nano-banana-pro
Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-06 00:14
Design & creation
22,134 results
openai-image-gen
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
amazon-a-plus-content
Plan and create Amazon A+ Content (Enhanced Brand Content). Design module layouts, write persuasive copy, plan comparison charts, and create image briefs that convert viewers into buyers.
amazon-brand-registry
Brand Registry Registration Guide — Eligibility Requirements, Application Process, Benefits, A+ Content Access, Brand Protection Tools
amazon-brand-tailored-promotions
Brand-targeted promotions — audience targeting, discount tiers, customer segmentation, repurchase incentives
amazon-enhanced-brand-content
Advanced A+ and Brand Story — module design, lifestyle imagery, comparison charts, mobile optimization
amazon-listing-images
Create a maximum conversion plan for Amazon product listing images. Following Amazon's image requirements and best practices, create a shot list, infographic layouts, lifestyle scene briefs, and an A/B testing plan.
amazon-product-photography
Plan Amazon product photography for maximum conversion. Shot list, lighting setup, infographic briefs, lifestyle scene planning, and image optimization that meets Amazon requirements.
amazon-storefront-design
Amazon Store building — page layout, brand story, shoppable images, traffic driving, conversion optimization
seedance-storyboard-generator
Professional AI video script and storyboard generator for the Seedance 2.0 platform. When the user requests: (1) convert an article/story into a video script, (2) generate Seedance 2.0 storyboard prompts, (3) plan a multi-episode AI video series, (4) for Nana Banana…
geometry-math-proof-remotion
Create math proof/geometry animation videos with Remotion: dark background with high saturation + precise SVG geometry + step-by-step formula reveal + subtitle-driven timeline, in 3Blue1Brown/Khan style. When the user wants to turn a math proof document (Pythagorean theorem, Euler's formula, integrals...), geometric derivation, algebraic identity, or algorithm visualization into a video with a precise geometric style, you must use this...
image-prompt-studio
Structured JSON prompt generation and modification (AI drawing workflow). When the user needs to generate a complete structured JSON drawing prompt from a one-sentence description, make precise minimal modifications to an existing JSON prompt, reverse-engineer a prompt from a reference image, create images in styles such as anime character art, or connect prompts to Nano Banana / GPT-Image… via apiz-cli
context-engineering
Design, audit, and verify how decision-relevant project information reaches an agent through the actual runtime. Use when an agent misses a governing boundary,…
skill-engineering
Design, rewrite, review, and test agent skills that improve a repeated agent action or judgment. Use when creating a skill, rewriting a SKILL.md, improving a…
visual-design
Design, redesign, or review real interfaces, documents, illustrations, and related visual systems from their content, audience, intended action, and existing…
design-forge
Use counterexamples and ablation to compare and judge the necessity of a mechanism, the boundaries of responsibility, and complete substitution relationships, and converge designs that deviate from the goal due to exceptions, patches, and local arrangements. Used for mechanism trade-offs, design forging and rework; general architecture design, local safeguard review, residual cleanup, or mere text streamlining each have their corresponding methods.
design-steward
Examine design and implementation through the trade-off tendencies of a long-term maintainer, judging what is worth keeping, simplifying, relocating, or discarding. Used for design judgment, complexity trade-offs, and overall burden assessment in divide-and-conquer review; does not replace correctness checks, nor does it automatically authorize cleanup or redesign.
interface-design
Design, refine, or critique product interfaces and interactions, judging visual craft and whether each screen, element, and flow serves a real task. Use for UI…
ui-improvement
Continuously improve the UI of multiple pages, component usage, and states in batches; diagnose problems from the task flow, control and page selection, foundational order, overall style, and local composition, form effective relationships through complete trial work, then propagate according to consumer differences and re-verify. Used for tasks that combine interaction design, aesthetic exploration, and scanning workload; a single local polish does not require the full process, and code contract review uses the project review method.
visual-design
Design, redesign, or review real interfaces, documents, illustrations, and related visual systems from their content, audience, intended action, and existing…
light-ui-ux
Next-generation full-stack UI/UX design & engineering system powered by a 59,000-record local SQLite FTS5 arsenal (`assets/light-arsenal.db`). Use whenever…
light-figure-drawing
Professional plotting and figure composition from the perspective of a top-conference expert. Use when the user needs to actually draw out a planned figure. Depending on the case, use Python (matplotlib/seaborn/plotly/altair), R (ggplot2), MATLAB, Visio, Origin, LaTeX/TikZ, Illustrator, PowerPoint…
light-system-design
Backend system design and database capabilities. Use when the task involves system architecture, database design, interface design, permissions/logging/exceptions/performance/deployment. Design ER diagrams, data table structures, interface documents, user permissions, data flow, module division, API specifications, database indexes, security policies, and deployment plans; especially suitable for research systems, management systems, data analysis platforms, visualization platforms, competition works, and software copyright projects.