Best & Trending Agent Skills
Reusable workflows for review, research, writing, and data analysis.
compile lua2c (single binary with embedded scripts)
A collection of security and utility hooks for Claude Code. Hooks allow you to extend Claude Code's behavior by running custom scripts at key points during execution.
我建了一个 （付费），聊 AI 短剧的工作流、工具和实操。 有兴趣的加我：，添加时**。
An easy-to-use web framework. Based on baize and pydantic.
Feishu knowledge base export, writing, and cloud-space management tool with Markdown, WeChat import, CLI, TUI, and OAuth 2.0
A structure-first data engine for workloads that scale by namespace. One Swamp per tenant, user, device, agent, or other natural unit. Reactive, gRPC-native, single binary.
Splinter maintains a set of lints for Supabase projects. It uses SQL queries to identify common database schema issues.
ATR (Agent Threat Rules) is an open detection rule format for AI agent security threats. Rules are written as YAML documents conforming to a versioned schema, identified by the public ATR-YYYY-NNNNN...
humanize-text-skill is a bilingual writing skill for removing AI-shaped prose and pulling the result toward a target human voice.
This project is currently in the testing stage. Star it, try it, and feel very welcome to share suggestions and feedback.
is a production-ready Python package designed for football (soccer) analytics, providing powerful tools from pena.lt/y/blog for data analysis, outcome modelling, and betting insights.
humble A humble, and fast, security-oriented HTTP headers analyzer
— 使用、修改或部署本專案，必須標明原作者 、附上本 repo 連結，並以相同授權公開原始碼。網路服務部署亦同。 本專案於 2026/04/13 從 MIT 切換至 AGPL-3.0。此日期之前取得的版本仍適用 MIT 授權。
面向电商商品图生产场景的图片套图 Skill。仓库提供一套从商品图分析、卖点提炼、Prompt 组织到成图输出的脚本与配置，适合用在淘宝、京东、拼多多、抖音等国内平台，以及独立站、Amazon 等跨境场景。
这是一个用 Python 从零构建 AI Agent 的教学项目。项目核心是 build-agent-example/：从一次模型调用开始，后续每一步都保留前一步的全部代码和能力，逐步加入循环、history、system prompt、工具、skills、memory、规划、子代理、团队协作、MCP 和 hooks。
给 Gemini CLI、Claude Code、Codex 等 AI 编程助手使用的 HarmonyOS NEXT 离线参考技能库。
Claude Code와 OpenAI Codex 양쪽에서 동작하는 에이전트 스킬입니다.
— 基于 Claude Code Agent Teams 的多智能体协作安全分析框架
⚠️ qu-ai-wei 仍在迭代，规则、分类、API 都可能变动。欢迎提 issue / discussion / PR 反馈。 繁體有自己的 AI 腔特征、用字偏好、排版规范，规则需要单独维护，留给后续版本。
Herdr Browser renders a real Chromium view inside a Herdr pane and exposes it to Chrome DevTools Protocol clients.
The spec-driven development system where specs and tasks live in your repo and never drift from the code.
A minimal, working multi-model team for opencode: a that plans and reviews but , delegating every change to a cheaper, faster . Inspired by the Devin Fusion "sidekick" pattern from Cognition.
让 AI 不只会“看网页、回答问题”，还能够安全地完成研究、比较、填表和后台操作等多步骤网页任务。
Give every developer — or every AI agent — a real computer in the cloud, and make spinning one up a two-minute, self-service action.