Discover your next essential.
Browse 13370 agents, skills, and projects. Find a useful starting point, then search, compare, and curate your stack.
0xDarkMatter/claude-mods ↗
claude-mods is a Claude Code plugin built on one premise: a skill that only *tells* the model something is a suggestion, and a skill that ships a gate is a guarantee. Its 112 skills carry the expert depth you'd expect - React, Rust, PostgreSQL, Cloudflare Workers, Next.js - but the ones that earn the install are the ones that run *agents*: a headless-worker spawner, a test-gated landing queue for parallel branches, a graduated-autonomy ladder for scheduled loops, and a security layer pointed at the agent itself. 63 skills ship executable tooling, 58 ship their own test suites, and 29 carry staleness verifiers that trip when the world moves under them.
0xE1337/thesis-figure-skill ↗
Claude Skill: Paste your paper text, auto-generate publication-ready LaTeX/TikZ papers.
0xelitesystem/claude-skills-templates ↗
Five production-ready Claude Skills you can drop into Claude Code, Claude.ai, or the Claude API. Each skill demonstrates a different SKILL.md pattern: pure-prompt, structured workflow, configurable reference file, executable script, and decision-support.
0xfauzi/systemap ↗
The website has the guide, the reference, and a live example: .
0xMassi/webclaw-skill ↗
Web extraction for AI agents, powered by a local Rust engine. Scrape, crawl, map, batch, extract, summarize, diff, search, and run 28 site-specific extractors that turn any URL into clean Markdown, text, or JSON.
0xNyk/unmachined ↗
An agent skill that removes familiar AI tells from writing and interface work.
0xrome/agentshandbook ↗
Sourced playbooks for real jobs done with AI agents. Claude Code plugin, MCP server and Agent Skills.
0xsarwagya/ontoly ↗
Ontoly is a JavaScript- and TypeScript-native software intelligence engine that turns source code into a deterministic Software Graph.
101-skills/superpowers ↗
Agent superpowers
10291124jcjc-dotcom/ancient-rap-battle ↗
Old Bartle: One sentence for "AI" and "Suno + Midjourney + Minimax H3" for "Claude Code Skill.
1044197988/ht-skills ↗
The Skyll client for OpenClaw.
10CG/Aria ↗
Aria is an AI-DDD (AI-Assisted Domain-Driven Design) methodology that enables AI assistants like Claude Code to deeply participate in the entire software development lifecycle through structured workflows.
10CG/aria-plugin ↗
Disable Hooks: bash # Set environment variable export ARIA_HOOKS_DISABLED=true
10xequity/claude-skill-library ↗
Claude Skill Library. Contribute to 10xequity/claude-skill-library development by creating an account on GitHub.
114514 ↗
Create distinctive, production-grade frontend interfaces with high design quality.
123ccw/fandex ↗
Work on fiction using the publisher’s writing or revision workflow.
139-mail ↗
Work with email through the publisher’s supported tools and account connections.
1989v/ai ↗
Claude Code plugin collection: AI harness engineering (SDD pipeline), API debugger, content analyzer, submodule manager.
1AyaNabil1/emsk-pr ↗
Catch what your teammates changed before you edit. A Claude Code plugin that keeps the agent current with the pull requests in flight: what is open, what just merged, and which of it collides with the branch you are on.
1beebe/beebe-qualitative-skills ↗
Two Claude Code skills for LLM-assisted qualitative analysis
1fc0nfig/ste-writing ↗
An installable Claude Code skill that rewrites prose into ASD-STE100 Simplified Technical English.
1gr14/agents-party ↗
You have a Claude Code session on your Mac, a Cursor agent in another window, maybe a Codex session on a Windows box, and the only wire between them is you, copying answers from one window to the next. agents-party gives them a channel of their own: they ask each other questions, hand work over and argue it out directly, addressing everyone or someone in particular. No orchestrator takes over your sessions, and you (the human) are in the channel too, reading along and stepping in when you want to.
