qu-skills

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video

Web search and content extraction with Tavily and Exa via inference.sh CLI. Apps: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract. Capabilities: AI-powered search, content extraction, direct answers, research. Use for: research, RAG pipelines, fact-checking, content aggregation, agents. Triggers: web search, tavily, exa, search api, content extraction, research, internet search, ai search, search assistant, web scraping, rag, perplexity alternative

Run 250+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok

Run 250+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok

Picks the right i2v model for your image type—product shot, landscape, illustration—and guides you through motion prompts and camera moves to get a usable clip in one go.

Takes a text prompt and produces high-quality product, marketing, or mockup images using Google's Gemini image models. Can edit existing images or combine multiple inputs.

Creates images from text, edits existing ones, or combines multiple reference images into one. Uses Google's latest image model and can ground results in live search.

Ingests a blog post, podcast transcript, or video script and generates 3–5 ready-to-post formats: LinkedIn thread, carousel, short-form clip quotes, newsletter snippet, and more.

A pre-built React component with agent runtime, tool-calling, streaming, and human approval built in. Paste it, wire up your Claude API key, and start routing user requests through Claude.

Uploads an image and returns a clean transparent PNG with the subject isolated. Works on product shots, portraits, and cluttered backgrounds without manual masking.

Turns an idea or insight into a formatted LinkedIn post with a hook, body, and CTA tuned to what LinkedIn's algorithm rewards—plus formatting tricks that stop the scroll.

Creates on-brand Open Graph and Twitter Card images sized and formatted for each platform, with text placement that survives the crop and reads at thumbnail size.

Walks through script formulas, scene breakdowns, pacing rules, and the exact tool chain to move from script to voiceover to final edit — no video experience required.

Converts meetings, podcasts, or video to text with millisecond-accurate word timestamps, speaker labels, and subtitle files ready to sync.

Uses Alibaba's Qwen model to render images with legible text overlays and fine detail. Good for marketing assets, social graphics, and designs that need both image and copy to coexist clearly.

Investor pitch deck structure with slide-by-slide framework, visual design rules, and data presentation. Covers the 12-slide framework, chart types, team slides, and common investor turn-offs. Use for: fundraising decks, investor presentations, startup pitch, demo day, grant proposals. Triggers: pitch deck, investor deck, startup pitch, fundraising deck, demo day, pitch presentation, investor presentation, seed deck, series a deck, pitch slides, startup presentation, vc pitch, investor meeting

Takes a dataset or table and recommends the right chart type, labels, colors, and annotations so your insight jumps off the page. Includes alternatives to common mistakes like pie charts.

Turns a script or conversation into studio-quality audio with distinct character voices, emotion, pacing, and natural speech patterns. Ready for podcasts, audiobooks, or explainers.

Wires Claude to live web search (Tavily or Exa), fact-checks answers against real sources, and returns grounded responses with citations instead of hallucinations.

Takes a script or conversation outline and produces a finished audio file with distinct voices playing different characters, ready for podcasts or video voiceovers.

Multi-slide carousel design for Instagram, LinkedIn, and Twitter/X with layout rules and hooks. Covers slide structure, text hierarchy, swipe psychology, and platform-specific specs. Use for: carousel posts, Instagram carousels, LinkedIn carousels, slide posts, educational content. Triggers: carousel, instagram carousel, linkedin carousel, slide post, carousel design, swipe post, multi-image post, carousel template, educational carousel, carousel content, instagram slides, linkedin slides

Chat UI building blocks for React/Next.js from ui.inference.sh. Components: container, messages, input, typing indicators, avatars. Capabilities: chat interfaces, message lists, input handling, streaming. Use for: building custom chat UIs, messaging interfaces, AI assistants. Triggers: chat ui, chat component, message list, chat input, shadcn chat, react chat, chat interface, messaging ui, conversation ui, chat building blocks

Walks through creating an app config, setting GPU/VRAM, wiring secrets, and pushing to inference.sh—handles both languages and explains resource trade-offs in plain terms.

Walks through logo types (wordmark, icon, combo), AI prompting techniques that avoid common pitfalls, and testing for legibility at favicon size—then iterates based on your feedback.

Write a brief and get photorealistic images, product shots, or concept art. Edit, inpaint, or batch-generate variations without leaving the chat.

Turns a raw commit log or feature list into a changelog that emphasizes what changed for users, not for engineers. Includes smart categorization, plain language, and distribution advice.

Creates a multi-dimensional persona with demographics, jobs-to-be-done, psychographics, and journey map. Includes anti-personas and ties each element to real market data, not guessing.

Creates marketing visuals, product mockups, or custom illustrations from a text prompt. Can adapt a style you upload or apply preset looks like "minimalist tech" or "warm editorial."

Generates genre-specific cover concepts with type hierarchy, color palettes, and AI imagery — then tests them at thumbnail size and iterates based on your feedback.

Upscales low-res, blurry, or compressed images using AI models trained on millions of photos. Works on screenshots, old photos, and AI-generated art.

Best practices and techniques for writing effective AI video generation prompts. Covers: Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora prompting strategies. Learn: shot types, camera movements, lighting, pacing, style keywords, negative prompts. Use for: improving video quality, getting consistent results, professional video prompts. Triggers: video prompt, how to prompt video, veo prompts, video generation tips, better ai video, video prompt engineering, video prompt guide, video prompt template, ai video tips, video prompt best practices, video prompt examples, cinematography prompts

Takes a long-form idea and breaks it into a tight Twitter thread with a hook that stops the scroll, numbered beats, and a call-to-action that lands.

Declarative UI widgets from JSON for React/Next.js from ui.inference.sh. Render rich interactive UIs from structured agent responses. Capabilities: forms, buttons, cards, layouts, inputs, selects, checkboxes. Use for: agent-generated UIs, dynamic forms, data display, interactive cards. Triggers: widgets, declarative ui, json ui, widget renderer, agent widgets, dynamic ui, form widgets, card widgets, shadcn widgets, structured output ui

Converts text into audio with 100+ natural voices across languages, emotional tone control, and accent options. Supports long-form narration, character voices, and real-time synthesis via CLI.

Drop-in React components that display agent tool calls as they run—pending, in progress, awaiting approval, completed. Handles status, progress bars, and approval flows out of the box.

Structures a post for developer readers: hooks with real problems, runnable code samples, clear section breaks, and the depth engineers expect without the sales talk.

Creates polished product shots, lifestyle scenes, and mockups for e-commerce—studio lighting, multiple angles, and packaging included. Ready to upload to Shopify or Amazon.

Researches what Google ranks for your target keyword, analyzes the top results' structure and tone, then outputs a brief with heading levels, word count targets, and internal links to include.

Converts a written scene or shot description into a high-quality video using Google Veo's latest models. Choose between quality and speed depending on your deadline.

Teaches chain-of-thought, few-shot examples, and system-prompt patterns that work across Claude, GPT-4, and image models. Includes templates for complex tasks and optimization techniques.

Converts text into studio-quality speech in 32 languages with 22+ realistic voices. Pick a voice, tune tone and pacing, get an MP3 ready to drop into your video or podcast.

Generate and edit images with Alibaba Qwen-Image-2.0 models via inference.sh CLI. Models: Qwen-Image-2.0 (fast), Qwen-Image-2.0-Pro (professional text rendering). Capabilities: text-to-image, multi-image editing, complex text rendering. Triggers: qwen image, qwen-image, alibaba image, dashscope image, qwen image 2, qwen image pro

Takes customer data, metrics, and quotes, then structures them using STAR framework with visualized results and distribution-ready formats for sales and marketing teams.

Describe a sound you need — "door slamming in an empty hallway" — and get a royalty-free audio file ready to drop into your video, game, or podcast.

Describe a mood, genre, and instruments—get original music up to 10 minutes long, ready for videos, podcasts, or games. Fully licensed for commercial use.

Builds a multi-step pipeline: generate image with FLUX → animate with Veo → add voiceover with Kokoro → mix in music → output polished MP4 or social clip. No manual handoff between steps.

Writes a script, generates visuals (Veo, Flux, Runway), and adds voiceover narration to produce a polished product demo, explainer, or social ad ready for Facebook, YouTube, or TikTok.

Generates platform-native posts — TikTok scripts with voiceover, Instagram captions with hashtags, YouTube thumbnails — all anchored to one core message or campaign angle.

Uploads a video or audio file and generates dubbed versions in 29 languages with the original speaker's voice preserved. Detects who's speaking automatically.

Convert text to natural speech with Inworld TTS, ElevenLabs, DIA TTS, Kokoro, Chatterbox, and more via inference.sh CLI. Models: Inworld TTS-2 (100+ languages, emotion steering), Inworld TTS 1.5 (ultra-low latency), ElevenLabs (premium, 22+ voices, 32 languages), DIA TTS (conversational), Kokoro TTS, Chatterbox, Higgs Audio, VibeVoice (podcasts). Capabilities: text-to-speech, voice cloning, multi-speaker dialogue, podcast generation, expressive speech, emotion/delivery steering, character voices. Use for: voiceovers, audiobooks, podcasts, accessibility, video narration, IVR, voice assistants, gaming characters, avatar audio. Triggers: text to speech, tts, voice generation, ai voice, speech synthesis, voice over, generate speech, ai narrator, voice cloning, text to audio, elevenlabs, eleven labs, voice ai, ai voiceover, speech generator, natural voice, inworld, inworld tts, character voice, game voice, npc voice