A finalization-discipline skill: the agent describes the accepted result and keeps rejected alternatives out of titles, commits and PRs
Skills
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, a risk 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: 203
An execution-discipline skill for Claude: staged planning, delegation to agents, failable checks and a double-check before delivery
An agent skill with TypeScript conventions: types, discriminated unions, functions, naming, source layout, React and tests, loaded per topic
Skills for Java projects: code review, Spring Boot, JPA, concurrency, Java version migration, Maven audits and security
Personal agent context in plain Markdown files you own, plus an onboarding skill built on a short interview
A skill that strips defensive caveats, apologies and excess hedging from text and makes claims direct while keeping needed limits
Skill with SaaS product-design principles: conversion, onboarding, retention, pricing and behavioral tactics
Amazon Skills
Amazon Skills by Nexscope
A skills pack for Amazon sellers: keyword research, listing optimization, FBA calculations, PPC campaigns and competitor analysis
A Terraform skill for Claude Code, Codex, Antigravity and Gemini CLI: cuts hallucinations and keeps code on HashiCorp's official practices
A skill that builds a personality for an agent: from your writing it produces markdown files so the agent writes and reasons in your voice
Skill for writing economics papers, drawing on advice from more than 50 authoritative guides
A skill with daily rankings of agent skills by installs, growth and mentions across several platforms at once
Skills with Apple HIG, Material Design 3 and WCAG 2.2 rules for reviewing interfaces on iOS, macOS, Android, the web and more
Color Expert
color-expert
A color science skill: OKLCH, APCA and WCAG contrast, design system ramps, palette generation, pigment mixing and color history
A skill for Jetpack Compose and Compose Multiplatform: the agent writes UI from references and checks it against androidx source
Skill that draws architecture, flowchart and sequence diagrams as hand-placed SVG in one house style
A set of skills that turn an AI agent into a tutor built on cognitive science, from school to career and social skills
Skills for positioning, content, LinkedIn, cold outreach and landing page audits with quick and deep modes
Creative coding skills for Claude Code: motion, micro-interactions and visual systems for web, Android and Apple
A set of Claude Code and Codex skills that teach the agent to write Spring Boot by your conventions and templates
Mindrally skills collection
Claude Code Skills Collection
Over two hundred coding-guideline skills for frameworks and languages, converted from Cursor rules to SKILL.md
A skill that finds AI writing tells, rewrites the text in a chosen voice, and optionally scores it from 0 to 100
Russian stack
Russian proofreading skill covering typography, bureaucratic style and 17 signs of machine text, with a rule cited for every fix
Creative Director
Creative Director Skill
A creative director skill: insights, ideas via SIT and TRIZ, Cannes-calibrated scoring and checks against a library of landmark campaigns
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 entry 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.