Discover your next essential.

Browse 11303 agents, skills, and projects. Find a useful starting point, then search, compare, and curate your stack.

ArthurZakirov/SkillPort ↗

Package agent skills once. Install them anywhere.

ArthurZakirov/SystemSmith ↗

Engineering methods for code, agents, and architecture.

The local-first, agent-native control plane for ComfyUI. An MCP server plus a live sidebar agent that generates images, video and audio, authors and runs workflows, manages models and custom nodes, and edits your live ComfyUI graph in natural language. Bring whatever model you have: Claude or ChatGPT on your subscription, Gemini on your Google login, a free local model via Ollama (fully offline), or any hosted model over one API key (DeepSeek, GLM, MiMo, Kimi, GPT, Claude via OpenRouter). The tools and the panel are the same on every tier, and the built-in LLM Arena scores each model on real ComfyUI tasks so you know what yours can do. One config targets local installs, LAN, VPS, or Comfy Cloud.

artsunique/rotstift ↗

German texts that don't sound like a language model: Linten, rewrite, counter-read, re-linten.

artwisdom/roofing-os-skills ↗

Free Claude skill for roofing contractors: summarize-inspection-notes turns field notes into a homeowner summary and an internal inspection record.

arty-kk/vibe-coding ↗

Understand the code. Make the change. Verify the result.

ArulVelusamy/generate-walkthrough ↗

A Claude Code skill that turns any codebase into a single, self-contained HTML walkthrough — a forensic, screen-by-screen trace of what the system actually does, from first entry point to terminal outcome, grounded in real file:line evidence.

ArunskiOrg/BenArunskiUtils ↗

Public Claude Code skills and standalone utilities. First up: a skill that turns a document into spoken-word audio, and one that explains code the way you'd want it explained. More skills and utilities will land here over time under the same layout.

arvindrk/extract-design-system ↗

Reverse-engineer design tokens (colors, typography, spacing, border radius, shadows) from any public website and generate starter JSON and CSS custom properties for your local project. Available as an AI agent skill (Claude, Cursor, Codex) and standalone CLI.

ArXiv Watcher ↗

Search and summarize papers from ArXiv.

arxiv-watcher ↗

Search and summarize papers from ArXiv. Use when the user asks for the latest research, specific topics on ArXiv, or a daily summary of AI papers.

aryangole07-hub/claude-useful-skills ↗

A curated library of Claude Code skills (~670), grouped by what they do. Our own skills sit next to third-party packs, which are vendored unchanged with their upstream license and an UPSTREAM.md naming the source commit.

ARYN26/you-are-here ↗

yah is a Claude Code plugin that shows which plan, phase, PR and next step you're on and tells you when to wrap (write the next step down, commit, then /clear), because short sessions that start from written-down state cost far less than long ones that rediscover it.

asaf-shitrit/ai-native-sdlc-skills ↗

The playbook's premise, in one line: code is no longer the bottleneck — the human-speed steps to the left and right of it are. Plan, review, test and deploy become the constraint once an agent writes most of the diff, and controls designed around a person reading every line stop matching reality. The answer isn't less process. It's the same control objectives with new enforcement.

asale-ai/anything-to-skill ↗

Turn a book, a paper, a documentation site, or a repository into an agent skill — and keep it worth loading afterwards.

asana-api ↗

Asana API integration with managed OAuth. Access tasks, projects, workspaces, users, and manage webhooks. Use this skill when users want to manage work items, track projects, or integrate with Asana w

AsaqeLee/peer-consult ↗

Multi-agent peer-consultation skill for collecting independent coding advice from multiple LLMs.

asauntung/claude-skill-cave ↗

Caveman mode skill for Claude. Fewer output tokens, longer usage before hitting limits.

asc-aso-audit ↗

Run an offline ASO audit on canonical App Store metadata under./metadata and surface keyword gaps using Astro MCP.

asc-crash-triage ↗

Triage TestFlight crashes, beta feedback, and performance diagnostics using asc. Use when the user asks about TF crashes, TestFlight crash reports, beta tester…

asc-notarization ↗

Archive, export, and notarize macOS apps using xcodebuild and asc.

