Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Creates text and media posts, likes and retweets content, sends direct messages, follows users, and retrieves profiles. Supports social content scheduling, engagement automation, and audience growth workflows.
Supports web search, content extraction, and direct answers using Tavily and Exa apps. Applies to research, fact-checking, content aggregation, RAG pipelines, and agent workflows.
Covers iOS and Android screenshot dimensions, gallery ordering, device mockups, and preview videos. Supports app store optimization and the visual presentation of store listings.
Covers turnaround views, expression sheets, color palettes, and techniques for visual consistency. Applies to character design for games, illustrations, animation, comics, and visual novels.
Uses structured research frameworks, feature matrices, positioning maps, review mining, and visual deliverables. Supports market research, product strategy, investor decks, competitive intelligence, and sales enablement.
Uses OpenAI GPT-Image-2 through the inference.sh CLI for image generation and editing. Supports inpainting, mask-based edits, multiple image references, and batch generation for product mockups, concept art, marketing visuals, and photo manipulation.
Uses Alibaba HappyHorse 1.0 through inference.sh for text-to-video, image-to-video, reference-to-video, and natural-language video editing. Supports character preservation and videos up to 15 seconds at 720p or 1080p for product demos and social content.
Explains how to animate still images using Wan 2.5, Seedance, Fabric, and Grok Video. Covers choosing a model, prompting motion, and directing camera movement for photo animations and product videos.
Covers above-the-fold layout, social proof placement, mobile design, F-pattern reading, and CTA psychology. Supports startup, product, and SaaS marketing pages and conversion optimization.
Uses Pruna P-Image, P-Image-LoRA, P-Image-Edit, and P-Image-Edit-LoRA through inference.sh. Supports text-to-image generation, image editing, LoRA styles, and multi-image compositing with an emphasis on fast inference.
Uses Pruna P-Video, WAN-T2V, and WAN-I2V through the inference.sh CLI. Supports text-to-video and image-to-video generation, audio, and 720p or 1080p output with an emphasis on fast inference.
Creates talking head videos from portraits using Pruna P-Video-Avatar through inference.sh. Supports text or audio input, built-in TTS, 30 voices in 10 languages, dynamic backgrounds, full-body control, and 720p or 1080p output for presenters, demos, education, and marketing.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name