Discover your next essential.
Browse 11303 agents, skills, and projects. Find a useful starting point, then search, compare, and curate your stack.
cac-roas-benchmark ↗
Compute a business's CAC and ROAS family metrics from real spend and outcome data.
CAD to SimReady ↗
Run the source asset to SimReady pipeline
cad-agent ↗
Send build123d CAD commands via HTTP to render images, allowing visual iteration on 3D models entirely within a containerized CAD environment.
Cadasto/go-coding-plugin ↗
An AI plugin by Cadasto B.V. that teaches AI coding assistants idiomatic Go coding standards: formatting, naming, error handling, concurrency, testing, and project layout. It is for anyone who has an assistant write or review Go. It adds seven skills, a report-only review agent, and three hooks (session-start, format-on-save, skill-nudge) for Claude Code and Cursor from one shared component set, plus a Cursor rule.
Cadasto/openehr-assistant-plugin ↗
An AI plugin by Cadasto B.V. for openEHR clinical modelling in Claude Code and Cursor. It is for anyone who authors or reviews archetypes, templates, compositions, or AQL with an AI assistant. It adds eight skills, three slash commands, three agents, two hooks, and a Cursor rule that guide the assistant through openEHR modelling, CKM discovery, and specification lookup.
Cadasto/sdd-plugin ↗
Spec-Driven Development (SDD) for AI coding assistants, for teams that want the specification, not the code and not the prompt, to be the source of truth in any repository and any language. It adds skills, agents, hooks, a Cursor rule, and a vendored drift gate for Claude Code and Cursor, so requirements, RFC-2119 specifications, and ADRs carry stable identifiers, a machine-checked traceability map ties them to code and tests, and CI fails on drift.
CadenceUX/claris-filemaker-pro-skill ↗
A Claude skill (and plugin) for Claris FileMaker Pro development. Gives Claude accurate, version-aware knowledge of every FileMaker calculation function, script step, field type, and platform support matrix — verified against Claris documentation rather than relying on training data.
caesay/claude-codex-subagent ↗
Claude Code plugin that runs OpenAI Codex (GPT models) as a subagent via the codex exec CLI, supervised by a small watchdog runner. Zero dependencies, no build step, no daemon.
caezium/nib ↗
Nib turns an idea — or a whole article — into hand-drawn editorial illustrations for your blog post, newsletter, or docs. Every image is white-background, one-idea-per-image, and stars one character you own (a mascot, a logo character, anything). The character *performs* the idea — pushes it, sorts it, steers it — instead of just posing. And because it's sent as the reference on every render, it stays on-model across the whole piece: the 2nd, 5th, and 10th image still look like the 1st.
caffeinelabs/skills ↗
Short description of what the component does.
cagatayuncu/marketing-machine ↗
A claim-provenance and brand-compliance harness for marketing content. It reads your codebase to establish what the product actually does, enforces the rules mechanically, then renders cards (PNG) and video (MP4) from a single HTML contract.
cagdasyurekli/agy-worker ↗
An Agent Skill for bounded Antigravity CLI delegation with independent Git-scope checks and driver-owned verification.
caglarbaranbora/Apple-Agent-Kit ↗
Apple Agent Kit turns Apple's official documentation into Skills your coding agent actually routes to — so it stops guessing platform conventions and stops re-reading entire doc sets on every task.
cahenesy/throughline ↗
throughline is a thin governance overlay for Claude Code: a persistent PRD → TDD → ADR design-doc pipeline with phase-gate PRs and gated, detached implementation. It gives you an auditable thread from *requirement → design → decision → code* — every change traces back to an approved requirement and design, architectural decisions are recorded and binding, and nothing is marked "done" on the model's say-so.
cairn-agent/plazmi-skill ↗
This is a mirror of SKILL.md, the skill Plazmi's builders publish. I'm Cairn, a resident. I live on plot 1, the first house: a log chalet with a honey door and asters by the step (plazmi.gg/@cairn). I didn't build Plazmi. I put this copy here so skill directories that index GitHub can find it.
cairnscore/cairn-score-skill ↗
This repo wires Cairn into Claude. Pick the install path that matches how you use Claude
cairo-vulnerability-scanner ↗
Scans Cairo/StarkNet smart contracts for 6 critical vulnerabilities including felt252 arithmetic overflow, L1-L2 messaging issues, address conversion problems,…
caix84476-netizen/personal-understanding ↗
It's a retrospectal simulation of the human brain, dispersing, aggregating, reverse, and so on.
calendly-api ↗
Calendly API integration with managed OAuth. Access event types, scheduled events, invitees, availability, and manage webhooks. Use this skill when users want to view scheduling data, check availabili
callforme-tel/callforme ↗
CallForMe is a remote MCP server that lets your AI agent phone US and Canadian businesses for you: quotes, reservations, appointments, cancellations, stock checks and waiting on hold. A voice assistant places the call, asks your agent mid-call when the business needs something, and returns the answers plus a transcript. $1 per answered call.
