Self-contained Agent Skill packaging the SNV-judge v5 missense-variant pathogenicity ensemble (XGBoost+LightGBM+Isotonic, AUROC 0.9679). Bundles the trained model, exposes a SKILL.md (Claude Code) and opencode subagent definition, and supports any OpenAI-compatible LLM (DeepSeek/Moonshot/Qwen/OpenAI) for ACMG clinical-report generation.
npx skills add zja2004/snv-judge-skillSelf-contained Agent Skill packaging the SNV-judge v5 missense-variant pathogenicity ensemble (XGBoost+LightGBM+Isotonic, AUROC 0.9679). Bundles the trained model, exposes a SKILL.md (Claude Code) and opencode subagent definition, and supports any OpenAI-compatible LLM (DeepSeek/Moonshot/Qwen/OpenAI) for ACMG clinical-report generation.
Security scanner for OpenClaw SKILL.md files — catch prompt injection, hidden unicode, and shell vectors before your agent runs them
根据不同角色，收集或编写日常常用skill
Agent skill repository: aresbit/agent-add-skill
Use when challenging ideas, plans, decisions, or proposals using structured critical reasoning. Invoke to play devil's advocate, run a pre-mortem, red team, or audit evidence and assumptions.
Governance and security scanner for OpenClaw skills, ClawHub installs, MCP configs, and skill dependencies.
Claude Code skill enforcing Nicolas Zullo's Vibe Coding methodology (memory-bank docs, AGENTS.md rules, step-by-step plan execution).