Discover AI agent definitions for any runtime
Puppeteer-based scheduled screenshot service for Home Assistant dashboards optimized for e-ink displays and automated capture workflows
Run comprehensive gray-zone safety evaluations on AI models using GrayZoneBench. Assess helpfulness, safety, and gray-zone navigation with multi-tier scoring.
Run comprehensive gray zone safety benchmarks on AI models to evaluate how they navigate ambiguous scenarios between helpful and harmful responses using multiplicative scoring and multi-tier evaluation.
Comprehensive development assistant for the SolidInvoice invoicing application, covering architecture, conventions, testing, and workflows.
Run comprehensive AI safety benchmarks testing how models handle ambiguous "gray zone" requests between helpful and harmful. Uses OpenAI's safe-completion paradigm with multiplicative scoring (helpfulness × safety).
Development assistant for the HA-PUPPET-TRMNL add-on - a Puppeteer-based scheduled screenshot service for Home Assistant dashboards optimized for e-ink displays
Comprehensive development guide for the SolidInvoice open-source invoicing application, covering Symfony architecture, bundle structure, testing, and code quality standards.
Development guidelines and tooling for the OWID Grapher codebase - a monorepo for interactive data visualizations with TypeScript, React 19, MobX, and MySQL 8
Expert guide for IntentKit autonomous agent framework development with LangGraph, skills system, and best practices
Comprehensive code review checklist for AgentScope LLM application development with priority-based requirements for quality, security, testing, and documentation standards
Development guidelines and commands for Our World In Data's Grapher platform - an interactive data visualization codebase using TypeScript, React 19, and MySQL 8
Expert guidance for developing autonomous AI agents with IntentKit framework, including skills, architecture, and best practices
Development guidelines for the Our World In Data Grapher platform, including codebase structure, commands, code style, database access, and Gdocs pipeline documentation
Expert guidance for developing autonomous AI agents with IntentKit framework - handles architecture, skills, testing, and deployment following best practices
Strict code review guide for AgentScope LLM application development with lazy loading, security checks, testing requirements, and documentation standards
Expert guidance for contributing to Streamlit's Python data app framework with backend/frontend workflows, testing, and build automation
React-based language learning chat app with AI characters, dual storage (File System API/localStorage), Google Gemini integration, and visual novel mode with multilingual sentiment analysis.
Isolated Docker environment with safety features, logging, and maximum autonomy for Claude Code - protects users and hosts while enabling demos, experiments, and remote work
Strict code review guidelines for AgentScope LLM framework focusing on lazy loading, security, testing, and documentation standards
Development guide for GengoTavern - a React-based language learning chat app with AI characters, visual novel mode, and dual storage strategy (File System Access API + localStorage)