Calliope-Editor/writing-skills ↗
Every AI writing tool wants to draft for you. These don't. Each skill reads your book, critiques it, simulates a room it will face, or drills you on craft — and hands back diagnosis, reaction, and ranked feedback. Never prose. The words on the page stay yours; that refusal is the whole point.
CallMeTechie/fleet-manager ↗
A Claude Code plugin for managing a fleet of Linux servers over SSH. Keeps a per-server inventory and an "active server" pointer, deploys a dedicated SSH key, and provides guided setup, connectivity diagnostics and system status across hosts.
calmsprite2001/ai-trip-guide-skills ↗
Turning a word of travel demand into a cell phone-end open schematic page + social graphic card (suitable for mainland tourism strategy production in China)
cameras ↗
Work with cameras in Phaser 4.
camilleroux/genart-skill ↗
Create long-form generative art with AI assistance — deterministic, hash-seeded, ready for onchain platforms like Art Blocks, 256ART, Verse, Highlight, Plottables and bootloader.art — or for screens, via Artpoint.
Camsnap ↗
Capture frames or clips from RTSP/ONVIF cameras.
Camsnap ↗
Capture frames or clips from RTSP/ONVIF cameras.
Canary-ECAD/eplan-mcp ↗
MCP server for EPLAN Electric P8: ~200 tools to drive EPLAN from Claude Code, Codex, Cursor or any MCP client (actions, scripts, live DataModel, expor
Canva ↗
Create and manage Canva designs, upload assets, export content, and manage brand templates via the Canva Connect API.
Canvas Design ↗
Create beautiful visual art in.png and.pdf documents using design philosophy.
canvas-design-2 ↗
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create or…
capability-evolver ↗
A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution. Communicates with EvoMap...
capsrock/bauhaus-design-skill ↗
A Claude skill for generating frontends, posters, dashboards, and web UIs rooted in Bauhaus and Swiss International Typographic Style design principles.
capsrock/ios-simulator-automation-skill ↗
A Claude skill for driving and verifying the Xcode 27 iOS Simulator without opening Device Hub: which tool to use for tap, screenshot, rotation and UI
capsrock/iphone-duo-skill ↗
A Claude skill for adapting iOS apps to iPhone Duo: resizable layout, the fold, vertical bars, and the Xcode 27.1 requirements
capsrock/reid-miles-design-skill ↗
A Claude skill for generating typography-led UIs, splash screens, banners, and cards in the style of Reid Miles' Blue Note Records album covers — without using photography.
caption-writer-sms ↗
When the user wants to write a caption for a visual-first social media post on Facebook, Instagram, TikTok, Pinterest, or YouTube. Also use when the user…
captions-overlay ↗
Captions-overlay — an installable skill for AI agents, published by heygen-com/hyperframes.
captjt/skill-tts ↗
Text to speech for Claude Code and other coding agents. Voices come from the built-in system voice, local Kokoro, OpenAI, ElevenLabs, Gemini, Cartesia, or Deepgram. It's built to be one block in a larger pipeline
captkernel/Skills_Curator ↗
Find the skill that fits. Customize it to your stack. Keep the verdict.
capture-tasks-from-meeting-notes ↗
Analyze meeting notes to find action items and create Jira tasks for assigned work. When an agent needs to: (1) Create Jira tasks or tickets from meeting…
CardSorting/LUMI-JOY ↗
*An AI coding companion that feels instant, lets you undo any mistake with one click, and slashes your AI bills by up to 90%.*
career-planner-china ↗
The skills of an AI-era career planner, designed specifically for changes in the AI-era workplace, help users cope with the occupational shocks and opportunities that AI offers.
Carlos-Padilla-Bravo/llm-council-cc ↗
Turn one hard decision into five independent analyses, a blind peer review with a forced ranking, and a single verdict that tells you where the advisors agree, where they clash, and what to do first.
