Superpowers software development methodology for coding agents, including planning, TDD, debugging, subagent execution, review, and platform-specific bootstrap behavior.

Comprehensive AI research skill library for autonomous research workflows, model training, evaluation, inference, MLOps, RAG, multimodal systems, and paper writing.

Ultra-compressed communication mode for coding agents, including caveman response style, terse commit/review helpers, memory-file compression, Cavecrew subagents, and Claude/Codex session-start activation hooks.

Production-grade engineering skills for AI coding agents covering the full software development lifecycle from spec to ship.

Garry’s Stack development workflows with platform-specific runtime integration.

Skill-only package of Taste Skill frontend design and image-generation agent skills from Leonxlnx/taste-skill.

Matt Pocock's public engineering, productivity, and misc agent skills for planning, TDD, debugging, issue workflows, architecture improvement, and concise collaboration.

A Claude Code harness that makes Opus or any Claude model see multi-step work through with evidence, verification grounding, investigation protocol, per-task routing, and early-stop guard support.

Engineering division from The Agency — 23 specialized agent personalities from msitarzewski/agency-agents. Each agent has deep domain expertise, unique personality, and production-ready workflows.

Lazy senior developer mode for AI agents that pushes YAGNI, standard-library-first, native-first, and minimal-code behavior through skills, commands, rules, and lifecycle hooks.

Up-to-date documentation lookup via Context7 MCP. Pull version-specific documentation and code examples directly from source repositories into your LLM context. Includes MCP server (HTTP), skill, agent, and command.

Create and edit Obsidian vault files including Markdown, Bases, and Canvas. Use when working with .md, .base, or .canvas files in an Obsidian vault.

Agents-only package of 19 Claude Code orchestration agents from Yeachan-Heo/oh-my-claudecode, including planning, execution, review, debugging, testing, security, research, and documentation roles.

Marketing agent skills for conversion optimization, copywriting, SEO, paid ads, analytics, growth, and go-to-market workflows.

Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

Pre-built small business workflows (including payroll planning, month-end close, weekly briefs, and growth campaigns) using your QuickBooks, PayPal, HubSpot, Docusign, Gsuite, O365, Canva, and other connected tools. You approve every step that touches money or customers.

Google Workspace CLI agent skills for Drive, Gmail, Calendar, Docs, Sheets, Slides, Chat, Apps Script, personas, and workflow recipes powered by the gws command-line tool.

Brainstorm, plan, debug, review, and compound learnings with AI agents

Core agents for application architecture, cross-layer implementation, UI work, and protocol-specific development. Includes 12 Codex-native subagents from VoltAgent/awesome-codex-subagents.

Guide for implementing smooth, native-feeling animations using React's View Transition API (`<ViewTransition>` component, `addTransitionType`, and CSS view transition pseudo-elements). Use this skill whenever the user wants to add page transitions, animate route changes, create shared element animations, animate enter/exit of components, animate list reorder, implement directional (forward/back) navigation animations, or integrate view transitions in Next.js. Also use when the user mentions view transitions, `startViewTransition`, `ViewTransition`, transition types, or asks about animating between UI states in React without third-party animation libraries.

Triage tickets, draft responses, escalate issues, and build your knowledge base. Research customer context and turn resolved issues into self-service content.

Review and verification agents that work especially well as read-heavy Codex subagents. Includes 16 Codex-native subagents from VoltAgent/awesome-codex-subagents.

Plugin development toolkit with skills for creating agents, commands, hooks, MCP integrations, and comprehensive plugin structure guidance

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

Read-heavy research agents for searching, validating, comparing, and synthesizing information. Includes 7 Codex-native subagents from VoltAgent/awesome-codex-subagents.

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

Use this skill when building applications with Gemini API hosted models, including Gemini and Gemma 4, working with multimodal content (text, images, audio, video), implementing function calling, using structured outputs, or needing current model specifications. Covers SDK usage (google-genai for Python, @google/genai for JavaScript/TypeScript, com.google.genai:google-genai for Java, google.golang.org/genai for Go), model selection, and API capabilities.

Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model (Opus/Sonnet/Haiku) in a file; questions about prompt caching / cache hit rate in an Anthropic SDK project. SKIP: file imports `openai`/other-provider SDK, filename like `*-openai.py`/`*-generic.py`, provider-neutral code, general programming/ML.

Deploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login — e.g. "deploy to vercel", "set up vercel", "add environment variables to vercel".

Microsoft Azure MCP and Skills integration for cloud resource management, deployments, diagnostics, AI, identity, storage, messaging, Kubernetes, and Microsoft Foundry workflows.