베스트 & 인기 Agent Skill
리뷰, 리서치, 글쓰기, 데이터 분석을 위한 재사용 가능한 워크플로.
Find AI-generated code that looks finished but isn't.
Claude Context Manager 通过自定义斜杠命令，让你能够随时保存 Claude Code 的会话上下文，在新会话中快速恢复之前的工作状态，彻底解决 API 错误导致上下文丢失的痛点。
把任何实习经历，提炼成真实可用的竞争力。 不只是程序员。开发 · 产品 · 运营 · 设计 · 销售 · 市场 · 金融 · 一切岗位
Portable agent memory — take your agent's memory anywhere.
很多人用 AI 改论文，改完越看越心虚：审稿人还没开口，自己先把「遗憾的是」「效果有限」「仍明显落后」写满了。结构是工作汇报式的，语言是自我审查式的——
基于三省六部架构的 AI 多 Agent 协作系统 · Windows 优化版
A deterministic design critique for HTML/CSS, extracted from the set of rules professional designers use in production-grade designs.
武术指导 Skill — 一句话需求生成 N 宫格武打分镜海报与视频提示词，覆盖武术、格斗、修真、戏曲、机甲等多类题材
Superpowers for GPT-5.6, 85.5% leaner. Target to more token-efficient use of GPT-5.6.
HTML 슬라이드를 기획·생성하거나 기존 덱을 후처리하면서, 맥락과 청중에 맞는 유명 밈을 절제해 삽입하는 Codex 스킬입니다.
Out-of-the-box agent teams can be excellent, but getting there takes time and effort — the right specialists, each with a point of view, and a bias applied where it sharpens the team and held back...
Turn data reports into 16:9 web-based slide decks — a Claude Code skill / standalone project template.
🚀 OpenManus-Max An Advanced Autonomous AI Agent Framework with Multi-Level Permissions & Trust Attenuation
A flexible and powerful AI agent library for Python, designed to build agents with tool support, multimodal capabilities, and streaming responses.
A collection of advanced agentic tools, skills, and workflows designed for the Antigravity AI coding assistant.
面向中文用户的 。项目基于 learn-claude-code 的 Agent 工程思路改造，用 Python + Aliyun DashScope/Qwen 实现一个只读 PR Review Agent：读取 Git diff 和 PR 描述，组织多个 reviewer 生成候选问题，再通过 debate loop 对 finding...
- : write in rich text or raw Markdown, switch anytime - : fully Obsidian-compatible - : a daily capture stream for quick notes, accessible from anywhere - inspired by Raycast: find anything as you...
A tiny skill that surfaces relevant terms of art as you work with agents, growing your domain vocabulary over time
一个可开新档的 AI 健身教练框架：训练记录、RPG 属性成长、剧情推进三者联动
A Swift library for macOS automation — mouse, keyboard, screenshots, image recognition, and AI-powered agents.
macOS 可用 · Windows beta · DeepSeek API key · 非商业使用 English README
只需要一句指令，就能让 Codex 把 GPT Image 2 生成的美观图片转换为 PPTX；然后在 PowerPoint 中选择**或**，即可编辑重建后的各个元素。注意， 如果要编辑比较底层的元素可能需要多次的**，因为我们的重建逻辑涉及多层次的 元素组合。
adds rollback/recovery, adaptive context loading, and model routing intelligence on top of the original GSD by TÂCHES. Synced with upstream v1.24.0.
PhD students spend weeks on literature surveys. Most of that time is plumbing — finding papers, extracting claims, cross-referencing terminology, building comparison tables, chasing citation chains.