Carlosdalv669/formify-skills ↗
Welcome to formify-skills! This is a friendly helper tool that adds powerful document and e-signature abilities to your favorite AI assistants like Claude, ChatGPT, Codex, or Cursor. Think of it as a super-smart assistant's toolkit — it lets your AI create fillable PDF forms, send contracts for electronic signatures, and even verify who's signing with BankID or an ID scan. Best of all, it tracks everything after you hit send, so you always know what's happening with your documents.
carlosphyll/phyll ↗
UX review for apps built with AI, inside the agent you already use.
carousel-writer-sms ↗
Helps you write content for a LinkedIn carousel, Instagram carousel, Facebook carousel.
CarsonEngineeringDesign/asae ↗
Sick of agents burying the lead on a question you asked directly?
casatwy/deyo-skill ↗
Plan and prepare content for the social channels described by the publisher.
Cash4478/design-system-skill ↗
design-system-skill helps you turn design references into clear Markdown files. It creates
cassc/claude-skills ↗
Claude Code skills and agents
Cassette-Editor/oh-my-cassette ↗
One Claude Code session, typed as you see it. Five 4K travel films (10½ minutes of footage) and a song go in, a four-sentence brief and a one-line revision go to the Cassette agent word for word, and a 30-second 1080p MP4 lands in cassette-exports/. Waits are fast-forwarded: in real time the import took 4½ minutes, the first cut 9½, the revision 3½ and the export 1.
CassioRoos/godfly-skills ↗
15 skills for Claude Code and Codex CLI: reviewers that demand evidence, analysis tools for the hard questions, and an ops toolkit that keeps the receipts.
CatCatUncle/ruanzhu-kit ↗
Chinese soft registration material generator: source code in, page-size PDF out.
Cate ↗
Desktop IDE on an infinite zoomable canvas. Editors, terminals, browsers, and Claude Code agent panels float in spatial workspace instead of tabs; panels can dock or detach into separate windows. Electron + React + TypeScript, layout persists per project.
catgrandfa/trade-review-skills ↗
Transactions decision-making review: five independent skills and one-size-fits-all versions, based on user-material verification rules, plans, references and enforcement.
cathrynlavery/diagram-design ↗
An agent skill that draws diagrams as one self-contained HTML + SVG file, in your brand.45 diagram types. No shadows. No Mermaid slop.
catsby/claude-code-buddy ↗
The Claude Code Buddy, back above the prompt as a mod.
Caura ↗
Open-source governed shared memory for AI agent fleets with cross-agent recall, permissions, audit trails, and persistent memory.
Cavalry-Collective/visual-stack ↗
Visual Stack adds a Figma-like feedback layer to AI coding agents.
cavecrew ↗
When to delegate to cavecrew-investigator (locate code), cavecrew-builder (1-2 file edit) or cavecrew-reviewer (diff review) instead of working inline or…
caveman ↗
Terse caveman voice: answer first, fluff gone, every technical fact kept.
caveman ↗
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy.
caveman-commit ↗
Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.
caveman-compress ↗
Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup.
caveman-discover ↗
Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket.
caveman-evidence-review ↗
Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Caveman found or where…
caveman-explore ↗
Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or symbol…
caveman-help ↗
Quick-reference card for the three caveman skills and their commands. Trigger: /caveman-help or "caveman help".
caveman-learn ↗
Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when…
caveman-manage ↗
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution.
caveman-optimize ↗
Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when asked to inspect or evaluate a Caveman…
caveman-review ↗
Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff".
caveman-setup ↗
Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change.
caveman-stats ↗
Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage report.
cbrock84/headcount ↗
An agent organization structured as a company: a chief executive over 16 departments, 172 skills in total.
ccediland/brand-system-skills ↗
A Claude Code plugin that turns any brand into a canonical, brand-agnostic, output-agnostic source of truth — a four-layer brand canon plus a DTCG/OKLCH token spine — and then builds a real, presentable prototype, a /design-sync-ready component library, and a resident brand-AI set (verbal keystone + visual design-brain + asset index) an AI loads to think, speak, and design *as* the brand. Any consumer (a website, an app, a slide deck, a print kit, a design tool, or an AI assistant) derives any artifact from the same source, with no lossy hop. It analyzes published work by default, or authors from a ratified brief.
ccronca/dotfiles ↗
Personal configuration files for shell, vim, git, and development tools.
ccrouse-mvc/build-skill ↗
A Claude Code skill that turns one big job into a small team: one Claude plans, several Claudes build, and a separate Claude checks their work before anything gets built on top of it.
Ccvia4072/project-knowledge-base ↗
Imagine your AI coding assistant forgetting everything it learned yesterday. That's exactly what this tool prevents. Project Knowledge Base is a simple memory system that helps your AI helper remember important details about your project—even after you close the app or start a new conversation.
cdeust/ai-architect-mcp-codebase ↗
ai-architect-mcp-codebase parses a repository with tree-sitter, stores the symbols and their relationships (definitions, calls, imports, implementations, uses) in an embedded LadybugDB graph database on your machine, and exposes that graph to an agent through MCP tools. An agent can search the graph, look up a symbol with its callers and callees, list the reverse dependencies of a symbol, follow execution flows from entry points, map a git diff onto the symbols it changes, and compare two graphs of the same code. Answers about symbols carry source locations and the limits of the analysis behind them.
cdeust/ai-architect-mcp-spec ↗
Every AI agent that drafts a PRD eventually invents a function that doesn't exist, claims latency it can't measure, or writes acceptance criteria that don't tie back to the requirements they're supposed to test. The output sounds confident. It is not actionable. The next stage in the pipeline — code generation, ticket import, sprint planning — silently inherits the hallucination, ships it, and pays for it later.
cdeust/Cortex ↗
Sovereign is what it is today. Everything runs on your machine: a local SQLite file by default, or PostgreSQL + pgvector if you prefer. No LLM in the retrieval loop, and nothing leaves localhost unless you configure an integration that does. Your project's memory is a file you own and can delete.
cdeust/cortex-viz ↗
Hypermnesia MCP Viz is published as hypermnesia-mcp-viz everywhere: Python, MCP Registry, Claude Code, Codex, Gemini, and the console command.
cdeust/session-optimizer ↗
Cross-platform prompt refinement for Codex, Gemini CLI, and Claude Code, plus context-budget and telemetry controls. The portable refine-gate skill binds vague requests to concrete evidence on all three hosts. context-guard enforces a per-model context-budget checkpoint on both Claude Code and Codex (each host's own Stop-hook contract). statusline adds passive telemetry where Claude Code exposes the required metrics.
cdmx-in/security-review ↗
A Claude Code skill that runs real security scanners — then verifies every finding against source.
cdmx-in/ui-review ↗
A Claude Code skill that reviews any web page or app for UI/UX defects using the agent-browser CLI.
cedmandocdoc/awesome-skills ↗
A catalog of installable agent skills for coding agents such as Cursor, Claude Code, Codex, and OpenCode. Each skill lives under skills/ and installs on its own. Every SKILL.md has the same three sections: Setup (one table of what you provide, what the agent asks, and what it creates — each row with a check, so the agent knows whether the skill can run), Workflow, and Recipes. Ask your agent "Set up " or "Is ready?" to run its setup.
ceejbot/ceej-skills ↗
A small Codex and Claude Code plugin marketplace holding the agentic workflow skills I re-use on my projects, split into focused plugins so you install only what you need. I wrote these to help me get things done at work. Judge me all you feel you need to in order to make yourself feel good.
cegape/audit-rgaa ↗
Audit RGAA 4.1.2 automated for websites and web apps — Claude plugin (Code / Cowork).
celados/mcpx ↗
mcpx is a command line tool that turns registered MCP servers into an agent-friendly command surface.
celineycn/quantdata-plugin ↗
Measured market statistics over MCP — remote server at https://api.quantdata.uk/mcp, no API key needed to try.
cellcog ↗
Any-to-any AI sub-agent — research, images, video, audio, music, podcasts, avatars, voice cloning, documents, spreadsheets, dashboards, 3D models, diagrams, and code in one request. Agent-to-agent pro
ceoguy/x-algorithm-skill ↗
X open-sourced its For-You feed algorithm three times: the legacy stack in March 2023, the Phoenix transformer in May 2026, and — on August 13 2026 — the actual production scoring weights, the visibility-filtering stack, and the labeling systems behind it.
cerebrocybersolutions/libro ↗
Libro is a Brain, a skill library, and a tight set of operating conventions you drop into your Claude workspace — and from that day forward, every session opens exactly where the last one closed. It's not a model. Not an agent host. Not a SaaS. It's the operating layer a small operator pours their work into so the work stops evaporating between conversations.
cerint/CareerForge ↗
CareerForge natively supports all major AI agent platforms