vector-ai-toolkit

AI-powered logo generation with iterative design workflow. Generates logo variations using Nano Banana 2 (Gemini 3.1 Flash) via OpenRouter, then processes finalists with local tools for cropping, background removal, and SVG vectorization. Use when the user asks to create a logo, design a brand mark, generate logo concepts, or needs logo variations for a project. Triggers: 'create a logo', 'design a logo', 'logo for', 'brand mark', 'logo variations', 'generate logos'.

When the user wants to edit, review, or improve existing marketing copy. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' or 'copy sweep.' This skill provides a systematic approach to editing marketing copy through multiple focused passes.

When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user says "write copy for," "improve this copy," "rewrite this page," "marketing copy," "headline help," or "CTA copy." For email copy, see email-sequence. For popup copy, see popup-cro.

Agent-orchestrated research that takes input text and conducts parallel multi-agent investigation. Accepts research questions, briefs, or seed context. Spawns parallel agents for web research, local project analysis, and specialized investigation. Produces citation-backed markdown reports. Triggers: "deep research", "research X", "comprehensive analysis", "investigate", "compare X vs Y", "analyze trends". Do NOT use for simple lookups (1-2 searches), debugging, or document analysis without web research.

Generate Excalidraw diagrams from text descriptions. Use when creating flowcharts, mind maps, hierarchies, timelines, comparisons, relationship maps, matrices, or freeform diagrams. Outputs Obsidian-compatible .excalidraw.md files.

Discover and install agent skills from the skills.sh ecosystem and local installed skills. Use when the user asks 'how do I do X', 'find a skill for X', 'is there a skill for...', 'can you do X' (where X is a specialized capability), or expresses interest in extending agent capabilities. Also use when the user wants to search for tools, workflows, or domain-specific help that might exist as an installable skill.

Generate and edit images using AI models including Nano Banana 2 (Gemini 3.1 Flash), FLUX.2 Pro, and FLUX.2 Flex via OpenRouter. Covers text-to-image generation, image editing, batch variations, and post-processing. Use when the user asks to generate an image, create artwork, make a picture, edit a photo, create illustrations, generate variations, make a banner, create social media graphics, or any visual content creation task. Triggers: 'generate an image', 'create a picture', 'make an illustration', 'edit this image', 'image variations', 'create artwork', 'banner', 'thumbnail', 'social media graphic', 'hero image', 'product shot'. For logo-specific work, prefer the logo-creator skill.

When the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing strategies,' 'marketing tactics,' 'ways to promote,' or 'ideas to grow.' This skill provides 139 proven marketing approaches organized by category.

When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' or 'consumer behavior.' This skill provides 70+ mental models organized for marketing application.

Create and edit HTML presentations and visual documents using the Vector Labs design system. Two modes: (1) Slide decks — horizontal, navigable presentations with the slide engine (pitch decks, proposals, workshops). (2) Visual documents — vertical, scrollable HTML pages (one-pagers, visual reports, briefs, reference docs). Use when the user asks to create a presentation, slide deck, pitch deck, slides, visual document, one-pager, document visual, or wants to edit existing ones. Triggers: 'apresentação', 'presentation', 'slide deck', 'pitch deck', 'slides', 'documento visual', 'one-pager', 'visual document', 'criar apresentação', 'fazer slides', 'documento bonito', 'relatório visual'.

When the user wants to create or update their product marketing context document. Also use when the user mentions 'product context,' 'marketing context,' 'set up context,' 'positioning,' or wants to avoid repeating foundational information across marketing tasks. Supports both single-product repos (`.claude/product-marketing-context.md`) and multi-product repos (`.claude/product-marketing-context/[slug].md`). Other marketing skills reference these files.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Comprehensive Three.js development guide covering scene setup, geometry, materials, lighting, textures, animation, shaders, interaction, post-processing, and asset loading. Use when the user is building or modifying any Three.js project, creating 3D scenes, working with WebGL rendering, implementing 3D animations, writing GLSL shaders, setting up camera controls, loading 3D models (GLTF/OBJ/FBX), or doing any Three.js-related development. Also use when the user mentions 'three.js', 'threejs', 'WebGL', '3D scene', 'shader', 'GLTF', or 'post-processing effects'.

Deploy projects to Vercel from the authenticated local CLI. Handles static sites, Next.js, Node.js, and any Vercel-supported framework. Resolves non-interactive CLI issues (scope, project linking) automatically. Use when the user asks to 'deploy to Vercel', 'put this on Vercel', 'subir na Vercel', 'deploy this', 'host this page', 'deploy em produção', or any request to deploy a project to Vercel. Also use when a deploy to Vercel fails due to scope or linking errors.

Select fonts, create type pairings, and choose icon libraries for web apps. Provides a decision workflow for typography choices based on app type, brand tone, and technical constraints. Covers free fonts (Google Fonts, Fontshare), type scales, font loading, and icon library selection. Use when starting a new webapp, choosing fonts, picking a typeface, creating font pairings, setting up a type scale, selecting an icon library, or when the user asks about typography, fonts, icons for a web project. Triggers include 'choose fonts', 'font pairing', 'typography for', 'pick a typeface', 'type scale', 'icon library', 'which icons', 'which font', 'tipografia', 'fontes para'.