No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is MedgeClaw safe to install? View the security audit →
🧬 MedgeClaw An AI-Powered Biomedical Research Assistant English | 中文 An open-source biomedical AI research assistant built on OpenClaw and Claude Code, integrating 140 K-Dense Scientific Skills for bioinformatics, drug discovery, clinical research, and more. Talk to your research assistant via WhatsApp, Slack, or Discord → it runs the analysis → you view results in RStudio or JupyterLab. Architecture What's Included | OpenClaw
| Stars | 641 |
| Forks | 149 |
| Language | TeX |
| Category | AI Tool |
| Quality Score | 62.3916044833376/100 |
| Open Issues | 6 |
| Last Updated | 2026-03-12 |
| Created | 2026-02-24 |
| Platforms | claude-code, cli |
| Est. Tokens | ~483k |
Looking for a MedgeClaw alternative? If you're comparing MedgeClaw with other ai tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
All powerful skills of ClaudeKit.cc!
A tool uses Windows Filtering Platform (WFP) to block Endpoint Detection and Response (EDR) agents from report
A java agent to generate method mappings to use with the linux `perf` tool
Skills I use with Claude for shaping
A tool to make socks connections through HTTP agents
SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration
Explore other popular ai tool tools:
MedgeClaw is Open-source AI research assistant for biomedicine — chat to run RNA-seq, drug discovery, clinical analysis, and more. Built on Claude Code with 140 K-Dense scientific skills, real-time dashboard, and . It is categorized as a AI Tool with 641 GitHub stars.
MedgeClaw is primarily written in TeX.
You can find installation instructions and usage details in the MedgeClaw GitHub repository at github.com/xjtulyc/MedgeClaw. The project has 641 stars and 149 forks, indicating an active community.
The top alternatives to MedgeClaw on Agent Skills Hub include claudekit-skills, EDRSilencer, perf-map-agent. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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: