Discover your next essential.

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

Aiyo28/memento-os ↗

Memento OS is a persistent memory plugin for AI coding tools. Every conclusion is stored as a reasoning artifact with an invalidation trigger — your agent remembers what matters and knows when to re-evaluate.

aj604/toolshed ↗

A personal Claude Code plugin marketplace.

AJ888/promptbrake-skills ↗

promptbrake-free-tools/ is a portable instruction package for all five hosted PromptBrake MCP tools: injection payloads, OWASP risk mapping, ADLC release planning, custom response test packs, and agent tool-call packs. It contains no PromptBrake server implementation.

Ajarallah/sard ↗

Create step-by-step narrative explanations in Claude, using text, articles, books, or presentation material.

ajaygunalan/chapter-to-synced-lecture ↗

A Claude Code skill that turns a book chapter (PDF) into a video lecture: narration plus slides that animate along with it, given in the voice of the book's own author.

ajbarea/techne ↗

*A plugin marketplace for AI coding agents: skills for code repos and for documents, opt-in git guards, and a spoken Claude Code.*

ajinkyalahade/iOS-Dev-ClaudeCode-Skills ↗

Build real iPhone apps by describing them. 180 skills that teach Claude Code how to design, build, test, and ship Apple apps the right way, written for iOS 27, Xcode 27, and Swift 6.

ajitta/Game-Engagement-Retention-Skills ↗

Claude Code plugin for game engagement and retention: reward moments, lifecycle strategy, and ethical guardrails

ajitta/know-your-unknowns ↗

Claude Code plugin for blind-spot discovery, planning, and implementation review

akasecurity/ai-tc ↗

AKA Security — We secure agent harnesses at the source.

akaszubski/autonomous-dev ↗

A harness that wraps Claude Code with enforcement, specialist agents, and alignment gates to deliver consistent, production-grade software engineering outcomes.

akhilguptahub/fable-skill ↗

Make any AI model think more carefully before it answers.

akhilvarier2000/youtube-summarizer ↗

A Claude skill that summarizes YouTube videos, provides transcripts in user-selected language (with special Hindi handling), and formats output in Markdown with Summary and Transcript sections.

akidly/yasmine ↗

Official Claude Code plugin for Yasmine — AI voice order confirmation API.

aklofas/kicad-happy ↗

AI-powered KiCad electronics design review and analysis

akovalion/paranoid-qa ↗

Claude Code skills that turn an AI agent into a meticulous QA engineer.

Akshat2634/Codelens-AI ↗

Local-first ROI analytics for Claude Code, OpenAI Codex, and GitHub Copilot

akshayrao14/git-practices ↗

A personal grab-bag of git workflow tooling, shell config, Claude Code skills, SQL helpers, and an AI-pairing methodology for junior engineers. Each top-level directory is independent — clone the repo and pull in only what you want.

aksheyw/career-command-center-template ↗

Claude Code is Anthropic's AI coding assistant. It runs in your terminal, reads the files in your project, and can change them for you. A skill is a markdown file of instructions it follows when a matching job comes up, and a plugin bundles skills so they install in one step.

aksheyw/claude-code-deep-review ↗

Claude Code is Anthropic's AI assistant for writing software, and this is one file you hand it. It reviews your work through fourteen different lenses, then keeps going until a whole pass finds nothing new.

aksheyw/claude-code-learned-skills ↗

Claude Code is Anthropic's AI coding assistant. It runs in your terminal, reads the files in your project, and can change them for you. A skill is a markdown file of instructions it loads and follows on its own when a matching task comes up.

aksheyw/claude-code-ship-gate ↗

Claude Code is Anthropic's AI coding assistant: it runs in your terminal, reads your project's files, and can change them for you. Ship Gate is a plugin for it, a bundle you install and switch on in one go. Before Claude can push to your main branch, it has to get past whichever of the eight checks apply to what you changed, from tests and type checks through to a secret scan and a code review. Fail one and the push doesn't happen.

aksheyw/context-bridge ↗

Claude Code is Anthropic's AI assistant for writing software, and it starts every conversation knowing nothing about the last one. This skill, a markdown file of instructions it loads, gives each project a small wiki, then writes a paste-and-resume note when you finish, so the next one starts warm.

AL-JANEF/janef-forge ↗

JANEF Forge gives a coding agent one short engineering contract, a deterministic router, and 24 focused engineering and defensive-security capabilities that load only when a task needs them. It replaces three earlier projects, janefskills, Agent Engineering Stack, and LeanCode Engineer, with one architecture, one router, and one quality gate.

alainabo/aso-dual-agent-review ↗

By ASO Ltd. — the digital backbone of African business.

alanvaa06/award-craft ↗

Claude Code plugin that builds and elevates Awwwards-level landing pages on a fixed stack: Next.js + Tailwind + GSAP + Lenis, optional React Three Fiber. It writes the page's story as well as its code, and every run ends in a mandatory visual verify loop — no page ships on "the build succeeded" alone.

alanvaa06/forge-master ↗

Agentic loop-engineering for Claude Code. Turn a designed PRD into autonomous, verified, self-correcting execution — decompose into phases, route each by complexity, apply TDD discipline where demanded, verify against testable acceptance criteria, and learn across runs until the task is complete or cleanly blocked.

alapha888/agent-skills-en ↗

Listed on the M8ven Trust Index: [](https://m8ven.ai/mcp/alapha888/agent-skills-en?s=readme)

alapha888/session-handoff-kit ↗

A free kit for users of AI coding agents (Claude Code, Codex, Cursor, Gemini CLI): end every session with a structured handoff, so the next session — or the next agent — starts from facts, not from a degraded, over-full context.

albegosu/second-brain ↗

Save UI inspiration from any app. A vision model curates it into a private wiki and turns your taste into a DESIGN.md your coding agent builds from.

albertoarena/claude-laravel-event-sourcing ↗

A Claude Code skill that helps you design and generate event-sourced domain code for Laravel using spatie/laravel-event-sourcing.

albertoclemente/agentic-design-patterns-skills ↗

A complete set of 22 Agent Skills for Claude Code (and any SKILL.md-compatible agent) covering the 21 agentic design patterns from Antonio Gulli's *Agentic Design Patterns: A Hands-On Guide to Building Intelligent Systems*, plus a router skill that helps you pick the right pattern for a problem.

alboechat/appsec-vulnerability-auditor ↗

You give Codex or Claude code (a file, a diff, a PR, a directory). The skill produces a prioritized vulnerability report — Critical / High / Medium / Low / Informational — with

aldogor/aldogor-claude-plugins ↗

Claude plugins by Aldo Gorga, a public health researcher working on digital health and AI. They carry a way of working: sources verified before they are cited, documents reviewed for structure before prose, projects that keep a dated journal, and sessions that close with the project in order. Most of the writing guidance is for Italian and English scientific and institutional prose.

alebgl77/claude-inc ↗

Peer CEO, CTO, and CAIO executives · 9 departments · 64 skill manuals.

alebgl77/grafana-llmops-forge ↗

Point it at any Grafana. Get a complete AI/LLM observability suite: discovered, generated, deployed, and *visually verified*.

alegauss/roadkeep ↗

roadkeep-mark.svg 160x160 icon roadkeep-logo.svg 520x160 mark + wordmark roadkeep-banner.svg 1200x300 source for the header above roadkeep-banner.png 1200x300 the header above. Raster and absolute because this file is also the PyPI project page (RK19): a relative path resolves against pypi.org and an SVG is served as text/plain, so both render as broken. roadkeep-social.svg 1280x640 source for the link preview roadkeep-social.png 1280x640 upload at Settings > General > Social preview. This is what renders when the repo URL is pasted into LinkedIn, Slack or a link card anywhere else. Re-render either PNG after editing its SVG: msedge --headless=new --window-size=1200,300 \ --screenshot=docs/assets/roadkeep-banner.png \ file:///.../docs/assets/roadkeep-banner.svg -->

AlehHaiko/UX-directives-skill ↗

Author: Aleh Haiko · Read the book: alehhaiko.com/ux · Full guide: Skill for Claude

AleksandarBisevac/claude-plugins ↗

A Claude Code plugin marketplace with one theme: enforced engineering discipline — plan gates, test gates, sign-off gates, secret guards. The guards are deterministic hooks; the pipeline they govern is a step driver that prints the model one instruction at a time — which is which, row by row.

aleksandr-alhoff/seo-landing ↗

An agent skill for building high-performance, technically optimized SEO landing pages. Turn an AI coding agent into a technical SEO specialist.

aleksandr-chaika/flutter-clean-arch-skills ↗

Complete development pipeline for Flutter projects with Clean Architecture and BLoC state management.

alelaguard/agentguards-plugins ↗

Stop prompt injection, secret leaks and destructive commands before your coding agent acts on them. Works with Claude Code, OpenAI Codex, Gemini CLI, GitHub Copilot CLI and OpenCode.

AlessandroCaula/dot-claude ↗

A reusable .claude/ scaffold that gives you and Claude Code a persistent memory across sessions.

alex-feel/claude-code-artifacts-public ↗

A public library of reusable Claude Code artifacts — skills, hooks, rules, environment configurations, agents, and slash commands — ready to drop into any Claude Code setup.

alex-feel/claude-code-toolbox ↗

Automated installers and an environment configuration framework for Claude Code on Windows, macOS, and Linux.

alex-jb/shadow-mentor ↗

A cryptographic evidence layer for AI agents. Every session becomes a signed, hash-chained record you can hand an auditor. Verify offline with a single HTML file.

alex-macra/claude-codex-skills-assembly ↗

Reusable agent skills, deterministic activation, safety hooks, and installers for Claude Code and OpenAI Codex, with an agentskills.io-compatible skill surface.

alex-roc/zotero-agent ↗

zot gives you full read-write control of your *local* Zotero library: search, bulk-edit metadata, tag, deduplicate, import by DOI/ISBN/arXiv, export, enrich missing fields, and summarize PDFs into notes — scriptable from the shell or drivable by an AI agent. It ships as a CLI, an MCP server, a Claude Code skill, and portable AGENTS.md instructions.

alex-zwingli/plan-to-eat-mcp ↗

A drop-in MCP server, a CLI, and a standalone Node client that give Claude, ChatGPT, any MCP-aware assistant, or your own shell full read/write access to your Plan to Eat account.

Alexa CLI ↗

Control Amazon Alexa devices and smart home via the alexacli CLI.

alexander-danilenko/cortex-claude-code-plugins ↗

This repository is a Claude Code plugin marketplace. Each plugin bundles a few related skills for one domain, such as web development, testing, or Jira reporting. You pick the plugins that fit your work. Nothing else gets loaded.

AlexanderAbramovPav/scriba ↗

Timed words carry an ASR score when the backend provides one (otherwise null), a speaker-attribution margin and an overlap flag after successful diarization. These are uncertainty signals, not measured word/speaker accuracy. The benchmarks/ DER scorer uses raw diarizer turns against your checked speaker labels.

Alexandre-LPZ/ultracode-cockpit ↗

Full power. Your hands on the throttle.

AlexCiortan/setlist ↗

Setlist is spec-driven development for Claude Code. You write the setlist, Claude Code plays it, and git hooks stamped into your repository refuse work that skipped the process. It is for one developer or a small team who would rather review than type. Every feature arrives through a spec you approved, and the spec outlives the chat, a compacted context and a swapped model. Spec Kit and BMAD give the agent a process to follow. Setlist gives git a process to enforce, so it holds under any agent or none. It is a discipline control for cooperating use and no security boundary. How Setlist thinks is the ten-minute account a lead can forward to a team.

alexconner-79/ill-communication ↗

UX writing, not fighting. A Claude skill that writes and reviews human-sounding copy, with proper UX writing craft built in.

alexe-ev/product-plugins ↗

Status: stable. 121 skills authored Feb–Mar 2026.

alexei-led/cc-thingz ↗

Portable skills, agents, hooks, and Pi extensions for Claude Code, Codex CLI, Copilot, Cursor, Grok, and Pi.

AlexeyGOblov/visual-attention-audit ↗

Measure visual clutter and where the eye lands.

alexgreensh/anidoodle ↗

Art and animation, written as code.

alexgreensh/eval-genius ↗

Evals are suddenly everywhere. Every AI talk, every launch post, every hiring thread says you need them. Then you sit down to actually do it, and the questions start.

alexhooi/herdr-orchestrate ↗

Run a team of AI coding agents — Claude Code, Codex CLI, pi — as visible terminal panes you can watch, scroll, and interrupt. One orchestrator routes, reviews, merges. You get pinged twice: for a decision only you can make, and when it's done.

alexis-morain/verbatim-linkedin ↗

Work In Progress ---- The LinkedIn post skill for Claude that interviews you first. It cannot write anything you did not say.

AlexisBalayre/claude-code-config ↗

A complete Claude Code setup you can drop into any repo: path-scoped rules, 35 skills, 12 subagents, 7 deterministic hooks, and a multi-agent PR review that runs in GitHub Actions.

alexlivre/pagespeed-optimizer-alexlivre ↗

A universal AI agent skill for analyzing, auditing, and optimizing web applications to 100/100 on PageSpeed Insights and Google Lighthouse 13+ across Performance, Accessibility, Best Practices, SEO, and GEO (Generative Engine Optimization) for AI search engines (Perplexity, ChatGPT Search, Gemini, Google AI Overviews, Claude).

alexmakarski/critic-gauntlet ↗

A Claude Code skill that pits five AI models against your work as adversarial critics, surfaces their raw objections to you unfiltered, and synthesizes where they agree. For decisions and documents you cannot cheaply reverse.

alexmmatos/essentials-claude-code ↗

Evaluates how well a project takes advantage of Claude Code extensions — CLAUDE.md, .claude/settings.json, skills, subagents, rules, and MCP — plus whether the project documents SOLID principles and GoF design patterns — and produces a 0-to-100 score with concrete recommendations on what to add or improve.

alexsmedile/pricing-skills ↗

Stop quoting gut feelings. Start pricing like a strategist.

Alexxiang2008/awesome-skills-map ↗

22 Chapter Claude Skills Panorama + Full Source

Alexxiang2008/hlzd-b2b-export-skills ↗

Agent Skills for B2B industrial exporters — market research (HS code, UN Comtrade, Google Trends, tender), buyer finding (Alibaba + Volza customs), in

alexyc9381/agency-skill ↗

An AI automation agency that runs inside Claude Code. Five agents, one command. Free, MIT, no signup, no API key.

alexyc9381/court-skill ↗

Put your idea on trial in front of a jury of 12 Claudes.

alexyc9381/hiring-panel-skill ↗

Seven Claudes try to reject your resume, then it rebuilds it with every mistake fixed. Free Claude Code skill, MIT.

alexyc9381/launch-skill ↗

Launch your app the way NASA launches a rocket: 8 Claudes each check one part of it, and all 8 have to say GO. One Claude Code skill. Free, MIT, no signup, no API key, nothing to connect.

alexyc9381/learn-skill ↗

A Claude setup that stops making the same mistake twice, and runs on its own. One free Claude Code skill.

alexyc9381/linkedin-roast-skill ↗

Five Claudes roast your LinkedIn profile, each one alone: a recruiter, a hiring manager, a founder, an expert in your field and a peer at your level. Then the skill fixes the profile: a new headline, an About section with the keywords people search for, every experience entry rewritten, a banner file and a headshot prompt.

alexyc9381/mentor-skill ↗

Claude writes the code. You make the calls. One Claude Code plugin that makes you learn while you build. Free, MIT, no signup, no API key.

alexyc9381/night-crew-skill ↗

Give your app a night crew: three Claude Code workers that run in the cloud every night while you sleep, and leave you pull requests to review in the morning. One Claude Code skill. Free, MIT, no signup, no API key.

alexyc9381/shark-skill ↗

Pitch your idea to a Shark Tank-style panel of Claude sharks who want to say no.

Alexyskoutnev/research-skills ↗

Ten Claude Code skills for writing an ML paper, abstract to rebuttal. Not prompts. Recipes, axioms, and mechanical checklists, reverse-engineered from papers that got in.

alfadur7/llm-wiki-newsroom ↗

A multi-agent AI knowledge base run by a five-role "newsroom" — open-source, local-first, no vendor lock-in. Drop articles, documents, and PDFs into the raw/ folder, type a single command, and the newsroom — powered by an agent like Claude Code — reads them, extracts entities, concepts, and relationships, and organizes everything into a fully cross-referenced wiki, a structured and persistent alternative to RAG. Unlike most takes on the idea, the agent that *writes* a page is never the one that *reviews* it, and the authoring guidelines evolve themselves over time. Every new document you add also enriches the existing pages. This repo ships with a small example corpus — the debate over what "open source" means for AI — under wiki/, but the framework is domain-agnostic.

alfredtech2026/shopify-app-review-brief ↗

A privacy-first workflow for turning low-star Shopify App Store reviews into an actionable product and support brief.

alfredzhang98/research-obsidian-skill ↗

A Claude Code skill suite that turns research papers and conversations into a well-organized, cross-linked Obsidian knowledge base. Built around one idea: every paper gets read once and filed once — into a structured note with figures, a verdict, and research openings, linked into a topic hub that turns a pile of papers into something you can actually learn from.

ali-demirbas/claude-lifecycle ↗

*Lifecycle marketing and CRM strategy as a Claude Code skill: customer journey design, behavioral segmentation, lifecycle messaging and channel copy for email, push, SMS, in-app and WhatsApp.*

ali-rajabpour/MonkeyArmy ↗

Opus commands, monkeys type, Opus signs off. A Claude Code plugin that delegates micro-tasks from a frontier-model supervisor to cheap workers (DeepSeek & co. via your local 9Router), isolated in disposable git worktrees, verified by the server, and reviewed and merged back by the supervisor.