prototypebench/prototypebench
Open benchmark for AI coding agents on full-stack feature shipping (React+Vite+Tailwind/FastAPI+SQLModel). 71 PR-mined tasks · 32k tests · execution-based scoring (pytest+Playwright) · no LLM-as-judge.
Open benchmark for AI coding agents on full-stack feature shipping (React+Vite+Tailwind/FastAPI+SQLModel). 71 PR-mined tasks · 32k tests · execution-based scoring (pytest+Playwright) · no LLM-as-judge.
npx skills add prototypebench/prototypebenchOpen benchmark for AI coding agents on full-stack feature shipping (React+Vite+Tailwind/FastAPI+SQLModel). 71 PR-mined tasks · 32k tests · execution-based scoring (pytest+Playwright) · no LLM-as-judge.
Frontend design skill for Claude Code, Codex, and Gemini CLI. Eight aesthetic anchors, each locking palette, typography, and texture to specific CSS tokens. Pick one per brief.
Website visual cloning skill for Claude Code — 6-phase process: recon, foundation, spec per section, parallel build, assembly, screenshot QA.
ai skill for frontend
The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's pattern. An Obsidian alternative for personal knowledge management, AI second brain, and durable Claude Code / Codex / OpenClaw memory.
Guide AI agents to discover OpenCLI commands, reuse browser logins, and handle adapters, downloads, and troubleshooting safely
AI-powered Healthcare Assistant built using Streamlit, LangChain, OpenAI GPT-4o-mini, and FAISS Vector Database.