Compare two AI tools side by side
Put any two skills or MCP servers next to each other: risk grade, what each can access, how popular it is, and how to install it.
| What | ClaudeSkills | ClaudeSkills |
|---|---|---|
| Risk grade | CC · Moderate risk signals Based on public adoption and transparency signals as of Oct 27, 2026. Our opinion, not a code audit or security guarantee. | DD · High risk signals Based on public adoption and transparency signals as of Oct 19, 2026. Our opinion, not a code audit or security guarantee. |
| Type | AI agent skill | AI agent skill |
| Est. context load | ~61 tokens idle · ~450 tokens when active (on-demand skill) | ~97 tokens idle · ~1.6k tokens when active (on-demand skill) |
| GitHub stars | 731 | 10 |
| Weekly npm downloads | — | — |
| Local files | No local folder access noted | Reads local files |
| Command execution | No shell command runner noted | No shell command runner noted |
| Network reach | Connects to outside service API | Local or standard API calls |
| Credentials | No API token required | No API token required |
| Package source | GitHub (staruhub/ClaudeSkills) | GitHub (kay-ou/ClaudeSkills) |
| Install command | Source repo only | Source repo only |
| Bottom line | Use ClaudeSkills only with non-sensitive data, review the actual skill code before deploying, and run agents in isolated environments that limit what they can access. | Signal-based grade (1/7 points): public source code. This reflects adoption and transparency, not a code review. |
Based on public adoption and transparency signals as of Oct 30, 2026. Our opinion, not a code audit or security guarantee.
Go deeper
Want to inspect exact published files, install hooks and network hosts?
Run a pre-install check on any package, MCP config or SKILL.md, or open a full report.