🎯Skills80
Generate AI images with 50+ models (FLUX, Gemini 3 Pro Image, Grok Imagine, Seedream, Reve) via the inference.sh CLI, covering text-to-image, inpainting, LoRA, image editing, and upscaling.
Generate AI videos (text-to-video, image-to-video, lipsync, upscaling) with 40+ models like Google Veo, Seedance, Wan, and Grok via the inference.sh CLI. Covers social videos, marketing clips, explainers, and AI avatars.
Umbrella skill for running 250+ AI apps through the inference.sh CLI — image and video generation, LLM calls, web search, 3D, and Twitter automation — from a single no-GPU-required install.
Install and authenticate the inference.sh (`infsh`) CLI so that agents can run any of 250+ cloud AI apps — image, video, LLM, search, 3D, and more — without needing a local GPU.
Run web search and content extraction through Tavily (Search Assistant, Extract) and Exa (Search, Answer, Extract) via the inference.sh CLI for research, RAG, and fact-checking workflows.
Execute arbitrary Python 3.10 code in a sandboxed inference.sh environment pre-loaded with NumPy, Pandas, Matplotlib, Playwright, MoviePy, Pillow, OpenCV, trimesh, and 100+ other libraries.
Render MP4 video from React/Remotion TSX component code via the inference.sh CLI with configurable resolution, FPS, duration, and codec — supports `useCurrentFrame`, `spring`, `interpolate`, `Sequence`, etc.
Automate Twitter/X through the inference.sh CLI — post tweets with media, like, retweet, delete, send DMs, follow users, and fetch posts/profiles via ready-made `x/*` apps.
Playwright-backed browser automation for AI agents via inference.sh, using an `@e` ref system to open pages, click, fill forms, screenshot, record video, and re-snapshot between navigations.
Design high-converting SaaS/product landing pages using an above-the-fold formula, hero section layout, CTA psychology, social proof placement, mobile rules, and F-pattern reading.
Convert still images into animated videos via inference.sh models (Wan 2.5 i2v, Pruna WAN-I2V, Seedance 1.5 Pro) with guidance on model selection, motion prompts, and camera movement.
Design high-CTR YouTube thumbnails at 1280×720 with AI image generation, covering safe zones, mobile-first 120px readability, face expression psychology, contrast, and A/B testing guidance.
Create film/video storyboards with AI image generation using proper shot vocabulary (ECU/CU/MS/MLS), camera angles, continuity and the 180-degree rule, plus a panel-stitching workflow.
Create commercial-grade product photography with AI (hero shots, studio packshots, lifestyle, e-commerce/Amazon listings) using inference.sh image models and prompt recipes for angle, lighting, and background.
Run a structured 7-layer competitor teardown — product, pricing, positioning, traction, reviews, content, and team — combining Tavily search and browser screenshots for market research and investor decks.
Platform-specific cheatsheet for producing video ads — dimensions, duration limits, safe zones, hook windows, and creative rules for TikTok, Instagram Reels, YouTube, Facebook, and LinkedIn.
Produce iOS App Store and Google Play screenshots with exact per-device dimensions, localization slots, gallery ordering, and device mockup prompts for ASO-focused store listings.
Guide for producing consistent characters across AI-generated images using reference sheets, turnaround views, expression sheets, color palettes, and FLUX LoRA training techniques.
Optimize Product Hunt launches — tagline limits, 1270×760 gallery images, description preview window, topic selection, maker comments, and launch-day tactics — with AI for visuals and research.
Part of the inference.sh skills collection providing access to 250+ AI models via CLI, including image generation, video generation, LLM calls, web search, and social media automation.
A social media content skill from the inference.sh collection, part of social guides covering LinkedIn, Twitter threads, and carousels using 250+ AI models through the inference.sh CLI.
Part of the inference.sh skills collection providing access to 250+ AI models via CLI, including image generation, video generation, LLM calls, web search, and social media automation.
Part of the inference.sh skills collection providing access to 250+ AI models via CLI, including image generation, video generation, LLM calls, web search, and social media automation.
A prompt engineering guide from the inference.sh skills collection, covering techniques for crafting effective prompts across 250+ AI models for image generation, video creation, and language tasks.
An SEO content brief guide from the inference.sh skills collection, leveraging AI models for search-optimized content as part of the writing and product guides accessible through the inference.sh CLI.
A logo design guide from the inference.sh skills collection, part of the design guides covering landing pages, thumbnails, and logos using AI image generation models via the inference.sh CLI.
A social media carousel guide from the inference.sh skills collection, part of the social guides covering LinkedIn, Twitter threads, and carousels using AI models through the inference.sh CLI.
Part of the inference.sh skills collection providing access to 250+ AI models via CLI, including image generation, video generation, LLM calls, web search, and social media automation.
A technical blog writing guide from the inference.sh skills collection, part of the writing guides covering blogs, case studies, and newsletters with AI models through the inference.sh CLI.
Part of the inference.sh skills collection providing access to 250+ AI models via CLI, including image generation, video generation, LLM calls, web search, and social media automation.
Part of the inference.sh skills collection providing access to 250+ AI models via CLI, including image generation, video generation, LLM calls, web search, and social media automation.
Full agent interface UI component from the inference.sh skills collection, providing a complete interface for interacting with 250+ AI models for image generation, video creation, LLM inference, and web search.
An inference.sh skill for working with large language models including Claude, Gemini, Kimi, and GLM through the inference.sh CLI, enabling AI agents to call LLMs via a unified interface.
Part of the inference.sh skills collection providing access to 250+ AI models via CLI, including image generation, video generation, LLM calls, web search, and social media automation.
Python SDK skill from the inference.sh collection, providing async support and streaming for building AI applications with 250+ models via the inference.sh CLI.
Part of the inference.sh skills collection providing access to 250+ AI models via CLI, including image generation, video generation, LLM calls, web search, and social media automation.
Part of the inference.sh skills collection providing access to 250+ AI models via CLI, including image generation, video generation, LLM calls, web search, and social media automation.
Part of the inference.sh skills collection providing access to 250+ AI models via CLI, including image generation, video generation, LLM calls, web search, and social media automation.
Part of the inference.sh skills collection providing access to 250+ AI models via CLI, including image generation, video generation, LLM calls, web search, and social media automation.
Part of the inference.sh skills collection providing access to 250+ AI models via CLI, including image generation, video generation, LLM calls, web search, and social media automation.
Image generation skill from the inference.sh collection focused on FLUX models, part of a suite of 50+ image models including Gemini and Reve accessible through the inference.sh CLI.
A case study writing guide from the inference.sh skills collection, part of the writing guides covering blogs, case studies, and newsletters with AI content creation through the inference.sh CLI.
An inference.sh skill that provides UI components for rendering tool call inputs and results in AI agent interfaces, supporting the inference.sh platform with 250+ AI models.
A marketing video skill from the inference.sh collection, part of the video guides covering storyboards, explainers, and ads using 40+ video generation models through the inference.sh CLI.
Create investor-ready pitch deck visuals via inference.sh CLI with a structured 12-slide framework covering problem, solution, market, traction, and team slides. Includes visual design rules, chart type guidance, and data presentation best practices.
Create talking head videos with AI avatars and lipsync via inference.sh CLI, using tools like OmniHuman and PixVerse. Covers portrait requirements, audio quality, and voiceover for spokesperson videos, course content, and presentations.
Part of the inference.sh skills collection providing access to 250+ AI models via CLI, including image generation, video generation, LLM calls, web search, and social media automation.
Part of the inference.sh skills collection providing access to 250+ AI models via CLI, including image generation, video generation, LLM calls, web search, and social media automation.
Generate images with Google Gemini 3.1 Flash Image Preview (Nano Banana 2) via the inference.sh CLI, supporting text-to-image, image editing, multi-image input (up to 14 images), and Google Search grounding.
Chat UI component from the inference.sh skills collection, providing reusable chat interface components for conversational experiences with 250+ AI models via the inference.sh CLI.
Transform any voice into a different voice while preserving speech content and emotion using ElevenLabs speech-to-speech models via inference.sh CLI. Supports 70+ languages with the multilingual model and English-optimized processing.
Premium text-to-speech with 22+ ElevenLabs voices via inference.sh CLI, offering three model tiers: Multilingual v2 (highest quality, 32 languages), Turbo v2.5 (balanced speed), and Flash v2.5 (ultra-fast). Features stability and style control for voiceovers, audiobooks, and video narration.
High-accuracy speech-to-text transcription using ElevenLabs Scribe models (v1/v2) via inference.sh CLI. Features 98%+ accuracy across 90+ languages with speaker diarization, audio event tagging, word-level timestamps, and forced alignment for subtitle generation.
Convert text to natural speech via inference.sh CLI using multiple TTS engines including ElevenLabs (22+ voices, 32 languages), DIA TTS for conversational speech, Kokoro TTS, Chatterbox, and more. Supports voice cloning, multi-speaker dialogue, and podcast generation.
An explainer video guide from the inference.sh skills collection, part of the video guides covering storyboards, explainers, and ads using 40+ video models through the inference.sh CLI.
Create AI-powered podcasts and audio content using text-to-speech tools like Kokoro TTS, DIA TTS, and Chatterbox via inference.sh CLI. Supports multi-voice conversations, background music, intro/outro, and full episode production.
Generate videos with Pruna P-Video and WAN models via inference.sh CLI, supporting text-to-video, image-to-video, and audio integration at 720p/1080p. Pruna optimizes models for faster inference without quality loss.
Generate images with Alibaba Qwen-Image-2.0-Pro via inference.sh CLI, featuring professional text rendering, fine-grained realism, and enhanced semantic adherence. Ideal for posters, banners, and text-heavy designs.
Transcribe audio to text via inference.sh CLI using ElevenLabs Scribe v2 (98%+ accuracy with diarization), Fast Whisper Large V3, and Whisper V3 Large. Supports multi-language transcription, timestamps, speaker diarization, and audio event tagging.
A video prompting guide from the inference.sh skills collection, covering prompt techniques for 40+ video generation models including Veo, Seedance, and Wan through the inference.sh CLI.
Remove background noise and isolate vocals from audio recordings using ElevenLabs via inference.sh CLI. Supports WAV and MP3 formats up to 500MB and 1 hour, useful for podcast cleanup, interview audio, and audio restoration.
JavaScript/TypeScript SDK skill from the inference.sh collection, providing streaming support, tool integration, and React components for building AI applications with 250+ models via the inference.sh CLI.
Create Open Graph and social sharing images via inference.sh CLI with platform-specific specs for Facebook, Twitter/X, and LinkedIn. Covers text placement, branding guidelines, OG meta tags, and dynamic image generation.
A product changelog guide from the inference.sh skills collection, part of the product guides covering competitor analysis, personas, and launches using AI models through the inference.sh CLI.
An inference.sh skill for building inference.sh apps. Part of a collection of 250+ AI agent skills providing access to image generation, video generation, LLM models, web search, and social media automation through the inference.sh CLI.
A LinkedIn content guide from the inference.sh skills collection, part of the social guides covering LinkedIn posts, Twitter threads, and carousel design using AI content generation through the inference.sh CLI.
Automatically dub audio and video into 29 languages using ElevenLabs via inference.sh CLI, with automatic speaker detection and voice-preserving translation. Ideal for content localization, video translation, and international distribution.
A customer persona guide from the inference.sh skills collection, part of the product guides covering competitor analysis, personas, and launches using AI models through the inference.sh CLI.
Generate and edit images with Alibaba Qwen-Image-2.0 models via inference.sh CLI, offering both a fast standard model and a Pro model with professional text rendering. Supports text-to-image generation, multi-image editing, and complex text rendering.
An inference.sh skill for discovering related skills. Part of a collection of 250+ AI agent skills providing access to image generation, video generation, LLM models, web search, and social media automation through the inference.sh CLI.
A Twitter thread creation guide from the inference.sh skills collection, part of the social guides covering LinkedIn, Twitter threads, and carousels with AI content generation through the inference.sh CLI.
Declarative UI widget renderer for React/Next.js that renders rich interactive interfaces from JSON via ui.inference.sh. Supports forms, buttons, cards, layouts, inputs, selects, and checkboxes for agent-generated UIs and dynamic forms.
An inference.sh skill for ElevenLabs sound effects generation. Part of a collection of 250+ AI agent skills providing access to image generation, video generation, LLM models, web search, and social media automation through the inference.sh CLI.
Create genre-appropriate book covers with AI image generation via inference.sh CLI. Covers fiction and non-fiction genre conventions, typography rules, sizing, thumbnail testing, and iteration workflows for self-publishing, ebook, and print covers.
An inference.sh skill for press release writing. Part of a collection of 250+ AI agent skills providing access to image generation, video generation, LLM models, web search, and social media automation through the inference.sh CLI.
An inference.sh skill for AI music generation via ElevenLabs. Part of a collection of 250+ AI agent skills that provide access to image generation, video generation, LLM models, web search, and social media automation through the inference.sh CLI.
An inference.sh skill for ElevenLabs dialogue generation. Part of a collection of 250+ AI agent skills providing access to image generation, video generation, LLM models, web search, and social media automation through the inference.sh CLI.
An inference.sh skill for newsletter curation. Part of a collection of 250+ AI agent skills providing access to image generation, video generation, LLM models, web search, and social media automation through the inference.sh CLI.
An inference.sh skill for AI image generation. Part of a collection of 250+ AI agent skills providing access to 50+ image models (FLUX, Gemini, Reve), 40+ video models, LLM models, web search, and social media automation through the inference.sh CLI.
Create realistic multi-speaker dialogue audio using Dia TTS and ElevenLabs via inference.sh CLI. Supports speaker tags for two-voice conversations with emotion control, pacing adjustments, and post-production for podcasts, audiobooks, and character dialogue.