베스트 & 인기 Agent Skill
리뷰, 리서치, 글쓰기, 데이터 분석을 위한 재사용 가능한 워크플로.
AI agent evaluation toolkit for Copilot Studio. Plan evals, generate test cases, interpret results, and triage failures — from Claude Code or GitHub Copilot.
https://github.com/user-attachments/assets/8bc180a3-0baf-473d-87c9-6aaacce302f2
This tool reads KakaoTalk's local database and automates the UI via macOS Accessibility APIs. It does not reverse-engineer the KakaoTalk protocol or call any Kakao APIs. See Disclaimer for details.
pi-subagents is a highly curated multi-agent framework for Pi agent harness.
Matt Shumer's aim prompt as a slash command — build a game against a named reference. Fill the three paragraphs. Run them. Stop when you stop it.
이 저장소는 hugohe3/ppt-master(MIT)를 기반으로 한 **입니다. 한국어 덱 제작에 맞춰 작업 절차 커스터마이징, 완료 PPTX 검증 워크플로우) 등이 조정·추가되어 있습니다. 원 프로젝트의 라이선스와 저작권 고지는 그대로 유지합니다.
We are moving from "prompt as text" to . Each skill acts like a lightweight, containerized application for AI work: a stable interface, opinionated workflow, and bundled resources that can be...
🐶 A curated list of Web Security materials and resources.
中国专利.skill：专利点挖掘与交底书（发明/实用/外观）编写，通俗解读专利，嗅探政策动向，辅助审查答复。
Huashu Design · HTML-native design skill for Claude Code · Claude Code 里 HTML 原生的设计 skill · 高保真原型 / 幻灯片 / 动画 + 20 设计哲学 + 5 维评审 + MP4 导出 · Agent-agnostic
👩🚒 Good content deserves good paper.
GEO-first SEO skill for Claude Code. Comprehensive AI search optimization for any website — citability scoring, AI crawler analysis, brand authority, schema markup, platform-specific optimization,...
该技能可以让龙虾对任何事实进行多维度核验，从不同学科视角深入分析和研究问题，往往可以给出让人惊艳的输出结果。
Current version: Audit, Generate & Document: DDD, CQRS, Event Sourcing, Clean/Hexagonal Architecture, Design Patterns, PSR, Tests ...
🔴 RedTeam Agent Autonomous AI-Powered Red Team Simulation Agent Install · Quick Start · Architecture · 中文
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.
A catalogue of — CRUD tables, detail & master-detail pages, kanban, calendar, wizard, charts, billing, RBAC, i18n, and more — that an AI agent into a real back-office.
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 curated collection of GitHub Copilot customizations — instructions, prompts, agents, and skills — ready to drop into your project.
Cross-platform UI/UX design reviewer grounded in Apple's Human Interface Guidelines (HIG), adapted as universal design rules for and apps.
A powerful, extensible AI coding agent CLI with multi-provider support, built-in tools, and a rich extension system.
让 Codex 通过 AGENTS.md 与本地 Markdown 记忆文件形成可审计、可维护的长期改进闭环。
A curated collection of practical, DeFi-focused utility skills developed by the . These skills enable AI agents to perform complex on-chain operations, payments, and identity management across...