Best & Trending Agent Skills
Reusable workflows for review, research, writing, and data analysis.
每个 Skill 是一个 Markdown 文件，被 AI 编程助手（如 Trae、Cursor、Copilot 等）加载后，能够引导 AI 正确完成嵌入式开发任务——从环境搭建、项目创建、编译、烧录到调试，全链路覆盖。
Disclaimer: This is not AGI — it is a frontier exploration.
面向 CS 顶会论文写作的 7-Agent Pipeline Skill，运行在 Claude Code 之上。将一个粗糙的研究想法变成一篇投稿就绪的顶会论文，覆盖从选题到 Rebuttal 的完整管线。
Persistent memory for AI coding agents. Your agent remembers what it learned across sessions.
Aeloon is a lightweight, high-performance, and modular AI agent framework featuring graph-driven parallel acceleration and flexible hot-swappable plugins for many usages (Deep research, Wiki,...
Make AI understand your Xiaohongshu (RedNote)
Claude Code Skills collection for BMAD
Lance is a modern columnar data format optimized for ML/AI workloads, with native cloud storage support. This extension will make Lance the best file/table/lakehouse formats on DuckDB.
O copiloto de IA para quem trabalha com Sankhya. Skills prontas para Claude com dicionário de dados completo, fluxos operacionais e configurações do sistema — para consultores, desenvolvedores e...
Structure design critique: goals, observations, severity, questions, next experiments.
为 Claude Code、Cursor 等 AI 编程工具安装 QKA 技能：
Autofish gives any agent a stable, explicit, and observable Android execution layer: inspect the screen, act through stable refs instead of brittle coordinates, verify outcomes after every step, and...
微信读书前几天上了一个官方 AI skill（weread.qq.com/r/weread-skills），把书架、笔记、阅读统计、推荐 6 件事开放给 AI。能力很强，但它只是「自然语言包装的搜索接口」——你让它推荐书，它不会去看你已经读过什么，常把你笔记 68 条的书又当新书推回来给你。
For engineers who want agents shipping code without a human in the loop.
A hypothesis-driven debugging skill for Claude Code, Codex, and Gemini CLI. Instead of blindly guessing fixes, it instruments your code with runtime logs, generates multiple hypotheses, and...
Environment-Runtime 是一个面向工程场景的轻量级 Agent Runtime。随着 OpenClaw 在企业工程流程中的关注度持续提升，一个现实需求也逐渐显现：面向通用场景的 agent runtime 设计未必能直接覆盖所有工程落地形态。这个项目把视角收窄到高确定性工程流程，希望把常见工程任务组织成更清晰、更可复用、更容易维护的运行时。
Human-defined workflows. AI-powered execution. YAML decision trees with scheduling, hooks, MCP, and 21 built-in tools.
There are plenty of skills out there. This library avoids slop and only ships skills that:
A lightweight .NET AI SDK for provider routing, streaming, tool calling, and chat session management.
One-page team capacity: load, buffer, explicit cuts — honest ranges.
Azur Lane Resources extracted and parsed by Fernando2603/Azurex
Per-task rubric-blind skills for the Parthenon self-evolving legal-agent framework (Harvey LAB).
PrediHermes is a Hermes skill for geopolitical market forecasting. It wires together:
A Claude Code skill that rewrites text into plain language per ISO 24495-1:2023 — the international standard that defines plain language by reader outcome: the intended readers can what they need, it...