Portable, high-quality Claude Code skills — self-contained, opinionated, and convergent.

规矩.skill：让 Agent 少点客服味，多点判断力！

Conventions for writing code and using developer tools reliably as an AI coding agent. A Claude Code skill.

Battle-tested agent skills and Cursor rules from real projects. Works with Cursor, Claude Code, and any agent.

Agent skills by Trent Sikute, installable via npx skills add trentsikute/skills

UI skills for Codex: design passes, browser automation, screenshots, responsive checks, and evidence packs.

Production-grade prompt engineering toolkit for AI video generation. Built on Higgsfield Seedance 2.0 + storyboard reference workflow. Agent-native (Claude Code, Cursor, Codex). Benchmark-driven script adaptation in 3 minutes.

An Open Source Platform For Building Projects With OpenAI's Codex, Claude CLI, And Other Coding LLMs Using Multi-Agent Swarms And Customizable Workflows. Runs On Windows, MacOS, And Linux.

雨姗AI收银助手 - 不用换收银，一键升级AI智能餐饮系统

Agent skill for searching Instagram image posts and saving visible media with attribution.

Audit your AWS bill with Claude. An executable, evidence-first AWS cost-optimization skill that verifies prices live and never deletes without proof.

npx skills add choegyumin/agent-skills

Anti-slop web frontend skill for AI coding agents. Auto-trigger every web task. Force Kimi/Lovable-tier quality with Discovery Form + 5 deterministic directions + 27 anti-patterns + ready-to-paste hero/section/motion blueprints. Distilled from open-design, taste-skill, impeccable.style, getdesign.md, kimi.com, lovable.dev.

A growing arsenal of Claude Agent SDK skills for serious frontend, design, and engineering work. Currently ships ui-arsenal: premium component-library expert for React + Next.js + Tailwind.

Open-source agent skills published by vllnt. Compatible with Claude Code, OpenCode, Codex, Pi, Cursor, Windsurf, and any runtime that loads skills from Markdown directories.

Agent Skills for Odoo, OCA-compatible addon development, porting, and open-core Odoo products.

Personal agent skills for Paper-first UI prototyping and design engineering.

Skill Forge: Claude Code plugin marketplace for agent harness docs, code quality workflows, and OpenCode customization.

Agent skills for logging, metrics, tracing, crash reporting, and analytics in mobile apps.

Master IFRS guidance for AI agents with cited answers, audit support, and up-to-date standard checks

Claude Code plugin extending heptameta/heptabase-cli-skills with a focused card cross-linking skill (ProseMirror schema + helper script).

Automation-ready download engine for AI agents.

Curated, eval-tested collection of agent skills for Claude Code, Cursor, Codex, Cline, and 36+ more AI agents. Drop-in capabilities your agent can invoke automatically.

Big Five (五大人格/OCEAN)測驗Skill

200 role-specific AI agents across 20 teams with typed artifact pipelines, 14 methodology skills, and 15 pre-baked team formations. The virtual engineering org for Claude Code, Cursor, Codex CLI.

GenPark skill: Automate ShopVidi US wholesale tasks, product scraping, and bulk orders.

AskProof helps non-engineers ask AI agents for proof before trusting done.

skills-doctor is an Agent Skill for auditing local AI agent skills. It guides an AI agent through a read-only review of local skill directories, trigger quality, context cost, progressive disclosure, safety risks, and maintainability issues. .

Claude Code 개발 라이프사이클 스킬 번들: Plan·Parallelize·Test·Review·Ship | Claude Code dev lifecycle skill bundle: Plan, Parallelize, Test, Review, Ship

A collection of Agent Skills — self-contained folders that teach AI agents to perform specialized tasks. Includes a production-readiness harness-audit skill, a plugin marketplace, a SKILL.md spec, and CI validation.

Skills for real engineers - not vibe coding

Agent skills for popup2026.com — drop-in SKILL.md package for Claude Code, Codex, Gemini, Cursor. Bundles the Popup Remote MCP server.

Routed skill-design catalog for AI agents with one /skill-master command, npm scaffolding, validation, and cross-runtime guidance.

A customizable framework for using LLMs in scientific workflows.

Curated agent skills, conventions, and workflows for building Kotlin Android apps with AI coding agents.

An agent skill for incremental teaching, restatement, and quiz-based understanding checks.

A beginner-friendly starter repo for creating, auditing, installing, and evolving Codex Skills from scratch.

The product-workflow layer on top of AI coding discipline — idea to shipped, without the spaghetti. Builds on Karpathy's rules with a 5-phase process, task tiers, and the amplifier mindset.

Open-source AI agent skill definitions for software engineering and related public-good workflows.

Verification skills for academic research — grounds every claim in fetched evidence, not memory. Citation/figure/contradiction checking, arXiv monitoring, NRF grant writing.

skillgate-agent - AI多模型网关与智能代理框架, 支持MiniMax/DeepSeek等主流模型, 集成MCP工具调用与技能系统。skillgate-agent - AI multi-model gateway & intelligent agent framework, supporting MiniMax/DeepSeek, MCP tools & skill system。

Reusable Factor Skills for Agent-native product optimization

Local-first security scanner and policy gate for Agent Skills

Claude Code plugins for spec-first development: every agent claim cites a source, every code change traces to a requirement, and ceremony scales to the weight of the task.

Multi-session Claude Code skill for strategic module remediation — research-first bug inventory, then an iterative one-bug loop with isolated smoke-test gates

Build focused research for Claude Code with one skill, three reference packs, and a clear workflow for mapping, judging, and synthesizing sources

macos-screen-recorder (sck-record) — a macOS screen recorder with system audio via ScreenCaptureKit: CLI, no driver, no sudo. Plus a Claude Code skill.

类书式 AI Agent 技能大典 · 精选/中文化/互见成网的 500+ 开源技能，可作为 Claude Code 插件市场一键安装。A curated, cross-referenced encyclopedia of 500+ open-source agent skills.

Say "new project" → get a perfectly-prepared project folder. A Claude Code bootstrap kit that grills the plan to a Definition of Ready, then auto-scaffolds files, memory, project sub-agents & tooling — routing to type-specific sub-skills (website, api, data/ml, quant, SaaS, CLI, app, game-mod, research, OSS… + a 7-day build-business ultraskill).

AI Skill 执行可靠性审查工具。评估 Skill 被 AI 执行时的可复现性、可信度与业务适配性。Halu = Hallucination, Catch = 捕获。

Self-hosted feedback loops for Agent skills: report corrections, monitor usage, open upgrade PRs, and sync skills locally.

Loop yes. Prompt no. Agent skills that turn specs into checked agent loops with receipts.

A harness factory for AI coding agents — turn one idea into a verified, installable, multi-host plugin.

Agent Skills collection — hand-drawn shorts, flight-monitor-agent, hotel-watch-agent and more