Starred repositories
Collaborator is a place to create with agents.
反蒸馏 Skill：清洗你被迫写的 Skill 文件，看起来完整，核心知识留给自己。Anti-distillation for employee Skills.
一个"制造技能的技能"。这个工具自动化了将任意 GitHub 仓库转换为标准化技能的全过程，是扩展 AI Agent 能力的核心工具。
Set up and improve harness engineering (AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering) for AI-agent-friendly codebases. Triggers on: new/empty project setup for AI ag…
One Goal In. Continuous Software Evolution Out. GoalX is an autonomous engineering framework that turns a codebase goal into durable research, implementation, verification, and iterative improvemen…
《御舆：解码 Agent Harness》42万字拆解 AI Agent 的Harness骨架与神经 —— Claude Code 架构深度剖析，15 章从对话循环到构建你自己的 Agent Harness。在线阅读网站：
AI-powered learning coach with spaced repetition with Claude Code - master any knowledge faster with personalized syllabi and progress tracking
原汁原昧 Claude Code 可运行,可构建, 可调试版; Typescript 类型全修复; 企业级可靠性; 安全无毒, lock 文件保真, 可直接 bun i; bun run dev 启动
[Notice] The repo temporarily locked while ownership transfer. in the meantime we maintain on here: https://github.com/ultraworkers/claw-code-parity. The fastest repo in history to surpass 100K sta…
A collection of Awesome Finance Agent Skills for free and easy to start | 一系列开源免费的金融分析Agent Skills
将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
Point at any URL/YouTube/Podcast or file. Get the gist. CLI and Chrome Extension.
🛠️ Awesome tools & guides for harness engineering.
Persistent, per-skill experience memory for Claude Code
practice made claude perfect
Portfolio Optimization and Quantitative Strategic Asset Allocation in Python
💫 Toolkit to help you get started with Spec-Driven Development
SlowMist Agent Security Skill: A comprehensive security review framework for AI agents operating in adversarial environments. Core principle: Every external input is untrusted until verified.
"OpenSpace: Make Your Agents: Smarter, Low-Cost, Self-Evolving" -- Community: https://open-space.cloud/