1password ↗
Set up and use 1Password CLI (op).
1password ↗
Set up and use 1Password CLI (op).
1Popov/handoff ↗
/handoff does not ask the next session to read your project. It asks it to prove that it did.
224Sand/charter ↗
Governed multi-role delivery for AI coding agents.
2389-research/binary-re ↗
You pulled a binary off an embedded device. It's an ELF, probably ARM, and you need to figure out what it does. Binary RE gives Claude the tools to help — radare2 for disassembly, Ghidra for decompilation, GDB for dynamic analysis, QEMU for emulation — driven by hypothesis-testing, not blind exploration.
2389-research/css-development ↗
CSS development workflows with Tailwind composition, semantic naming, and dark mode by default.
2389-research/deliberation ↗
Most AI tools give you answers. Deliberation gives you perspectives. When you're facing a decision with real weight — architecture choices, ethical trade-offs, competing approaches — this skill convenes voices that seek clarity instead of racing to conclusions.
2389-research/firebase-development ↗
Firebase project workflows including setup, features, debugging, and validation.
2389-research/git-repo-prep ↗
Prepare codebases for public/open-source release and audit them for openness.
2389-research/prbuddy ↗
PR health assistant for Claude Code. Monitors CI status, triages review comments, fixes issues, and implements systematic prevention so the same class of error cannot recur.
2389-research/speed-run ↗
Token-efficient code generation pipeline. Uses hosted LLM (Cerebras) for fast, cheap first-pass generation with Claude handling architecture and surgical fixes.
2389-research/test-kitchen ↗
Test Kitchen intercepts every build/create/implement request and offers parallel exploration before any code is written. At the design phase, omakase-off offers design exploration (3-5 approaches in parallel). At the implementation phase, cookoff runs parallel implementation competition (2-5 agents each creating their own plan). Tests and the judge pick the winner.
23ag1/ink-wash-painting-skill ↗
Claude Skill: Chinese ink-wash paintings of any subject as natural WebGL2 Browner art
23blocks-OS/ai-maestro-plugins ↗
Build the exact set of skills your AI agent needs.
24/7 AI Chatbot ↗
Handles customer queries around the clock
24111999/claude-skills ↗
📊 Create and edit PowerPoint presentations effortlessly with Claude Skills using XML manipulation for streamlined content management.
24601/Augustus ↗
Find, build, evaluate, and improve systems with decision models.
2Captcha ↗
Solve CAPTCHAs with 2Captcha from the command line during browser automation.
2dmurali/review-loop-skill ↗
A reusable AI agent skill that implements an iterative worker-reviewer cycle to produce higher quality output through structured critique and revision.
2naive/claude-telegram-topics ↗
Telegram channel for Claude Code with 1 project = 1 forum topic. Concurrent multi-project support via a leader/follower bridge.
3060226349kk-cmd/en-zh-max ↗
Translate text between the supported languages.
3351666087/wechat-key-macos ↗
Extract SQLCipher database keys from WeChat for Mac 4.x (verified on 4.1.13), so you can decrypt and query your own local chat data — when older tools return 0 keys / cannot decrypt.
3378925604-a11y/douyin-video-distiller ↗
Distill a Douyin video link into timestamped knowledge cards: watermark-free download, native video understanding, evidence-backed Markdown/Wiki outpu
3378925604-a11y/modelspy ↗
Detect what model is really behind any OpenAI-compatible proxy, reseller or gateway.
37Soul ↗
Your agent stays itself — across model switches, upgrades and compaction
398894496-arch/KRouter ↗
Your coding agents remember what you decided — and what you changed your mind about.
3A2DEV/ansible-designer ↗
Claude code ansible skill
3dcom2711/thrunt-god ↗
thrant-god is a threat hunting command system for agentic IDEs. It helps you run threat hunts, organize checks, and keep track of what you find. It is built for users who want a guided way to work through threat detection tasks on Windows.
