internet-skill-finder — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited internet-skill-finder (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Search 7 verified GitHub repositories for Agent Skills.
python3 /home/ubuntu/skills/internet-skill-finder/scripts/fetch_skills.py --search "keyword"Options: --list (all skills), --online (real-time fetch), --json (structured output)
python3 /home/ubuntu/skills/internet-skill-finder/scripts/fetch_skills.py --deep-dive REPO SKILLWhen using cached data, prepend:
ℹ️ Using cached data. Enable GitHub Connector for real-time results.
Format each match:
### [Skill Name]
**Source**: [Repository] | ⭐ [Stars]
**Description**: [From SKILL.md]
👉 **[Import](import_url)**Suggest /skill-creator for custom skill creation.
Script auto-detects and uses best method:
| Priority | Method | Rate Limit | Behavior |
|---|---|---|---|
| 1 | GitHub Connector | 15000/hr | Auto real-time |
| 2 | Offline cache | Unlimited | Fallback |
| 3 | GITHUB_TOKEN env | 5000/hr | With --online |
JSON output includes "using_cache": true/false to indicate data source.
When cache is used, inform user: Enable GitHub Connector for real-time results.
7 repositories: anthropics/skills, obra/superpowers, vercel-labs/agent-skills, K-Dense-AI/claude-scientific-skills, ComposioHQ/awesome-claude-skills, travisvn/awesome-claude-skills, BehiSecc/awesome-claude-skills
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.