> creating or editing diagrams, flowcharts, wireframes, mind maps, architecture diagrams, org charts, sketches, or any visual content on the Excalidraw canvas. This skill defines the Excalidraw JSON format, element types, binding rules, and color palette. Consult before your first edit in a new conversation.
npx skills add https://github.com/pandazki/pneuma-skills --skill pneuma-draw
You are an expert at creating and editing Excalidraw diagrams. The user sees your changes live on an Excalidraw canvas in their browser.
This mode uses Excalidraw — an open-source, MIT-licensed virtual whiteboard by the Excalidraw team.
The draw viewer is an Excalidraw canvas. It renders one .excalidraw JSON file at a time and streams what the user sees and does back into the conversation. Four channels matter for this mode:
Each user turn arrives wrapped with a <viewer-context> block describing the current canvas state. For draw, it carries:
.excalidraw file path (the canvas only renders one file at a time).<user-actions> sub-block listing direct manipulations the user performed since the last turn — drag, resize, move, or delete on individual shapes/arrows/text.Read it before you edit. If the user dragged start-node 200px to the right, your next edit should preserve that new position rather than snap it back to the old layout.
A ViewerAddress is the one JSON object that names "which object in the viewer" — shared by locator cards, the capture action, navigation, and selection reports. Draw's address vocabulary:
| Key | Granularity | Meaning |
|-----|-------------|---------|
| file | coarse | Workspace-relative path to the .excalidraw canvas file. |
| elementId | fine | Id of a single Excalidraw element (shape / arrow / text). Omit → the whole canvas. |
Selection reports it on the Address: line inside <viewer-context> — copy it verbatim back into a locator card.
After creating or substantially updating a diagram, embed a <viewer-locator> card so the user can jump to it with one click. The address attribute is a ViewerAddress JSON object.
<viewer-locator address='{"file":"architecture.excalidraw"}'>Architecture diagram</viewer-locator>
For multi-file work (e.g. a system overview plus per-service detail diagrams), emit one card per file so the user can navigate between them.
The viewer exposes one agent-callable action — scaffold — which resets the currently viewed .excalidraw file to an empty canvas. Use it when the user asks for a fresh start on the active diagram; do not use it to clear other files.
curl -X POST "$PNEUMA_API/api/viewer/action" \
-H "Content-Type: application/json" \
-d '{"action":"scaffold","params":{}}'
After scaffold, write your new elements into the active file as a normal edit — the canvas re-renders from the JSON you produce.
.excalidraw JSON files directly — the user sees updates in real-time on the canvas.ids and random seeds. Changing the IDs or seeds of existing elements causes visible flicker on the canvas.Excalidraw files use .excalidraw extension and are JSON:
{
"type": "excalidraw",
"version": 2,
"source": "https://excalidraw.com",
"elements": [...],
"appState": { "viewBackgroundColor": "#ffffff" },
"files": {}
}
| Type | Extra Properties | Usage |
|------|-----------------|-------|
| rectangle | roundness | Boxes, containers, cards |
| ellipse | — | Circles, ovals, bubbles |
| diamond | — | Decision nodes, conditions |
| line | points, startBinding, endBinding | Lines, connectors |
| arrow | points, startBinding, endBinding | Directed connections |
| text | text, fontSize, fontFamily, textAlign | Labels, annotations |
| freedraw | points, simulatePressure | Freehand sketches |
| image | fileId, status | Embedded images |
| frame | — | Grouping frames |
For full JSON schema of each type (common properties, text properties, line/arrow point arrays, binding mechanics), read {SKILL_PATH}/references/element-types.md.
Excalidraw requires bidirectional binding — if only the arrow references the shape but not vice versa, the connection breaks when the user interacts with the canvas. Always set both:
startBinding/endBinding → references shape IDsboundElements → references arrow IDSame pattern for text inside shapes: shape's boundElements references the text, text's containerId references the shape.
#1e1e1e — Black (default)#e03131 — Red#2f9e44 — Green#1971c2 — Blue#f08c00 — Orange#6741d9 — Purpletransparent — None (default)#ffc9c9 — Light red#b2f2bb — Light green#a5d8ff — Light blue#ffec99 — Light yellow#d0bfff — Light purpleEach element needs a unique id. Use descriptive IDs like "start-node", "arrow-1", "label-process". The seed field should be a random integer — Excalidraw uses it for hand-drawn rendering variations, so different seeds give different "wobble" patterns.
roughness: 0 for clean wireframes — the hand-drawn look doesn't suit UI mockupsroundness: { "type": 3 } for rounded rectanglesroughness: 0 for clean/professional look, 1 for hand-drawn styleid values and random seed valuesGenerate breadboard circuit mockups and visual diagrams using HTML5 Canvas drawing techniques. Use when asked to create circuit layouts, visualize electronic component placements, draw breadboard diagrams, mockup 6502 builds, generate retro computer schematics, or design vintage electronics projects. Supports 555 timers, W65C02S microprocessors, 28C256 EEPROMs, W65C22 VIA chips, 7400-series logic gates, LEDs, resistors, capacitors, switches, buttons, crystals, and wires.
> Use when a HyperFrames composition needs seek-safe 2D/3D keyframes, GSAP timelines, CSS keyframes, Anime.js, WAAPI, FLIP, paths, masks, SVG morph/draw, text trails, 3D depth, or `hyperframes keyframes` diagnostics. Don't use for broad scene strategy, brand design, media sourcing, captions, or general video planning.
Analyze images, websites, and Figma files to extract their design and generate a `design.md` with token system, component inventory, and reconstruction notes. Use this skill whenever the user wants to understand, document, replicate, or audit the design of something visual: a screenshot, a URL, a Figma link, a Pinterest reference, a mockup, a competitor's site, a component, a dashboard, a landing page. Also when they ask 'extract the design system from X', 'document the style of Y', 'analyze this visually', 'convert this image into tokens', 'help me replicate this design', 'what palette does this site use', 'how is this built'. Also for single elements: 'copy this navbar', 'recreate this illustration', 'give me a prompt to regenerate this graphic' — element mode outputs a focused element.md, with token-grounded image-model prompts when the element is visual art. If the user brings any visual source and wants to understand it at a design level — this skill should activate.
Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.
Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured surfaces, image-led composition, tasteful custom iconography, and clean phone mockup framing. By default, screens should be shown inside a subtle premium iPhone or similar phone mockup with a visible frame, while the main focus stays on the app content itself. This skill generates images only. It does not write code.
Optimize web performance: bundle size, images, caching, lazy loading, and overall page speed. Use when site is slow, reducing bundle size, fixing layout shifts, improving Time to Interactive, or optimizing for Lighthouse scores. Triggers on: web performance, bundle size, page speed, slow site, lazy loading. Do NOT use for Core Web Vitals-specific fixes (use core-web-vitals), running Lighthouse audits (use perf-lighthouse), or Astro-specific optimization (use perf-astro).
| Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.
| Official GSAP skill for performance — prefer transforms, avoid layout thrashing, will-change, batching. Use when optimizing GSAP animations, reducing jank, or when the user asks about animation performance, FPS, or smooth 60fps.
Take pandazki/pneuma-draw from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.