asc-ppp-pricing ↗

Set territory-specific pricing for subscriptions and in-app purchases using current asc setup, pricing summary, price import, and price schedule commands.

asfakulsiam/asfakulsiam-motomation-design ↗

An agent skill that guides a coding agent through research, art direction, build and validation of a website. It aims for original, typography-led sites that fit the product, with motion as a deliberate choice. At the top tier, scrolling plays like a film. The result still depends on the agent, the brief and a human review; the skill does not guarantee award-level output.

ash1794/vibe-engineering ↗

Performs [action] for [context]. Use when [trigger condition].

ashfulcra/fulcra-tools ↗

Vibe-coded by Fulcra’s lawyer, on Fulcra’s own primitives. Unofficial, unsupported, and a useful thing to point your agents at.

ashlrai/ashlr-plugin ↗

Token-efficiency plugin for Claude Code and Codex: MCP tools and hooks that replace high-volume Read/Grep/Edit/Bash calls with compact equivalents, po

aShu-guo/ts-abbr-skill ↗

An agent skill that makes generated/refactored TypeScript naming follow a shared abbreviation dictionary (business → biz, context → ctx, configuration → cfg, ...) instead of verbose full words. Works with Claude Code, Codex, and any agent supported by the skills CLI.

AshwinSathian/humanize-writing-skill ↗

Claude Code skill that makes Claude's prose read as written by a person.

asidko/reverse-grill-skill ↗

Review a PR without reading the code.

ask-matt ↗

Ask which skill or flow fits your situation. A router over the skills in this repo.

ask-sonner ↗

Guide to Sonner, the React toast library — install and wire up the Toaster, pick the right toast() call.

askuma/generate-tech-stack ↗

Scan any project and generate a visual TECH_STACK.html page — light/dark theme, auto-adapting, zero config.

askuma/workflow-generator ↗

Scan any project and generate WORKFLOW.html — a dark-mode visual system diagram showing every component, how they talk to each other, and where your throughput ceiling actually is.

asm0dey/precedent ↗

precedent gives your coding agent a memory of the architectural, business and tooling choices you have settled — across every project, for years — and puts them back in front of you when a similar choice comes up again.

aso ↗

Helps you audit or optimize an App Store or Google Play listing.

ASOScan/aso-skills ↗

ASOScan is an ASO skill for Claude, Claude Code and ChatGPT: ask about your own apps in plain words and get your real App Store and Google Play numbers. If you are looking for an aso skill Claude connects to directly, or aso skills Claude can run without an API key, this is it.

asrms/enterprise-agents-claude-copilot ↗

A ready-made team of expert AI agents for Claude Code and GitHub Copilot. Drop one folder into your repo and get senior-level help on every phase of the SDLC, backed by clear, enforceable rules. Free to use, change, and share, commercial use included (MIT License).

asrplv/ailibri-skill ↗

Agent skill: pick an AI tool for a task from the ailibri.com catalog (pricing, free tier, availability from Russia)

assafelovic/skyll ↗

Skyll is a REST API and MCP server that lets any AI agent search for and learn agent skills at runtime. It aggregates skills from multiple sources, fetches the full SKILL.md content from GitHub, and returns structured JSON ready for context injection.

assafkip/claudemy ↗

Any topic into 2-minute audio lessons with cited sources

assembly-one-step-clip ↗

The assembly step video, using AI as a step fact, is a one-step short film for each frame. This step-by-step studio delivers short video and step video of the product in step order.

assistant-ui/skills ↗

Agent skills for building AI chat interfaces with assistant-ui.

ASTARLab-s/cosquared-marketplace ↗

13 validated skills and commands for AI-assisted development, from CoSquared — a privacy-first coach for how you work with AI coding tools.

asteria-jacky/skills ↗

Claude Code skills for refactoring toward ubiquitous language and deep modules.

astro ↗

Skill for building with the Astro web framework. Helps create Astro components and pages, configure SSR adapters, set up content collections, deploy static…

astro-framework ↗

Astro framework specialist for building fast, content-driven websites with islands architecture. Use when creating Astro components, configuring hydration…

astro-han-karpathy-llm-wiki ↗

Build or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.

astrofoundry/talk-normal ↗

A writing skill for AI agents: answer first, plain words, whole sentences.

astroicers/skill-quality-research ↗

Craft-first quality review for Agent Skill repos — an LLM judges how well a skill is WRITTEN (trigger design, writing quality, scope, anti-hallucinati

astrolicious/agent-skills ↗

Skill for building with the Astro web framework. Helps create Astro components and pages, configure SSR adapters, set up content collections, deploy static sites, and manage project structure and CLI commands.

