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 add-skill 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.
Local Meeting Transcription & Speaker Diarization AI Skill (SenseVoice + 3D-Speaker). Offline Video/Audio to Text with Speaker Separation (< 3GB). 本地纯离线会议转写与说话人分离智能体技能，集成音视频提取及高精度 ASR。
Portable skills, agents, and templates that add Spec-Driven Development and TDD workflows to any Claude Code project. Deterministic gate checks, bounded self-review loops, and binary acceptance criteria keep AI agents on track. Proven across TypeScript, Flutter, and Python.
Scan installed agent skills and generate HTML slide decks to track your automation tools.
Claude Code Plugin for lenne.tech development - Skills, Commands & Hooks for Nuxt 4, NestJS, TDD and CLI tools
Exercise: Build applications with GitHub Copilot agent mode
Build an AI customer support agent for e-commerce with FastAPI, LangGraph, RAG FAQ search, order tools, and chat streaming