Your AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders — self-improving context memory. Kills context rot, ships features, not spaghetti. Claude Code & Codex. Any stack. 30 seconds
npx skills add ngxccc/agent-skills-kitYour AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders — self-improving context memory. Kills context rot, ships features, not spaghetti. Claude Code & Codex. Any stack. 30 seconds
A curated collection of research agents, skill libraries, autonomous research loops, paper-writing pipelines, MCP servers, and benchmarks built around Claude Code, OpenAI Codex CLI, and adjacent coding-agent CLIs for AI/ML research.
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.
蓝湖设计稿转前端代码的 Claude Code Skills 工具集 | Lanhu design-to-code workflow for Claude Code
Claude Code skill for publishing skills to GitHub and awesome-claude-skills lists. Encodes hard-won lessons from real publishing attempts.
Build AI skills that distill any person’s thinking into reusable workflows and prompts
Modular, testable prompt and agent skill library with DeepEval metrics, multi-model CI, and Vercel npx skills compatibility. Prototype reusable skills (SKILL.md + Python registry) for production-grade LLM development.