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。
An is a plugin that teaches AI coding agents best practices for a specific technology, delivered as a portable Markdown knowledge pack.
JSON spec -> .excalidraw + .png + animated .gif
一个适配 Claude Code / Codex 等 Agent 环境的配图 Skill，用来把文章、笔记、图表截图、产品概念、工作汇报、教学材料和人文观点，生成**。
- 🤷 "AI到底能帮我做什么？" —— 听了100场演讲，还是一头雾水 - 💸 "我该先投哪个方向？" —— 怕投错钱，更怕错过窗口期 - 📊 "别人都在用AI了？" —— 焦虑但不知道从哪开始
Demo: Analyzing 2 years of NVDA, AMD & SPY stock data (15,000+ lines of raw JSON) using DeepSeek V3.2
aicoding-cookbook 是一个面向 AI Coding 工作流的实用资料仓库，收集了本地配置资产、可复用技能和辅助脚本。它的定位不是应用、SDK 或框架，而是一套围绕真实操作场景整理出来的 cookbook，用于配置工具、复用技能，以及标准化日常的 AI 辅助开发流程。
My personal library of domain-agnostic agent skills, reused across every project. Small, composable, and hackable — works with any harness that supports skills: Claude Code, Codex, opencode, Cursor,...
这里不是一叠孤立的提示词。每个 Skill 都用 SKILL.md 固化触发条件、工作阶段、确认门槛和交付物，让 Codex、Claude Code 等 Agent 在产品、开发、研究、写作和日常效率任务中按同一套方法工作。
Write a SKILL.md, drop in some evals, and find out — empirically — whether your skill actually makes the model better at the task.
A collection of Claude Code skills for academic research workflows.
On February 28th, 2026, DeerFlow claimed the 🏆 #1 spot on GitHub Trending following the launch of version 2. Thanks a million to our incredible community — you made this happen! 💪🔥
One command. 25 agent skills. Zero to profitable business.
Generate and evaluate agent skills based on traces with agents. Create skills with teacher models (expensive/slow) that student models (cheap/fast) can use to perform harder tasks reliably.
(asm) is a scriptable CLI built for AI agents and automation — install, search, audit, and organize skills across Claude Code, Codex, Cursor, and 16 more tools.
Codex skills for translating market information into testable investment research frameworks.
A collection of Agent skills and Claude Code plugins for HashiCorp products.
An Agent Skill that reviews scientific and engineering manuscripts for writing quality, applying the methodology from Dr. Kristin Sainani's Writing in the Sciences course at Stanford (2012).
The central challenge in AI development isn't a lack of ideas, but the inconsistent process of turning them into robust, reliable skills.
Experimental skill — will iterate over time. Please send your feedbacks in github issues.
Reusable Agent Skills for single-page SEO auditing. Give it a URL — get a structured HTML report with actionable findings.
The easiest way to evaluate your Agent Skills. Tests that AI agents correctly discover and use your skills.
AI-powered article illustrations with intelligent position detection and cover learning system. Claude Code Skill.
基于 Sorftime MCP 服务和 Claude Skills 的亚马逊分析工具集。
See the Feishu doc version of this intro (with usage-scenario showcases).