Drawio Skill

Draw.io Diagrams

Overview

Generate .drawio XML files and export to PNG/SVG/PDF/JPG locally using the native draw.io desktop app CLI.

Supported formats: PNG, SVG, PDF, JPG — no browser automation needed.

PNG, SVG, and PDF exports support --embed-diagram (-e) — the exported file contains the full diagram XML, so opening it in draw.io recovers the editable diagram. Use double extensions (name.drawio.png) to signal embedded XML.

When to use / when NOT to use

Use this skill for: polished, precise diagrams (architecture, network, strict UML, ERD), anything needing solid opaque fills, 10,000+ stock/branded shapes, swimlanes, or custom geometry, exported as editable PNG/SVG/PDF.

Do NOT use it — route elsewhere — for:

• A casual hand-drawn / whiteboard look → excalidraw or tldraw.
• Diagrams-as-code that live in git / render in Markdown → mermaid (general) or plantuml (UML).
• Freeform infinite-canvas sketching or freehand strokes → tldraw.

Bundled resources

When the workflow references one of these, read it on demand — none of them need to be in context up front.

| File | Read it when | |---|---| | references/diagram-types.md | The user names a specific diagram type (ERD, UML class, sequence, architecture, ML/DL, flowchart) | | references/shapes.md + scripts/shapesearch.py | The diagram needs a specific shape — a cloud icon (AWS/Azure/GCP), Cisco/Kubernetes/network symbol, UML/BPMN/ER/electrical/P&ID element — or any time you'd otherwise guess a style= string. shapesearch.py "" returns the exact official style for 10k+ shapes | | scripts/aiicons.py | The diagram involves an AI/LLM brand (OpenAI, Claude, Gemini, Mistral, Llama, HuggingFace, Ollama, LangChain, …) — aiicons.py "" returns a draw.io image style for the brand logo (lobe-icons via CDN; --embed to inline). draw.io has no built-in AI logos. See references/shapes.md → "AI / LLM brand logos" | | references/style-presets.md | The user asks to learn / save / list / set-default / delete a style preset, or you've resolved an active preset and need the application rules | | references/style-extraction.md | You're inside the Learn flow and need the extraction procedure (called from style-presets.md) | | references/troubleshooting.md | An export fails, vision rejects a PNG, or a rendering looks wrong | | scripts/repair_png.py | After every -e PNG export — fixes draw.io's truncated IEND chunk (issue #8) | | scripts/encode_drawio_url.py | The CLI is unavailable and you need a browser-fallback diagrams.net URL (--edit for an editable editor URL) | | references/autolayout.md | The diagram is large or layout-heavy (dependency/call graph, code structure, >~15 nodes) and you want Graphviz to place nodes + route edges instead of hand-placing coordinates | | scripts/pyimports.py · jsimports.py · goimports.py · rustimports.py | The user wants to visualize a Python, JS/TS, Go, or Rust project structure — extracts the import graph (transitive-reduced, optional --group containers, nested by sub-package) for autolayout | | scripts/pyclasses.py | The user wants a Python class hierarchy / class diagram — extracts classes + inheritance edges (boxed by module with --group) for autolayout | | scripts/validate.py | You generated a .drawio (especially via autolayout or for a large hand-placed diagram) and want a fast deterministic structural lint (dangling edges, dup/reserved ids, broken parents, overlaps) before the vision self-check |

Prerequisites

The draw.io desktop app must be installed and the CLI accessible:

macOS sandbox / sandbox isolation note (e.g., codex.app): In some sandboxed macOS environments, invoking the draw.io desktop CLI (even drawio --version) can crash the draw.io process or produce no output. If that happens, treat the CLI as unavailable in this sandbox isolation — do not keep retrying inside the sandbox. Prefer a non-sandboxed host environment (outside sandbox isolation) for any CLI export work, or use the browser fallback / XML-only outputs.

# macOS (Homebrew — recommended; CLI binary is `drawio`, not `draw.io`)
brew install --cask drawio
drawio --version

# macOS (full path if not in PATH)
/Applications/draw.io.app/Contents/MacOS/draw.io --version

# Windows
"C:\Program Files\draw.io\draw.io.exe" --version

# Linux
drawio --version

Install draw.io desktop if missing:

• macOS: brew install --cask drawio or download from https://github.com/jgraph/drawio-desktop/releases
• Windows: download installer from https://github.com/jgraph/drawio-desktop/releases
• Linux: download .deb/.rpm from https://github.com/jgraph/drawio-desktop/releases — do not use snap (AppArmor sandbox denies secrets/keyring on servers, causes crash)

Workflow

Before starting the workflow, assess whether the user's request is specific enough. If key details are missing, ask 1-3 focused questions:

• Diagram type — which preset? (ERD, UML, Sequence, Architecture, ML/DL, Flowchart, or general)
• Output format — PNG (default), SVG, PDF, or JPG?
• Output location — default is the user's working dir; honor any explicit path the user gives (e.g. "put it in ./artifacts/"). Don't ask if they didn't mention one.
• Scope/fidelity — how many components? Any specific technologies or labels?

