@magentosh

youtube-thumbnail-design covers dimensions, safe zones, color contrast rules, text placement, face psychology, and ai-driven generation via belt cli. includes 120px mobile preview test and content-specific prompt patterns.

app-store-screenshots covers platform-specific dimension requirements, gallery ordering strategy, and caption guidelines for ios and android. includes device mockup generation via inference.sh cli and preview video structure templates.

video-ad-specs documents platform-specific dimensions, duration limits, and safe zones for tiktok, instagram, youtube, facebook, and linkedin. includes aida framework, hook techniques, and bash examples using inference.sh cli, but lacks decision logic and failure modes.

character-design-sheet provides practical workflows for maintaining visual consistency in ai-generated character imagery using detailed prompt anchors, reference sheets (turnaround, expression, outfit, color), and lora training techniques.

remotion-render compiles react/tsx component code into mp4 videos via inference.sh cli, supporting animation primitives like useCurrentFrame, spring, and Sequence. accepts tsx string, renders to file.

competitor-teardown outlines research via external search and screenshot tooling, but lacks decision logic, output schema definition, and structured analysis synthesis steps to deliver actionable competitive matrices or positioning maps as advertised.

image-to-video provides a quick-start guide for converting still images to video using the belt CLI, but omits model comparison, motion prompting strategies, and decision logic mentioned in the description.

product-hunt-launch provides a CLI workflow for generating gallery images and optimizing launch assets via inference.sh, but lacks decision logic, timing strategy, and launch-day tactics described in the slug.

agent-browser wraps playwright for web automation via inference.sh, exposing element interaction through @e refs and screenshot/video capture. incomplete documentation leaves implementation details and capability boundaries unclear.

twitter-automation provides basic cli integration for posting to x/twitter via inference.sh, but lacks actionable procedures, trigger specification, and failure handling beyond a minimal quick-start example.

ai-video-generation wraps inference.sh cli to invoke 40+ video models including veo and seedance, but lacks procedural depth, error handling guidance, and clear intent boundaries.

landing-page-design wraps an image generation CLI for hero section visuals but lacks conversion optimization guidance, layout rules, mobile considerations, and cta psychology despite the description claiming these.

product-photography wraps a CLI call to an image generation API, providing one example prompt for studio packshots. lacks decision logic, failure modes, and actionable workflow guidance beyond copy-paste.

storyboard-creation wraps inference.sh CLI calls to generate individual image panels via flux-dev-lora. covers basic prompt templating and dimension specification but lacks shot vocabulary, continuity guidance, or multi-panel workflow.

Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh). Pre-installed: NumPy, Pandas, Matplotlib, requests,…

Run AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance,…

Run AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance,…

Web search and content extraction with Tavily and Exa via inference.sh CLI. Apps: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract.…

Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric,…

Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein…