skill-hub
Skill1 starsChanged 9 months agoMITView on GitHub
OpenClaw skill discovery, security vetting & install. Searches 3000+ curated skills from ClawHub registry and awesome-openclaw-skills catalog. Scores credibility, detects prompt injection & malicious patterns, manages installations. Quick-checks GitHub for new skills.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- yinsanbian/AgentSkillHubtheir own version, first seen Oct 17, 2026
- kannaka-labs/Kannaktopustheir own version, first seen Oct 13, 2026
- PabloJustDevelops/skill-hub-modtheir own version, first seen Aug 20, 2026
- FlyrenxingSkill/skill-hubtheir own version, first seen Aug 8, 2026
- finger88/my-claude-skillstheir own version, first seen Apr 7, 2026
- kevinaimonster/skill-hubtheir own version, first seen Mar 18, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- kevinaimonster/skill-hub★ 4same name
- finger88/my-claude-skills★ 3same name
- PabloJustDevelops/skill-hub-mod★ 1same name
- yinsanbian/AgentSkillHub★ 1same name
- FlyrenxingSkill/skill-hub★ 0same name
- kannaka-labs/Kannaktopus★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository3 other files it gives its agents.
- openclaw-backupSkill
- openclaw-whispererSkill
- skill-vettingSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 46
After finding a skill, install via ClawHub:
- Distinctive: line 114
Before installing unknown skills from registry
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Skill Hub
Unified skill discovery, security vetting, and installation for OpenClaw.
Commands
Search Skills
Find skills by keyword, category, or credibility score.
python3 scripts/skill-hub-search.py --query "spreadsheet"
python3 scripts/skill-hub-search.py --category "DevOps" --min-score 60
python3 scripts/skill-hub-search.py --query "auth" --live # include live ClawHub results
python3 scripts/skill-hub-search.py --installed # show only installed
python3 scripts/skill-hub-search.py --not-installed --limit 20 # discovery modeInstall Skills
After finding a skill, install via ClawHub:
npx clawhub@latest install <skill-slug>Vet Skills (Security Scan)
Scan a skill for malicious patterns, prompt injection, and logic weaknesses.
python3 scripts/skill-hub-vet.py --slug google-sheets # vet single skill
python3 scripts/skill-hub-vet.py --all-installed # vet all installed
python3 scripts/skill-hub-vet.py --category "DevOps" # vet category
python3 scripts/skill-hub-vet.py --top 10 # vet top N unvettedStatus Dashboard
See installed vs catalog coverage, unvetted warnings, recommendations.
python3 scripts/skill-hub-status.pyQuick Check (GitHub API)
Fast check if new skills were added since last sync. Uses gh CLI — no full download needed.
python3 scripts/skill-hub-quick-check.py # check for updates
python3 scripts/skill-hub-quick-check.py --sync # auto-sync if updates found
python3 scripts/skill-hub-quick-check.py --query "ai" # check + search new skillsBrowse Full Catalog
Export catalog as formatted table (terminal or markdown), grouped by category.
python3 scripts/skill-hub-table-export.py # terminal table
python3 scripts/skill-hub-table-export.py --format markdown # markdown table
python3 scripts/skill-hub-table-export.py --category "AI" # filter categorySync Catalog
Full re-fetch from GitHub awesome-list. Computes credibility, preserves vet results, shows diff.
python3 scripts/skill-hub-sync.pyCredibility Scores (0-100)
| Tier | Score | Meaning |
| Trusted | 85-100 | Curated + vetted + mature |
| Good | 60-84 | Curated or vetted, some signals |
| Unvetted | 30-59 | Exists in registry, not scanned |
| Caution | 0-29 | Missing signals or security warnings |
Security Checks
Code-level: eval/exec, shell injection, obfuscation, network access, env harvesting, destructive ops.
NLP/Prompt-level: hidden instructions, role hijacking, invisible unicode, exfiltration prompts, authority escalation, social engineering.
When to Use
- User asks "find a skill for X" or "is there a skill that can..."
- User wants to extend capabilities with new tools
- User wants to check if installed skills are safe
- Before installing unknown skills from registry
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.