Astron ↗

Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.

asymmetra-inc/docdd-dev-kit ↗

Development kit for non- er to continue creating web apps and games with Claude Code and Codex ( -in docdd)

asynchronos/operator47-plugins ↗

Claude Code plugin marketplace by operator47. Context optimization and workflow automation plugins.

AsyrafHussin/agent-skills ↗

A collection of skills for AI coding agents. Works with Claude Code, Cursor, Codex, and 70+ agents.

atarico/fix-cv-find-job-skill ↗

Fixes your CV and finds you a job.

atazifor/engineering-memlog ↗

Engineering Memlog gives AI coding agents a durable memory of hard-won debugging lessons across projects. When a real failure appears, the agent searches previously verified causes, checks whether one fits the current evidence, and continues normal diagnosis when nothing does.

atdy/maoxuan-product-agent ↗

In Chinese, distilled from the whole approach of the dictum " Practice ", AI Product Manager/Producing Department Agent Skill: Solving demand.

atgreen/secscan-skill ↗

A token-efficient, in-session security-triage skill for Claude Code.

AThevon/genjutsu ↗

Creative coding skills for Claude Code, claude.ai and Cowork. Web (React, Vue, Svelte, Astro, vanilla CSS, Three.js, Canvas), Android (Jetpack Compose, Compose Multiplatform) and Apple (SwiftUI, iOS and macOS). bunshin is web only for now.

athola/claude-night-market ↗

A plugin marketplace for Claude Code. Install only the plugins you need to run git workflows, code review, spec-driven development, and autonomous agents from inside your Claude Code session.

Athyrr/aikit ↗

An agentic method for Claude Code: a plugin that turns a request into a spec, a plan, reviewed tasks and a verified result — without the orchestrating session ever filling up.

Atiqul-Islam/genesis ↗

An agent-builder for Claude Code — a team of three agents (Sensei, Method, and Mneme) that builds, tests, installs, and remembers specialized Claude Code agents with enforced expertise and per-agent semantic memory.

atlas-doc/atlas-flight-booking-skill ↗

Install the Skill and then ask your AI agent to search or book a flight

AtlasCloudAI/awesome-seedance-2.5-prompts-skills ↗

A curated library of Seedance 2.5 video prompts plus Seedance 2.5 Skill, an installable Agent Skill that improves prompts, plans and reviews storyboards when needed, and generates controllable video. It uses Seedream 5.0 Pro for storyboard images and Seedance 2.0 as the current executable video default, switching to Seedance 2.5 only when the selected provider exposes it.

atlassian/atlassian-mcp-server ↗

The official Atlassian MCP Server is a cloud-based bridge between your Atlassian Cloud site and compatible external tools. Once configured, it enables those tools to interact with Jira, Confluence, Jira Service Management, Bitbucket, Compass, Loom, and Atlassian platform data (Projects, Goals, Teams, Focus, Talent, and the Teamwork Graph) in real time. Authentication uses OAuth 2.1 or API tokens, so every action respects the user's existing access controls.

atlassian/forge-skills ↗

Atlassian Forge lets you build and deploy apps directly on the Atlassian platform - issue panels, Confluence macros, dashboard gadgets, and more. The Forge Skills Plugin bundles several Forge-focused skills plus MCP-backed tooling so your agent can scaffold apps, review them before deploy, debug production issues, and stay current on Forge APIs and the Atlassian Design System.

atlassian/trello-mcp-server ↗

The official Trello MCP (Model Context Protocol) is a cloud-based bridge between your Trello account and compatible external AI assistants. Once configured, it lets those tools interact with your Trello boards, cards, and tasks using natural language.

atman-33/workhub ↗

All-in-one Dev Hub — a Windows desktop app where you and your AI agents work from the same task board, backed by a plain-Markdown Obsidian vault.

