101-skills

Small, cluttered thumbnails lose attention in crowded YouTube feeds. This skill provides practical design rules and image prompts for clear, mobile-ready concepts.

Current information is difficult to gather and normalize across sources. This skill uses Tavily and Exa to search, answer questions, and extract web content.

Video ad requirements vary by platform, making creative adaptation slow and error-prone. This skill provides specifications, story structures, and generation workflows for efficient production.

Managing Twitter/X publishing and engagement can require repetitive manual work. This skill provides belt CLI workflows for posts, media, likes, reposts, messages, follows, and lookups.

Turning a script into coherent shots requires precise framing, continuity, and annotation. This skill guides shot planning and optional AI panel generation.

Turning React animation code into shareable video requires a configured rendering pipeline. This skill submits Remotion TSX to inference.sh and returns rendered video output.

Complex Python tasks often require libraries and an isolated runtime. This skill submits code to inference.sh and returns console output or generated files.

Product teams need consistent images for listings and campaigns. This skill provides practical prompts, shot guidance, and remote generation workflows for polished product photography.

Visitors leave when a landing page lacks clear value, trust, or direction. This skill provides practical rules for persuasive, responsive, conversion-focused page design.

Product Hunt launches require coordinated listing content, visuals, timing, and engagement. This skill provides specifications, templates, research commands, and a launch-day playbook.

Cloud AI services often require separate APIs and workflows. This skill guides Claude, Codex, and Claude Code through inference.sh app discovery and execution.

Choosing a video model and motion prompt for a still image can be difficult. This skill provides practical models, prompts, durations, and workflows.

Competitive research often becomes scattered and difficult to compare. This skill organizes evidence into feature, pricing, SWOT, review, and positioning deliverables.

AI image generators often change a character's face, colors, clothing, and proportions between images. This skill provides reference-sheet, description-anchor, palette, and LoRA workflows for more consistent results.

Store listings fail when screenshots use weak ordering, unreadable captions, or incorrect dimensions. This skill provides platform specifications, gallery strategy, generation prompts, and video guidance.

Choosing and operating video generation models requires many separate workflows. This skill provides direct belt CLI guidance for generation, animation, editing, audio, and finishing tasks.

Choosing and invoking image models individually slows creative work. This skill provides one belt CLI workflow for generation, editing, upscaling, and image stitching.

Avatar video production often requires separate speech, animation, and lip-sync tools. This skill organizes inference.sh models into reusable presenter, dubbing, and UGC workflows.

Manual browser tasks are slow and difficult to repeat. This skill provides session-based commands for consistent navigation, interaction, capture, and verification.

Managing separate AI APIs and workflows slows production. This skill guides Claude, Codex, and Claude Code through inference.sh discovery, execution, uploads, and task tracking.