Skip clarification if the request already specifies these details or is clearly simple (e.g., "draw a flowchart of X").

Step 0 — Resolve active preset. Determine which (if any) user-defined style preset applies to this generation.

• Scan the user's message for a phrase that clearly names a style preset: "use my ` style", "with my style", "in mode", "in the style of ". A bare with does **not** count — "draw a diagram with redis" names a component, not a style. If a clear match is found → active preset = `.
• Else, check ~/.drawio-skill/styles/ for any file with "default": true. If found → active preset = that one.
• Else → no preset active; fall through to the built-in color/shape/edge conventions for the rest of the workflow.

Load the preset JSON from ~/.drawio-skill/styles/.json, falling back to /styles/built-in/.json. If the named preset exists in neither location, tell the user the name is unknown, list the available presets (user dir + built-in), and stop — do not silently fall back to defaults.

When a preset loads successfully, mention it in the first line of the reply: "Using preset ` (confidence: `)." See the Applying a preset subsection below for how the preset changes color/shape/edge/font decisions.

1. Check deps — resolve which name the binary has on this system and use that name verbatim in every subsequent command in this workflow. Try in order: (a) drawio --version (the canonical name for Homebrew cask, jgraph .deb/.rpm, Arch AUR), (b) draw.io --version (older builds, some custom symlinks, some distro packages), (c) macOS .app direct: /Applications/draw.io.app/Contents/MacOS/draw.io --version, (d) Windows: "C:\Program Files\draw.io\draw.io.exe" --version. The first one that prints a version is your binary; remember the exact path/name and substitute it for drawio in every export command below. Do not copy the example commands verbatim if your binary is named differently — the examples use drawio only because it's the most common. On macOS-Homebrew, drawio is just a thin wrapper script that execs /Applications/draw.io.app/Contents/MacOS/draw.io — they run the same engine, so candidate (c) is only needed when the drawio wrapper is absent (e.g. the app was installed by drag-and-drop without the cask).
2. Plan — identify shapes, relationships, layout (LR or TB), group by tier/layer
3. Generate — write .drawio XML file to disk. Hand-place coordinates for small/styled diagrams. For large or layout-heavy diagrams (dependency/call graphs, code structure, >~15 nodes), don't hand-place — describe the graph as JSON and run python3 /scripts/autolayout.py graph.json -o .drawio to compute node positions + orthogonal edge routing via Graphviz (see references/autolayout.md). For a Python / JS-TS / Go / Rust project, the matching importer (scripts/pyimports.py, jsimports.py, goimports.py, or rustimports.py) extracts the import graph (transitive-reduced; add --group to box modules by sub-package, nested for deep trees) ready for autolayout; for a Python class hierarchy, scripts/pyclasses.py extracts classes + inheritance instead. For complex architecture diagrams with many visible edge labels, give labels labelBackgroundColor=#ffffff;fontSize=11 and use edge geometry x/y offsets plus ` to move long labels into nearby whitespace instead of relying on draw.io's default midpoint placement. After generating any .drawio, run python3 /scripts/validate.py .drawio for a fast structural lint (dangling edges, dup ids, overlaps) before exporting. Default output dir is the user's working dir; if the user specified an output path or directory (e.g. ./artifacts/, docs/images/), use that instead — mkdir -p` the target dir first. Apply the same dir choice to PNG/SVG/PDF exports in steps 4 and 7.
4. Export draft — run CLI to produce a preview PNG. Do NOT pass -e at this step — the embedded zTXt mxGraphModel chunk it adds causes vision APIs (Claude included) to return 400 "Could not process image" in step 5. Cap the preview width with --width 2000 (not -s 2) — Claude's vision API rejects images larger than 2576×2576px with "Unable to resize image — dimensions exceed the 2576x2576px limit", and -s 2 on a medium-or-larger diagram easily overshoots that ceiling. Save the clean preview as .png (single extension). Embedding and full-resolution scale are for the final export only (step 7).
5. Self-check — use the agent's built-in vision capability to read the exported PNG, catch obvious issues, auto-fix before showing user (requires a vision-enabled model such as Claude Sonnet/Opus). If reading the PNG returns a 400 / "Could not process image" error, you almost certainly exported with -e by mistake — re-export without -e and retry once. If it still fails, skip self-check and continue to step 6.
6. Review loop — show image to user, collect feedback, apply targeted XML edits, re-export, repeat until approved
7. Final export — re-export the approved version to all requested formats. Use -e here (PNG/SVG/PDF) so the deliverable stays editable in draw.io; save as .drawio.png to signal embedded XML. For PNG with -e, run python3 /scripts/repair_png.py .drawio.png immediately after — draw.io's CLI truncates the IEND chunk in -e PNG output (8 bytes missing), producing a corrupt file that vision APIs and strict PNG decoders reject (issue #8). Report file paths.

