Two official Ant Design skills: a guide to antd 6, Pro 5 and X 2 plus an offline antd reference workflow for code and migrations
Skills for AI agents
A skill gives an agent a ready-made ability: a tested prompt, a set of steps, sometimes files and scripts. This section collects skills for Claude Code, Cursor, Codex and other agents, each with an install command, an access level and a plain description of who needs it and when.
Match with Foxx AI
Describe the task or paste package.json, and Foxx AI will pick matching skills, MCP servers and CLI tools.
Found: 3123
Two dozen skills: video scripts and covers, publishing to X and Substack, security scanners, Claude Code session export
Typst Skill
claude-skill-typst
A Typst 0.15 skill covering tables, equations, templates and packages, with two verification subagents and API search
A skill that teaches an agent to wire up Envilder: one envilder.json maps env variables to AWS SSM or Azure Key Vault secrets.
Claude Code skill that draws vertical 9:16 explainer reels in a cut-paper style: script, voice and MP4 from one prompt
Agent Skill that turns diagrams and photos of optical setups into editable Blender models with real mounts and an evidence trail
A skill that builds a hierarchy of agents: a chief, per-project managers and workers in separate git worktrees inside herdr
A local handwriting image generator with CLI and MCP: an agent picks font and paper, saves a preset and renders text offline.
Sixteen Spring Boot skills: the agent explores the application first, then edits JPA, DTOs, REST, Security, Kafka and tests.
A skill that writes a full SwiftUI file with spring physics, haptics and glass surfaces from a plain-language animation brief.
A set of ready-to-copy Claude Code skill folders: PDF, slides, Next.js, image and video generation and social publishing.
A Codex skill that hands tasks to web ChatGPT with project terminal access, saving Codex quota; modes from Medium to Pro.
A skill that audits a draft NSFC grant application: it finds logic gaps and returns a prioritized list of fixes
Official
Thirteen skills and two rule files for Kuikly, Tencent's Kotlin UI framework: components, animation, networking, profiling
T3 Tots lets an agent read T3 Code thread state, answer questions and send reports, including to a phone
An NVIDIA skill that leads an agent from a privacy brief to a script that finds and replaces personal data in text datasets.
Personal assistant kit for Claude Code, Codex CLI and Grok CLI: file-based memory, 23 skills and a guided first-run setup
A library of 80 skills for Codex covering design direction, frontend, motion, accessibility, QA and site handoff
A Codex skill: three distinct visual concepts, screenshot review and cutting excess, so interfaces look less templated.
Nature Writing Studio
nature-writing-studio
Turns a Chinese or English article draft into Nature-style English using a pattern base distilled from hundreds of papers.
Skill guiding a LaTeX manuscript to editable DOCX with a journal template, live Zotero citations and Word cross-references.
Claude Code Toolkit (robertguss)
Claude Code Toolkit
A set of Claude Code skills and hooks: brainstorming, worker-led project leadership, a wiki, and a book pipeline.
Skill, MCP server and CLI that let any agent call Codex image generation, after picking a style from several directions
Codex skill that makes short MiniMax H3 videos from your images on a Google Colab GPU, with a job queue and result download
Frequently asked questions
What is a skill for an AI agent?
A skill gives an agent a ready-made ability: a tested prompt, a set of steps, sometimes files and scripts. The agent picks it up and solves the task by the defined scenario.
How do I install a skill?
Each card has an install command for a specific agent: Claude Code, Cursor, Codex and others. Usually you copy a folder into the skills directory or install it through a plugin manager.
How is a skill different from an MCP server?
A skill gives the agent knowledge and a sequence of actions, an MCP server gives access to external data and tools over a protocol. They are often used together.