Atomic Agent ↗

Local-first CLI and TUI coding agent that runs open-weight models entirely on your machine via a llama.cpp fork.

Atomic-Mail/atomicmail ↗

Read and write email through the Atomic Mail from an AI agent. Handles proof-of-work authentication and JMAP so the agent thinks in JMAP method calls.

atoslins/metodo ↗

Coding agents fail in three recurring ways. They call something impossible after a single probe. They switch approach at the first difficulty, comparing an option they measured with one they only imagined. And they apply a fix in three of seven places, prove one of four effects, and report the job as done.

atretyak1985/swarmery ↗

Local control plane for Claude Code: see every session, approve permission prompts from one queue, delegate tasks to headless agents in git worktrees

Atri10/executor ↗

An initiative-scoped workflow system for coding agents. You describe a major idea; the engine takes it through intake, discovery, architecture, design, specification, planning, plan regression, execution, review, and verification — with a strict per-initiative ID namespace, separated thinking and execution stores, and schema-enforced contracts at every state transition.

attac-t/the-foundry ↗

Foundry is a protocol, not a tool. It installs on a repository you already have, and today it runs on the Claude Code CLI.

Attemainio/dotnet-toolkit ↗

Compiler-aware C# code intelligence for Claude Code and Codex.

Attio ↗

Attio API integration with managed OAuth. Manage CRM data including people, companies, and custom objects.

attio-api ↗

Attio API integration with managed OAuth. Manage CRM data including people, companies, and custom objects. Use this skill when users want to create, read, update, or delete records in Attio, manage t…

attorneynate/legal-skills ↗

Agent Skills is an open standard for giving AI agents new abilities: a skill is a folder with a SKILL.md file of instructions and any scripts it needs. The same folder works in Claude and Claude Code, ChatGPT and Codex, Gemini CLI, GitHub Copilot, VS Code, Cursor, and many other agents. Each skill here is self-contained and can be installed on its own.

AtulPurohit/Antigravity-Awesome-Skills ↗

🚀 The ultimate collection of 300+ production-ready agentic skill definitions for AI coding assistants. Optimized for Claude Code, Antigravity, Gemini CLI, Cursor, Copilot, AutoHand Code, Kiro, and more.

atvari-eu/nix-skills ↗

Install individual skills via the skills CLI

Atypical-Consulting/claude-legends-review ↗

AI code reviews by Elon Musk, Steve Jobs & Linus Torvalds. Three personas debate your code until consensus. Claude Code skill — install in 10 seconds.

Audio ↗

Process, enhance, and convert audio files with noise removal, normalization, format conversion, transcription, and podcast workflows.

Audio Generation ↗

AI audio generation and text-to-speech powered by CellCog. Voiceover, narration, voice cloning, avatar voices, sound effects, music, podcasts, dialogue.

audio-drama-voice-studio ↗

Allocating each character in the script to a single sound color, with the whole line of white sequences arranged in the sequence of the scripts, and the numbering, which can be dragged directly into the editing software.

audit ↗

Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity…

audit-website ↗

Audit a website with the squirrelscan CLI and fix the findings in code. Runs SEO, performance, security, technical, content, accessibility, and 16 other rule…

auditfellow/auditfellow-plugins ↗

Your internal audit team's methodology, loaded as a skill before the model writes. Findings, risks, controls, workpapers, GenAI audits, data strategy and AI usage documents come back in your team's format, checked, with N/A wherever your organization never supplied a value.

augchan42/inkstone ↗

Custom Claude Code skills by Augustin Chan.

auge2u/lisa-helps-ralph-loops ↗

Give Claude Code a memory before it touches your code.

AugentaAI/augenta-plugin ↗

Help your agents remember and share their work across projects.

AugustusW/audio-tldr-skill ↗

Claude Code skill: summarize videos, audio & podcasts with local cached transcription

AugustusW/parcel-kau-a ↗

Track Taiwan parcels from an agent skill — six couriers read directly, no API key

aunysillyme/website-build-skill ↗

A skill pack that turns your AI into an expert website builder. It teaches your LLM or agent current, researched practice in design, brand, accessibility, performance, search, security, stacks and code, so the sites it builds look and work like a professional made them.