f4rkh4d/forge-skill
51 opinionated skills for AI coding agents. 27 ship with AST/shell verifiers. -72% verifier-visible slop on Sonnet 4.6, -58% on Haiku 4.5 (20 adversarial prompts, 3 runs/arm).
51 opinionated skills for AI coding agents. 27 ship with AST/shell verifiers. -72% verifier-visible slop on Sonnet 4.6, -58% on Haiku 4.5 (20 adversarial prompts, 3 runs/arm).
npx add-skill f4rkh4d/forge-skill51 opinionated skills for AI coding agents. 27 ship with AST/shell verifiers. -72% verifier-visible slop on Sonnet 4.6, -58% on Haiku 4.5 (20 adversarial prompts, 3 runs/arm).
Test security vulnerabilities in Gemini, Claude, and DeepSeek models using specialized prompt injections.
Connect any LLM to OpenClaw — production-tested middleware for Qwen3-235B and beyond
TDD-based routing quality engineering for LLM skill routing systems. Works with Claude Code, Cursor, Gemini CLI, Codex CLI, and any SKILL.md-compatible tool.
V Sync AI Hub 2026: One Config for All Powerful AI Tools
stuff i made for myself, some of it orignally quite situational, but now generalized for reuse
Multi-agent AI code review tool — 5 specialist agents + judge aggregation. Claude Code plugin, Python CLI, GitHub PR integration, VS Code extension.