IMGLAB / SKILLS
Practical skills for making, evaluating and working with visual products.
An open-source collection of design skills for AI coding tools, built around a landing-page-design rule set that covers page planning, a full visual system, and the delivery details most generated pages skip.
A free open-source AI-agent skill that turns documents into browser-editable presentations: 12 visual themes, 1020 layouts, per-page control consoles, and one-click export to HTML, PDF and genuinely editable PPTX.
An open-source Agent Skill that helps you understand whatever is on screen visually, by compressing the current topic into the smallest, clearest structure. It reaches for pseudocode, call trees, component trees, file trees, Mermaid diagrams and diffs, and writes a single focused HTML file when a diagram is too dense for Mermaid. Five days of field use point to four jobs it does well, finding story angles, producing screenshot-ready infographics, untangling AI concepts like Agent, RAG and MCP, and mapping out an unfamiliar tool's workflow.
An open-source, MIT-licensed Codex Skill that plans and scripts beat-synced outfit-change videos for a single adult female character. It locks identity from a reference image, generates five-outfit collage keyframe prompts, and outputs a shot-by-shot video timeline with 12 swappable transition mechanisms like sticker fly-ins, sleeve wipes, spin handoffs and action beats.
An open-source Skill and prompt framework for GPT-Image 2 that generates candid real-life summer portraits of a Korean Instagram-style influencer. It runs on a skeleton of five slots, expression, outfit style, scene, moment and photography technique, backed by thick variable pools, so generation stays inside a defined boundary of randomness instead of being over-controlled into drawing conflicts.
An open-source Chinese portrait-photography skill that reads a set of reference images, extracts their shared visual DNA, and rewrites makeup, wardrobe, scene, lens, pose and lighting as prompts you can still edit.
An open-source Codex skill that turns a few portrait parameters into a directed, camera-ready prompt — 20 styles, 6 image tools, MIT licensed, 1.2k stars and climbing without any promotion.
No resources match these filters.
