by perkel666 · Claude Skill · ★ 55
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 55 |
| Forks | 1 |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 54/100 |
| Open Issues | 4 |
| Last Updated | 2026-11-04 |
| Created | 2026-10-03 |
| Platforms | claude-code |
| Est. Tokens | ~18k |
MegaCapybara The fastest inference engine for Qwen3.8-27B on the NVIDIA GeForce RTX 5090. Up to 500 tokens/s for one coding agent and up to 2,000 tokens/s for a team of them, on Windows 11 and Linux. A launcher sets it up and shows, before you load, what every setting costs in accuracy, speed and memory.
These tools work well together with MegaCapybara for enhanced workflows:
Looking for a MegaCapybara alternative? If you're comparing MegaCapybara with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
LLM server for NVIDIA Blackwell only (GeForce RTX 50, RTX PRO). On one RTX 5090, Qwen3.8-27B one user: 96.3 to
An offline coding agent for local models. One command sets up the best model your GPU can run, and on 24 GB+ R
The coding agent that gets more out of your AI subscription. Fastest and leanest of 20 agents tested, with unl
Turn GitHub Copilot into OpenAI/Anthropic API compatible server. Usable with Claude Code Or Codex Or Opencode!
is a local reverse proxy providing unified access to multiple AI providers (Claude, Codex) through a single in
Loz is a command-line tool that enables your preferred LLM to execute system commands and utilize Unix pipes,
Explore other popular claude 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: