image-annotate
Mark up an existing image with shapes, arrows, text, numbered steps, highlights, blur, or solid redaction. Use this skill whenever the user wants to annotate a…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Design & creation
22,044 results
rec
Record a web or Electron-renderer flow as an annotated video with playwright-cli, then extract frames to confirm how it actually looks. Use when the user…
edgespeak-transcribe
Transcribe audio/video on-device via EdgeSpeak into text, JSON, or SRT, with optional word-level timing, anonymous speaker diarization (who said what), and…
legal-ai-model-router-stephane-boghossian
Routes any legal task to the right LLM, like OpenRouter but for legal work and grounded in benchmarks instead of brand loyalty. Built from mid-2026 legal evals…
carl-motion
29 motion-graphics styles (paper collage, synthwave, ink wash, woodcut, point cloud, claymation, risograph, glassmorphism, blueprint, pixel game, particles,…
seedance-20
This skill should be used when creating, improving, or troubleshooting Seedance 2.0 video on any surface — Dreamina, Jimeng, CapCut, Doubao, Volcengine/Ark,…
edu-chem-tutorial
Turn a chemistry course (not a single reaction) into an interactive teaching course page: step-by-step knowledge point explanations + Canvas 2D scene animation + sidebar knowledge point panel + info cards + player controls. Suitable for complex explanatory chemistry courses, such as redox balancing, metal activity, periodic law of elements, ion coexistence, rate equilibrium, etc. Canvas 2D rendering (no Three.js), data-driven generation (similar to...
story-handdrawn-video
Use Agnes Video V2.0 pure text-to-video + Remotion to produce 9:16 vertical short videos. Two styles:`crayon`(Q-version hand-drawn crayon style fairy tales/life, MaShanZheng brush Chinese subtitles) and `textbook`(Oxford textbook style English teaching cards, Agnes narrative illustration video +…
geometry-math-proof-remotion
Create math proof/geometry animation videos with Remotion: dark background with high saturation + precise SVG geometry + formulas revealed step by step + subtitle-driven timeline, in 3Blue1Brown/Khan style. When the user wants to turn math proof documents (Pythagorean theorem, Euler's formula, integrals...), geometric derivations, algebraic identities, or algorithm visualizations into precise geometric-style videos, you must use this...
talking-head-remotion
Build reusable talking-head video projects with Remotion: supports talking-head audio/video, a circular PIP in the bottom-right, synchronized subtitles at the bottom, a chapter progress bar at the top, a modern Studio theme, SFX/BGM planning, and a runnable React composition. When the user wants to create or modify a talking-head video project, migrate an existing HyperFrames talking-head template to Remotion, set up…
default-resource-recommendations
Recommended default chart/icon/font/animation resources; consult the corresponding documents in references as needed.
design-bid-proposals
By default, generate 3 design pitch directions that can be directly implemented; if the user explicitly requests 2, 5, or another number, that number must be generated as requested. This skill is only responsible for pitch rules, case-splitting strategy, and prompt constraints; it does not provide standalone scripts. During actual execution, follow the existing Gemini CLI approach: first write the prompt file, then call Gemini sequentially to complete the planning round, individual proposal rounds, and the summary round.
gemini-cli-uiux
Use Gemini CLI to execute UI/UX design and implementation tasks. Suitable for scenarios that require invoking Gemini CLI, reading long context based on local document paths, and writing results directly to project files.
pencil-import-workflow
Use Pencil MCP to read the currently open .pen file and Frame (no upload required), let the user confirm the import scope and output structure, then generate the Axhub Make prototype directory (spec.md + index.tsx) and perform acceptance.
screenshot-page-workflow
Process specification for visual analysis and prototype restoration based on web page or App screenshots; used when screenshot recognition, asset extraction (functional/interaction/business analysis), page code generation, and acceptance are needed.
ui-ux-pro-max
UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter,…
shiwu-huajing
Fifteen Realms of Painting — a craft book for making MG animation short videos with code. It teaches you (the AI) to write original short films in a certain motion design style based on the user's theme: flat vector, single-stroke line art, isometric 2.5D, 3D texture, frame-by-frame hand-drawn, collage, liquid, morphing, Bauhaus, retro neon/VHS, frosted glass, variety-show display type, educational infographic stickers, pixel art, cyber…
female-outfit-director
Generate linked image prompts and video scripts for "same character multiple outfit collage first frame + beat-synced outfit-change short video". Use when the user requests realistic character outfit collages, five looks, floating character stickers, hanfu / ancient-style / modern fashion outfit changes, click-to-change outfits, beat-synced transformations, extending a video based on an uploaded reference image, or wants outfit/transformation parameters recommended before generation.…
lov-professional-portrait
Turn a single-person photo into a polished professional portrait while preserving the person's identity. Use restrained skin retouching, exposure cleanup,…
lov-visual-clone
Analyze a reference design image and extract visual DNA — layout, style, color palette, texture, typography, copy tone, spacing, etc. — into a structured,…
tgravity-work-video-indexer
TGravity Work video material index and clip table Skill. Used for video analysis skills, /tgravity-video, /tgravity-video-init, /tgravity-video-check, /tgravity-video-run, /tgravity-video-validate, help me analyze video materials, help me make a material table, …
codex-image
Use this skill when the user wants to generate images, edit images, or create images with gpt-image / GPT Image / OpenAI image models. Triggers on requests…
cx-design
CX workflow — technical design and execution contract. Triggered when the user mentions "technical design", "Design Doc", "API design", "interface design", "architecture design", "system design". Reads the PRD to generate a design document, saved locally to 开发文档/CX工作流/功能/{feature_title}/设计.md. This step only serves medium-to-large features…
ui-ux-pro-max
UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter,…