热门好用的 Agent Skill 推荐
用于审查、研究、写作和数据分析的可复用智能体工作流。
pi-subagents is a highly curated multi-agent framework for Pi agent harness.
67 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer.
44 plug-and-play skills for OpenClaw — self-modifying AI agent with cron scheduling, security guardrails, persistent memory, knowledge graphs, and MCP health monitoring.
AI-native quantitative research framework
基于 AI 自动生成高质量 PPT 图片和视频的强大工具，支持智能转场和交互式播放
DeepClause Typescript DML SDK and runtime
Skills & reviewer agents for AI-first climate science — built and used by a PhD atmospheric scientist
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower.
"一器而工聚焉者，车为多。" ——《考工记》 两千年前，造一辆马车是最复杂的系统工程：**承载乘者，辕定方向，辐传动力，軎辖为约束——每个构件各司其职，合而为一，车方能行。 今天，构建一个 AI Agent 亦是如此：对话循环为**，工具系统为**，权限管线为**，而将这一切承载于其上、使智能体真正运转的运行时框架—— Agent Harness——正是那个**。
AI Agent 驱动的开源可自部署视频工作台：将小说与剧本转为角色、场景、道具资产、分镜、视频和剪映草稿，支持跨镜头一致性、多供应商与费用追踪 | Self-hosted AI video workspace for stories, storyboards and short-form video production
Claude Code skill to support Android app's reverse engineering
Timoni is a package manager for Kubernetes, powered by CUE and inspired by Helm.
Your AI executive team on Discord. 7 specialized agents — Engineering, Finance, Marketing, DevOps, Legal, Management, Chief of Staff. One-click setup on any free-tier server. Built on Clawdbot.
Examples of my Claude Code infrastructure with skill auto-activation, hooks, and agents
Learn as you build. Build with intent. Ship real products. Agentic engineering done right.
A curated collection of GitHub Copilot customizations — instructions, prompts, agents, and skills — ready to drop into your project.
A catalog of installable skills for AI coding agents: Claude Code, Codex, Antigravity, and Grok.
Anti-AI-slop design skill for Claude Code, Cursor, and Codex.
的 AI Agent 工作台，一定程度上解决Openclaw的长期记忆及安全问题： 1. 对话与证据落盘为本地 JSON； 2. 长期记忆由 memory_module_v2 做结构化蒸馏与混合检索实现11倍tokens压缩； 3. 接入自己微调的Qwen3.5 4b模型配合Langchain的before_agent middleware用于合规内容检测； 4.
humanizer-zh 是一个兼容 Codex、Claude Code 和 OpenClaw 的中文去 AI 味技能。它用于重写、润色或审阅中文博客、评论、产品分析、newsletter、书稿章节等长文本，让文字更像中文母语者写出来的，而不是翻译腔、模型拼接稿或营销通稿。
A three-phase autonomous pipeline that inspects any SaaS product, builds a working clone with real cloud infrastructure, and QA-tests everything — no human in the loop.
基于 Claude Code / Codex 的 SRC 漏洞挖掘 Agent 技能体系 —— 系统级提示词 + 14 个专项安全测试 Skill 知识库
- 对话会落盘到本地 JSON - 长期记忆保存在 Markdown - 技能不是黑盒函数，而是可读可改的 SKILL.md - Prompt、工具调用、记忆注入、检索过程都能被看到
Most popular OSS agent harnesses (Cline, Roo Code, Continue, OpenCode, Aider) leave on the table because their prompt-caching code is subtly wrong, off-by-default, or just missing for some providers.