If drawio --version crashes or prints nothing (common in restricted macOS sandbox isolation like codex.app):

• Do not keep retrying CLI invocations inside the sandbox.
• Skip steps 4, 5, 6, and 7 (CLI export + PNG-based review) and use Browser fallback (scripts/encode_drawio_url.py) or deliver the .drawio XML only.
• If the user needs PNG/SVG/PDF outputs, ask them to run the export commands in a non-sandboxed host environment (outside sandbox isolation) and share the resulting files.

Escalation rule:

• If the binary exists on PATH (or known app path exists) but execution fails with abnormal exit, empty output, Electron startup failure, display/session error, or likely sandbox restriction, prefer one escalated retry before falling back.
• If the binary is missing entirely, do not escalate just to search more aggressively; go to install guidance or fallback.

Step 5: Self-Check

After exporting the draft PNG, use the agent's vision capability (e.g., Claude's image input) to read the image and check for these issues before showing the user. If the agent does not support vision, skip self-check and show the PNG directly.

Important: the draft PNG read here must have been exported without -e. Draw.io's -e flag emits a PNG with a truncated IEND chunk (8 bytes of type+CRC missing) that the Anthropic vision API rejects with 400 "Could not process image" (issue #8). The simplest fix for the preview step is to skip -e entirely; the final export in step 7 keeps -e and runs the repair snippet. If you see the 400 error here, re-export without -e and retry once; if it still fails (any other reason), skip self-check and proceed to step 6.

| Check | What to look for | Auto-fix action | |-------|-----------------|-----------------| | Overlapping shapes | Two or more shapes stacked on top of each other | Shift shapes apart by ≥200px | | Clipped labels | Text cut off at shape boundaries | Increase shape width/height to fit label | | Missing connections | Arrows that don't visually connect to shapes | Verify source/target ids match existing cells | | Off-canvas shapes | Shapes at negative coordinates or far from the main group | Move to positive coordinates near the cluster | | Edge-shape overlap | An edge/arrow visually crosses through an unrelated shape | Add waypoints (`) to route around the shape, or increase spacing between shapes | | Stacked edges | Multiple edges overlap each other on the same path | Distribute entry/exit points across the shape perimeter (use different exitX/entryX values) | | Edge-label overlap | Edge text overlaps another label, line, or node in the exported PNG | Keep the label on the edge, add a white label background, and move it locally with edge geometry x/y` offsets into adjacent whitespace |

• Max 2 self-check rounds — if issues remain after 2 fixes, show the user anyway
• Re-export after each fix and re-read the new PNG

Step 6: Review Loop

After self-check, show the exported image and ask the user for feedback.

Targeted edit rules — for each type of feedback, apply the minimal XML change:

| User request | XML edit action | |-------------|----------------| | Change color of X | Find mxCell by value matching X, update fillColor/strokeColor in style | | Add a new node | Append a new mxCell vertex with next available id, position near related nodes | | Remove a node | Delete the mxCell vertex and any edges with matching source/target | | Move shape X | Update x/y in the mxGeometry of the matching mxCell | | Resize shape X | Update width/height in the mxGeometry of the matching mxCell | | Add arrow from A to B | Append a new mxCell edge with source/target matching A and B ids | | Change label text | Update the value attribute of the matching mxCell | | Change layout direction | Full regeneration — rebuild XML with new orientation |

Rules:

• For single-element changes: edit existing XML in place — preserves layout tuning from prior iterations
• For layout-wide changes (e.g., swap LR↔TB, "start over"): regenerate full XML
• Overwrite the same {name}.png (no -e) each iteration — do not create v1, v2, v3 files. -e is reserved for the final export in step 7.
• After applying edits, re-export and show the updated image
• Loop continues until user says approved / done / LGTM
• Safety valve: after 5 iteration rounds, suggest the user open the .drawio file in draw.io desktop for fine-grained adjustments

Step 7: Final Export

Once the user approves:

• Export to all requested formats (PNG, SVG, PDF, JPG) — default to PNG if not specified
• Report file paths for both the .drawio source file and exported image(s)
• Auto-launch: offer to open the .drawio file in draw.io desktop for fine-tuning — open diagram.drawio (macOS), xdg-open (Linux), start (Windows)
• Confirm files are saved and ready to use

Style Presets

A style preset is a named JSON file capturing a user's visual preferences (palette, shapes, font, edges). When active, it fully replac

…

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: Agents365-ai
• Source: Agents365-ai/drawio-skill
• License: MIT
• Homepage: https://agents365-ai.github.io/drawio-skill/

Install and usage instructions live in the source repository linked above.