#6868th of 455 in Skills, plugins and prompts
clawhub
Public registry for publishing and searching OpenClaw agent skills and plugins
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 9.6k
- License
- MIT
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- TypeScript
8,008 on 22 Apr 20269,553 on 11 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
ClawHub is the skill registry for OpenClaw. Users publish versioned SKILL.md bundles, search them with OpenAI embeddings over Convex vector search, and install them through a `clawhub` CLI. It also catalogs OpenClaw code plugins, bundle plugins and experimental whole-agent Template packages. The web app is TanStack Start on a Convex backend with GitHub OAuth.
Who it is for: OpenClaw users who publish or install agent skills and plugins
Strengths
- Versioned publishing with changelogs, tags, rename redirects and duplicate-skill merging
- Embedding-based vector search instead of keyword matching
- CLI covers login, search, install, pin, update, publish and soft-delete
- Security analysis checks declared env vars and binaries against skill behavior
Weaknesses
- Self-hosting needs Convex, a GitHub OAuth app and an OpenAI API key
- Built around OpenClaw; skills and plugins are not generic across other agents
- Install telemetry is sent when logged in unless CLAWHUB_DISABLE_TELEMETRY is set
- Whole-agent Template packages are marked experimental
What it needs
- no GPU
- Needs Convex, Convex Auth (GitHub OAuth), OpenAI API (text-embedding-3-small), Bun
- Models: OpenAI text-embedding-3-small
- port 3000
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Skills, plugins and prompts
See all 455| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |