@halt-catch-fire

ai-avatar-video generates talking head videos from portraits using inference.sh CLI, with p-video-avatar as the recommended option for speed and cost. supports four model variants, built-in tts, and full workflows for ugc, localization, and dubbing.

youtube-thumbnail-design covers dimensions, contrast rules, safe zones, and text placement for high-ctr thumbnails. provides prompt templates for flux and seedream, psychological guidance on face expressions, and a 120px mobile legibility test.

p-video-avatar generates talking head videos from portrait images using inference.sh cli, supporting 10 languages, multiple voice options, and custom audio input with configurable resolution and behavior prompts.

remotion-render transpiles tsx component code to mp4 video via inference.sh cli. supports react hooks, remotion animation apis, and prop injection. outputs video url on completion.

happyhorse exposes alibaba's video generation and editing models (t2v, i2v, r2v, video edit) through belt cli with concrete examples for each model variant and parameter documentation, though lacks failure mode guidance and decision logic.

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 with configurable resolution and output formats.

infsh-cli wraps 250+ inference.sh cloud apps (image generation, video, llms, search, 3d, twitter) behind a single belt cli. installation and basic command patterns are documented, but lacks actionable skill procedures, error handling, and auth workflows.

product-hunt-launch provides a minimal cli-based workflow for generating product hunt gallery assets via inference.sh, but lacks strategic guidance on launch timing, tagline composition, maker comments, and day-of execution.

competitor-teardown provides a starting point for competitive analysis by combining web search (via tavily) and cli-based tool invocation. the coverage is incomplete and the procedure is partial, leaving significant implementation work for actual swot matrices, positioning maps, or ux review.

agent-tools wraps inference.sh CLI to invoke 250+ cloud-hosted ai models across image, video, llm, search, and social media categories. lacks actionable decision logic, error handling, and clear integration patterns for agent workflows.

agent-browser wraps playwright for web automation via inference.sh, supporting element interaction through @e refs and screenshots. lacks depth on failure modes and concrete procedure.

p-video wraps pruna's optimized video generation models (p-video, wan-t2v, wan-i2v) via inference.sh cli for text-to-video and image-to-video synthesis, but the skill definition is skeletal and lacks operational depth.

twitter-automation exposes x/ apps (post-tweet, post-like, etc) via belt CLI but lacks procedural depth, decision logic, and failure handling beyond raw command examples.

ai-image-generation wraps inference.sh cli to invoke 50+ image models including flux and gpt-image-2, with minimal documentation and no specified output contract or failure handling.

ai-video-generation wraps inference.sh CLI to invoke 40+ video models including Veo and Seedance 2.0, but lacks actionable procedural depth, error handling, and input validation guidance.

landing-page-design covers ai-generated visual assets for landing pages via inference.sh cli, but lacks substantive guidance on conversion optimization, layout principles, or cta strategy despite claiming it in the description.

product-photography wraps inference.sh CLI calls to bytedance/seedream-4-5 for ai-generated product shots. lacks procedural depth, edge case handling, and actionable guidance on lighting, composition, or output validation.

Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse…

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…

Automate Twitter/X with posting, engagement, and user management via inference.sh CLI. Apps: x/post-tweet, x/post-create (with media), x/post-like,…

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

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 ByteDance Seedance 2.0 via inference.sh CLI. Unified model for text-to-video, image-to-video, and reference-to-video with synchronized…

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,…

Character consistency across AI-generated images with reference sheets and LoRA techniques. Covers turnaround views, expression sheets, color palettes, and…

Film and video storyboarding with shot vocabulary, continuity rules, and panel layout. Covers shot types, camera angles, movement, 180-degree rule, and…

App Store and Google Play screenshot creation with exact platform specs. Covers iOS/Android dimensions, gallery ordering, device mockups, and preview videos.…

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

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