. LaunchKit gives your AI coding assistant a complete, working product to start from — websites, startups, and web apps that are clickable on day one.
…превью ограничено; полный список — в репозитории.
