← ClaudeAtlas

handdrawn-schematiclisted

Generate a hand-drawn, whiteboard-sketch schematic that explains a concept, pipeline, architecture, algorithm, or mechanism at a glance, on a pure white background. Composes a friendly hand-lettered infographic prompt (wavy marker strokes, numbered panels flowing left to right, chunky chalk arrows, hand-written notes beside shapes) and by default renders it to a PNG via the bundled codex image_generation tool (ChatGPT OAuth); falls back to emitting the copy-paste prompt when codex is unavailable. Use when the user wants a hand-drawn / hand-written / whiteboard-style schematic, a sketch diagram that shows a schema, a friendly explainer figure, a doodle-style method overview, or 손그림/화이트보드 스타일 도식/개념도. For matplotlib data plots use scienceplot-py or xkcd-py; for a multi-style (editorial, blueprint, neon, poster) prompt-only composer use wide-slide-illustrator; for the paper-review method+results pair use journal-club-review.
Axect/skills · ★ 3 · AI & Automation · score 76
Install: claude install-skill Axect/skills
# Hand-Drawn Schematic Turn any schema (a concept, pipeline, architecture, algorithm, or mechanism) into a single friendly hand-drawn whiteboard illustration on a **pure white background**: wavy marker strokes, numbered panels flowing left to right, chunky chalk-style arrows, and short hand-written notes drawn beside the shapes. Every label, number, and equation is lettered by the same hand into the one drawing, so it reads like a research postdoc's explainer sketch for a small-group talk. By default this skill **renders a PNG** with the bundled `codex` image_generation tool (ChatGPT OAuth, no API key). When codex is not available it falls back to emitting the finished prompt so the user can paste it into any image generator. ## When to use - "Draw a hand-drawn schematic of how X works" - "Make a whiteboard-sketch figure explaining this pipeline / architecture" - "Sketch a doodle-style diagram of this algorithm" - "이 개념/구조 손그림 도식으로 그려줘" / "화이트보드 스타일 개념도 만들어줘" Do NOT use for: - Real data plots (matplotlib, seaborn, plotly) → `scienceplot-py` (publication `science`+`nature` style) or `xkcd-py` (sketch-style matplotlib from data). - A multi-style prompt-only composer across six looks (Editorial Magazine, Engineering Blueprint, Swiss Minimalist, Dark Tech/Neon, Scientific Poster) → `wide-slide-illustrator`. - The paired method + results infographics inside a paper walkthrough → `journal-club-review` (this skill is the reusable single-figure generator extracted fro