BenchClaw is a Codex/OpenCode skill workflow for benchmark construction, evaluation, and maintenance. It standardizes the full pipeline—from idea drafting and data generation to evaluation, reporting, failure diagnosis, and skill refinement—so agents can build reproducible, auditable benchmarks with clear quality gates, lineage, and rollback.
npx skills add EurecaMoment/BenchClawBenchClaw is a Codex/OpenCode skill workflow for benchmark construction, evaluation, and maintenance. It standardizes the full pipeline—from idea drafting and data generation to evaluation, reporting, failure diagnosis, and skill refinement—so agents can build reproducible, auditable benchmarks with clear quality gates, lineage, and rollback.
Multi-provider API proxy for Claude Code with Anthropic ↔ OpenAI format conversion and TUI management.
A production-ready, framework-free Agentic Workflow for travel planning built with Python and the Model Context Protocol (MCP).
Production-grade Angular 21 + PrimeNG 21 enterprise architecture and Claude Code skill system for zoneless, Signals-first realtime applications with scalable frontend patterns, WebSocket architecture, Tailwind integration, and performance-focused engineering.
AI agent built on NeMo Agent Toolkit
Build Unity shader skills for mobile GPUs and WebGL with AI-ready guides for writing, reviewing, and optimizing shaders
AI Agent 操作飞书的托管远程 MCP 服务，复用 lark-cli 的 200+ 工具与 23 个 Skill。团队共享一个飞书应用，IT 集中管控，成员浏览器授权即用，数据按用户隔离。基于 AWS Bedrock AgentCore。