by openclaw · Codex Skill · ★ 4.5k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is skills safe to install? View the security audit →
| Stars | 4,469 |
| Forks | 1,217 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 46/100 |
| Open Issues | 7 |
| Last Updated | 2026-05-01 |
| Created | 2026-01-06 |
| Platforms | python |
| Est. Tokens | ~72762k |
Skills Skills in this repository are backed up from https://clawdhub.com - check them out there for an easier experience (or have your clawdbot do it!) Disclaimer: there may be suspicious or malicious skills within this repo. We do retain them for a short time for further analysis, we recommend you only use the site to download skills from, and treat this as a historical archive instead.
Looking for a skills alternative? If you're comparing skills with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Sca
The largest open-source medical AI skills library for OpenClaw🦞.
Save or export your private and public Slack messages, threads, files, and users locally without admin privile
AI skill for OpenClaw & Claude Code — recommend from 10000+ Nano Banana Pro (Gemini) image prompts. Smart sear
Personal memory across agents
Build autonomous AI agents in Python.
Explore other popular codex skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: