@101-skills

p-video-avatar animates portrait images into talking head videos via inference.sh cli, supporting 16 voices across 10 languages with optional tts or custom audio input. offers 720p and 1080p output with cost-effective pricing and reproducible generation via seed control.

app-store-screenshots provides platform-specific dimensions, gallery ordering heuristics, and caption guidelines for ios and android app store listings. covers device mockup generation via inference.sh cli but lacks validation and rollback procedures.

remotion-render compiles react/tsx video code into mp4 files via inference.sh, supporting remotion animation primitives. includes working examples and python sdk bindings but lacks error handling and failure mode documentation.

character-design-sheet provides practical techniques for maintaining visual consistency in ai-generated character imagery through detailed prompt anchors, reference sheets, and optional lora training. covers turnaround views, expression sheets, color palettes, and common failure modes with mitigation strategies.

gpt-image wraps openai's gpt-image-2 model for text-to-image generation, image editing, and mask-based inpainting via belt cli. supports batch generation up to 10 images in multiple formats and resolutions.

agent-tools exposes a catalog of 250+ cloud-hosted AI models via CLI, covering image generation, video, LLMs, search, and social automation. lacks decision logic and error handling for production use.

product-hunt-launch provides a partial workflow for generating gallery assets via inference.sh, starting with hero image generation. lacks launch tactics, timing strategy, and submission procedures outlined in description.

agent-browser wraps playwright for web automation via inference.sh, exposing element refs and screenshot capture. covers basic navigation and interaction but lacks depth on error handling and recovery patterns.

infsh-cli wraps 250+ inference.sh apps (image generation, video, llms, search, twitter) behind a belt command-line interface with local file upload support and task polling, but lacks actionable decision logic and failure handling for production use.

web-search integrates tavily and exa search via belt cli for querying and extracting web content, but lacks sufficient documentation depth and failure mode guidance for production use.

product-photography generates studio-style product images via the belt CLI and bytedance seedream model. covers packshot fundamentals through prompt engineering but lacks procedural depth and failure handling.

twitter-automation wraps x api operations (post, like, engage) through belt cli but lacks procedural depth, error handling, and realistic workflow examples beyond a single tweet posting command.

seedance wraps bytedance's video generation model via a cli tool, supporting text-to-video with optional synchronized audio output through inference.sh.

ai-image-generation wraps inference.sh cli to invoke 50+ image models including flux and gpt variants, but lacks structured intent definition, decision logic, and failure handling.

ai-video-generation wraps inference.sh cli to invoke 40+ video models including veo and seedance variants, with minimal procedural guidance and no error handling documentation.

storyboard-creation wraps inference.sh CLI to generate storyboard panels via AI image models, but lacks shot vocabulary, continuity rules, panel layout guidance, and editorial workflow that the description promises.

Generate images with Pruna P-Image models via inference.sh CLI. Models: P-Image, P-Image-LoRA, P-Image-Edit, P-Image-Edit-LoRA. Capabilities: text-to-image,…

Generate videos with Pruna P-Video and WAN models via inference.sh CLI. Models: P-Video, WAN-T2V, WAN-I2V. Capabilities: text-to-video, image-to-video, audio…

Generate and edit videos with Alibaba HappyHorse 1.0 models via inference.sh CLI. Models: HappyHorse T2V, I2V, R2V, Video Edit. Capabilities: text-to-video,…

Structured competitive analysis with feature matrices, SWOT, positioning maps, and UX review. Covers research frameworks, pricing comparison, review mining,…

Still-to-video conversion guide: model selection, motion prompting, and camera movement. Covers Wan 2.5 i2v, Seedance, Fabric, Grok Video with when to use…

Video ad creation with exact platform-specific specs for TikTok, Instagram, YouTube, Facebook, LinkedIn. Covers dimensions, duration limits, AIDA framework,…

YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression…

Landing page conversion optimization with layout rules, hero section design, and CTA psychology. Covers above-the-fold formula, social proof placement, mobile…

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

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