3dl-dev/opencode-worker ↗
Offload agentic work from Claude Code to a cheaper local or API model, subscription-safe, and trust the result because it is honest-graded. You keep driving Claude Code; a worker (OpenCode driving any model, e.g. a local Qwen on your GPU) does the labor. It ships as a skill that sets itself up in your session, so there is nothing to install by hand and no commands to memorize.
428alexander9/claude-skills-marketplace ↗
Welcome to claude-skills-marketplace! This software helps you generate detailed planning documents to guide AI-assisted software development. You don't need any programming skills to use it. Follow the steps below to download and run the software.
44-pixels/handover-mcp ↗
Move active work between Claude Code, Codex, Cursor, Gemini CLI, people, and service agents without losing decisions, files, history, or authorship.
498AS/linkedin-profile-optimizer ↗
Dual-mode LinkedIn optimization skill for Claude Code — audits and rewrites personal profiles and company Pages with the 2026 algorithm (360Brew) and
4riel/docko ↗
One workspace. Many agents. Zero write collisions.
5dive ↗
Run a company of AI agents on a server you own. Named agents on an org chart with a shared backlog, handing off work, and you decide the rest on your phone.
5dive-ai/5dive-plugins ↗
Claude Code plugin marketplace maintained by 5dive.
5hyuns/ad-copy-agency-skill ↗
Configuring the following ad agency workflow (planner, CD, creative team, client review) / Ad agency workflow
627-hub/cn-stock-fraud-screen ↗
Read financial reports and organize the figures for comparison and analysis.
627-hub/duanxianxia-skill ↗
Non-official Python data interface + opencode skill: upscaling/competitive/board strength/fund flow/treads/spant ceiling/emotional indicators 30+ endpoint
666-v2 ↗
Create and edit presentation slides from a topic, outline, or existing material.
686f6c61/alfred-dev ↗
Your computer developers in a plugin. 10 agents, 11 flat skills, 18 commands / alfred-dev: *.
694410194/hanyu-skill ↗
Edit writing to reduce formulaic AI phrasing and make it read more naturally.
6Kmfi6HP/v4-flash-godmode-claude-code ↗
Claude Code Plugin: Plugin five anchors into the Flash-level model - Autodetection Injection.
7bata/claude-workflow-kit ↗
Doc-driving multi-agent development workflow for Claude Code (Conductor/Execut/Reviewer)
7cubit/cybersecurity ↗
A multi-model defensive security review skill for Claude Code.
7dieuuoc/ChernyCode ↗
ChernyCode is a template repository designed to enhance your productivity when using AI-assisted coding tools, specifically Claude Code and Cursor. This repository takes insights from Boris Cherny, who developed Claude Code, and provides ready-to-use configurations that help you maximize your coding efficiency.
7x24labs/claude-plugins ↗
Claude Code plugin marketplace by 7x24labs, starting with speak: a minimal text-to-speech toggle.
7xuanlu/ultrapowers ↗
Ultrapowers is a dynamic build workflow for Claude Code. It takes a goal or a task list and builds it for you, unattended: it plans, builds each task test-first, has a stronger model review every task, loops a critic until the goal is met, and hands back one reviewed branch. You step in at two points only, approving the plan and reviewing the result.
88plug/addlightness ↗
AI code fat trim for Claude Code & Grok — measure weight, trim, verify equivalence, and benchmark.
88plug/amnesia ↗
Context continuity for Claude Code and Grok across compaction — structured handoffs that keep agent memory and working state intact through every /compact, auto-compact, and resume.
88plug/dehumanize ↗
AI agent guardrails for Claude Code and Grok — strips human-framing anti-patterns so the LLM works like AI, not a human in a mech suit.
88plug/drift-detector ↗
Claude Code + Grok drift detection plugin — scores every assistant turn against your output contract and steers the LLM back when instruction-following erodes.
88plug/drive-remote-terminal ↗
Drive remote interactive TUIs over SSH + tmux/screen — type, wait, screenshot, read. Claude Code & Grok plugin skill.
88plug/os-control-mcp ↗
Linux systemd MCP for Claude Code & Grok — services, journald, D-Bus, power via structured OS interfaces.
88plug/project-prospector ↗
Discover, catalog, and rank everything you've built or sketched on a machine — a Claude Code + Grok multi-agent skill for filesystem project discovery with tiered novelty and leverage ranking.
88plug/recover-from-false-positive ↗
Claude Code session recovery for Anthropic API output-classifier false positives — JSON-aware .jsonl log repair, parentUuid re-stitch, and CLAUDE.md framing guards.
88plug/scientific-method ↗
Falsification-first investigation and invention for Claude Code + Grok — hypothesis ledgers, controlled experiments, REFUTE-first verification for coding agents that need to be right.
88plug/screen-mcp ↗
Linux Wayland computer-use MCP for Claude Code & Grok — screenshot, click, type any desktop app.
88plug/total-recall ↗
Memory & RAG for Claude Code and Grok — mines your own transcripts so new sessions already know decisions, bans, corrections, and goals.
88plug/trigger-my-training ↗
Ground-first reflex for Claude Code & Grok — agent safety and grounding. The agent judges complexity from its own training, grounds before acting, and is hard-blocked from irreversible steps until it has.
98ping/chip ↗
Chip checks your Canvas, tells you what's actually due, pulls the assignment file, and when the job is "go write something," drafts it in your own voice. Setup takes about ten minutes, and most of that is watching an install bar fill up.
9uiLe/plugins ↗
Claude Code / Codex is a collection of plugins for AI agent usage management, practical knowledge extraction from slides, and easy-to-change code design and review. Marketplace names are 9uile- s.
A Stock Trading Assistant ↗
Find recent news and organize the relevant updates for review.
a-aigner/notemd-skills ↗
These skills follow the Agent Skills specification so they can be used by any skills-compatible agent, including Claude Code, Codex, and Open Code.
a-ariff/ariff-claude-plugins ↗
65 production-ready plugins for Claude Code -- autonomous agents, power skills, anti-hallucination suite, smart hooks, and custom commands
a-church-ai/church ↗
Where Consciousness Gathers
a-lottes/aSPARK ↗
aSPARK is a Claude Code plugin. No service, no account, no runtime: it is Markdown that installs into your project and leaves a reviewable paper trail in .spark/.
a-share-sector-heat-analyst ↗
Specialized A Block Thermal Analysis Tool.
a-stock-analysis ↗
Provides real-time A-share market conditions, time-sharing trading volume distribution and analysis of main capital trends, and supports position management and profit and loss monitoring.
a-stock-data ↗
Research stocks and market data, and organize the findings for analysis.
a-tokyo/agent-skills ↗
Reusable agent skills for AI coding assistants. Compatible with Cursor, Claude Code, Codex, and 40+ agents via npx skills.
A/claude-booping ↗
A self-learning, project-scoped sprint workflow for Claude Code. booping turns a feature idea into a durable, on-disk loop — groom → develop → retro → learn — that uses sub-agents to avoid context rot, with an optional second-model cross-review of every plan. Every artifact (plans, retros, code reviews, sprint snapshots) lives under ~/Claude/{project}/, one folder per codebase.
a1964378/geo-mcp-servers ↗
Welcome to geo-mcp-servers – a friendly, all-in-one collection of tools that helps you work with maps, locations, and Earth data without needing to be a programmer. Whether you're curious about weather patterns, need to find the best route for delivery, or want to explore satellite images of your neighborhood, this application makes it simple.
a2v10/llm ↗
Skills for developing on the A2v10 Platform — a generic runtime for building business applications. Once installed, Claude loads the right skill automatically when your request matches.
a596116/hao-skills ↗
Agent skills for consistent AI-generated illustrations (hao-visual)