SuperAPI AI DirectoryFind an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-03 00:11
21,826 results
Image generation / generate images / draw images — generate images with OpenAI gpt-image-2. Supports text-to-image, reference-image-to-image (img2img), and mask inpainting. When the user asks to draw with GPT, generate images with OpenAI, gpt-image-2, text+image-to-image, reference image generation, img2img, inpainting…
Generate visually striking PPT slides via OpenAI's gpt-image-2 -- use any style in styles/<id>.md or mimic a user-supplied .pptx template; outputs high-res…
Claim inventory tool for YouTube videos. Use when the user pastes a YouTube URL and asks "what claims does this video make", "list every claim", "show me the…
Artifact extraction tool for YouTube videos — pulls links, code snippets, named books, tools, and people mentioned. Use when the user pastes a YouTube URL and…
Deliberate product delight through micro-interactions, celebratory moments, playful copy, brand personality, and memorable but practical UX touches. Use…
Use when designing experiments, result tables, mock planning data, evaluation protocols, or results sections before real data are final
Use when creating flowcharts, architecture diagrams, or conceptual diagrams - generates prompts for image AI
Use to install and run NVIDIA Asset Harvester (Apache-2.0) to extract per-object 3D Gaussian Splat assets (`gaussians.ply`) from AV NCore V4 clips or masked…
Run TAO Data Services TMM unique-neighbor matching mining from embedding parquet files for object detection workflows. Use when an object detection workflow…
Rough-cut ready-made MP4, MOV, and MKV videos: compress pauses, identify misspoken restatements and discarded takes, and export a new video, edit plan, and audit report. Use when the user requests automatic rough cutting, compressing spoken pacing, or exporting an edit timeline. Not for Screen Studio native projects (leave that to screen-studio-editor), and does not generate subtitles (leave that to oil-subtitle).
Stand up a complete, ready-to-run computer-vision analytics stack on Intel hardware with one Docker Compose command — point it at your video sources and an…
Make a narrated demo or promo video of the project's live site or app — scripted browser takes, Gemini voice-over, captions, music bed, ffmpeg edit, shareable…
For a non-trivial pull request, write a self-contained HTML design doc under the temporary `.pr/` directory and link a visibility-appropriate preview in the PR…
Reviews a diagram or social card - Mermaid, DOT, SVG, or PNG - with lints (syntax, caps, contrast, overlap, tokens), a render, and an analyze-then-judge…
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with…
Manually invoked skill for reskinning Payload UI components. Requires Figma URL. Usage: /ui4
Configure container image registries including GitHub Container Registry (ghcr.io), Docker Hub, and Harbor with automated image scanning, tagging strategies,…
Create beautiful visual art in .png and .pdf documents using design philosophy. Use when the user asks to create a poster, piece of art, design, or other…
Document typesetting skill: resumes, one-pagers, white papers, letters, portfolios, and slide decks laid out on warm paper-like pages with serif type and…
Official animation skill from the Motion team (Motion, formerly Framer Motion, plus plain CSS animation): animation best practices for vanilla JS, React, Vue,…
OpenTofu infrastructure-as-code reference for HCL syntax, state management, module design, and provider configuration. Use when working with…
Critique an existing UI and return ranked, evidence-backed fixes. TRIGGER when: user explicitly asks for a design critique, broad UI review, or ranked design…
Use when someone needs word-level timestamps from audio — lyric alignment, cut-safe line boundaries, or caption source timing before burn-in with video-editing.
Use when Site DNA and all 12 brand interview answers are in hand and it's time to generate the final replication prompt. Phase 3 of SRIP — applies 11 synthesis…