kortix-ai

Discover, compare, and run AI models using Replicate's API. Use this skill whenever the task involves AI-generated media — images (text-to-image, style transfer, editing, upscaling, background removal), video, audio, or any other ML model output. Requires a REPLICATE_API_TOKEN — ask the user for it if not already set.

Use for distinctive production-grade websites, landing pages, and interactive web experiences with strong design and QA discipline.

Transcribe any audio or video file to text using Whisper (Groq or OpenAI). Use when the agent receives voice messages, audio files, video messages, or any media with speech. Triggers on: 'transcribe', 'what does this say', 'voice message', 'speech to text', 'audio', any file path ending in .ogg .mp3 .mp4 .wav .webm .m4a .flac .oga .oga

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Control desktop applications on the user's machine using agent-click. Use when you need to click buttons, type text, read screens, scroll, drag files, move/resize windows, open/quit apps, interact with UI elements, or automate desktop workflows. Triggers: 'click on', 'open app', 'type into', 'scroll down', 'drag file', 'take screenshot', 'read the screen', 'interact with UI', 'desktop automation', 'computer use', 'agent-click'. Built on agent-click (https://github.com/kortix-ai/agent-click, https://www.agent-click.dev/) — an open-source computer use CLI by Kortix. Right now only works on macOS.

Create, manage, validate, preview, and export HTML presentation slides (1920x1080). Load this skill when you need to build a slide deck, export to PDF/PPTX, or preview slides in a browser.

Interact with the user's local machine via Agent Tunnel. Use when you need to read/write files on their computer, run shell commands locally, take screenshots, click, type, control the mouse/keyboard, manage windows and apps, read/write the clipboard, or use the accessibility tree to interact with UI elements. Triggers: 'access my machine', 'local file', 'on my computer', 'my desktop', 'take a screenshot of my screen', 'run this on my machine', 'click on', 'open an app', 'accessibility tree'.

Deep research agent skill. Use when the user needs thorough, scientific, truth-seeking research on any topic -- investigating claims, finding primary sources, synthesizing evidence, producing cited reports. Triggers on: 'research this', 'investigate', 'deep dive', 'find sources', 'what does the evidence say', 'literature review', 'fact check', 'analyze the research on', any request requiring multi-source investigation with citations.

Full-stack web development with Convex + Vite React. TDD-driven, strict TypeScript, fully autonomous. Covers scaffolding, schema design, backend functions, frontend components, testing, styling, and deployment. Use when building web apps, sites, or frontend tasks from scratch or adding features to Convex projects. Triggers on: 'build a web app', 'create a site', 'Convex app', 'React app', 'full-stack', 'frontend', 'build me an app', any request to create or modify a Convex + Vite React application.

Complete Kortix sandbox system reference. Covers: container image, s6 services, filesystem layout, persistence model, environment variables, secrets management (API for setting/getting/deleting env vars), ports, runtimes, init scripts, cloud mode, desktop environment, deployments (deploy apps to live *.style.dev URLs), cron triggers (scheduled agent execution), semantic search (lss), session search & management (API + on-disk queries), skill creation guide, and all installed tooling. Load this skill when you need to: understand the sandbox, debug services, configure the environment, set API keys/secrets, deploy web apps/APIs/static sites, schedule cron jobs, search files semantically, query session data, or create new skills.

Create professional logos through an intelligent, iterative design process. Use this skill when the user wants to create a logo, icon, favicon, brand mark, wordmark, or any visual brand identity mark. Triggers on: 'create a logo', 'design a logo', 'make me a logo', 'logo for my brand', 'I need a logo', 'brand mark', 'wordmark', 'logomark', 'icon design', 'favicon'. This is NOT a one-shot image generator — it researches, strategizes, generates symbols with AI, visually inspects every output, then programmatically composes them with real Google Fonts typography into complete logo systems (logomark, wordmark, combination marks in multiple layouts).

Scientific paper writing in LaTeX -- full pipeline from structure to compiled PDF. TDD-driven: every section is compiled and verified before moving to the next. Covers project scaffolding, citation management (OpenAlex to BibTeX), per-section academic writing with self-reflection, figure/table inclusion, LaTeX compilation, and comprehensive verification. Triggers on: 'write a paper', 'create a paper', 'academic paper about', 'scientific paper', 'LaTeX paper', 'write up results as a paper', 'draft a paper on', 'research paper about', any request to produce a formal academic/scientific paper in LaTeX. Assumes research findings, data, and/or figures already exist or will be provided -- this skill handles the WRITING, not the experimentation.

Use this skill any time the user wants to create, edit, or export a slide deck presentation. This includes any task involving slides, decks, pitch decks, keynotes, or visual presentations. Trigger when the user says anything like 'create a presentation', 'make slides', 'build a deck', 'presentation about X'. The deliverable is a set of HTML slides (1920x1080) created via the presentation-gen tool, with optional PDF/PPTX export. Do NOT trigger for documents, reports, spreadsheets, or web pages — only slide deck presentations.

REQUIRED for any task that involves operating a desktop application — opening apps, clicking buttons, typing into fields, pressing keys, scrolling, dragging, reading what's on screen, moving or resizing windows, or verifying state after an action. Always use the `agent-cu` CLI commands (open, snapshot, click, type, key, find, scroll, drag, batch, wait-for) instead of falling back to `open -a`, AppleScript, `osascript`, `xdotool`, `System Events`, or any other shell workaround — those can't read state back, don't verify, and are fragile across app updates. agent-cu is the canonical computer-use tool for controlling any macOS / Linux / Windows / Electron app via accessibility APIs. Trigger on prompts like "open Music and play X", "search for Y in Maps", "fill out this form", "compute in Calculator", "send a Slack message", "drag this file", "read what's in the current window", or anything where a human would click/type/look at a desktop app.

Full semantic search over Desktop files, agent memory, and knowledge. Use when the agent needs to find relevant files or search knowledge semantically.