BeardedChop/clawvet
Security scanner for OpenClaw SKILL.md files — catch prompt injection, hidden unicode, and shell vectors before your agent runs them
Security scanner for OpenClaw SKILL.md files — catch prompt injection, hidden unicode, and shell vectors before your agent runs them
npx skills add BeardedChop/clawvetSecurity scanner for OpenClaw SKILL.md files — catch prompt injection, hidden unicode, and shell vectors before your agent runs them
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.
2026 AI Training Module Generator - Instant Shockproof Skills Download
Claude Code skills that use the Codex CLI (ChatGPT subscription, no API cost) for spec/plan review and a PR-time codex-review gate compatible with --auto
Manage NeuralVaultCore memory with a safe, low-token system prompt for Claude Code, plus /nvc:init and /nvc:end commands
Recently updated agent-skill-related GitHub repository: borys-t-majewski/ai_devs_4_training.
Claude Skill for Context Sharing between Repos