quality-critique
Visual quality critique checklist for draw.io diagrams — run before writing any .drawio file
What this skill does
# Diagram Quality Critique Run this critique on every generated diagram XML BEFORE writing the file. Fix all issues found before saving — do not write substandard diagrams. ## Critique Checklist ### 1. Structure (must pass — blank file prevention) - [ ] XML starts with `<mxfile>` wrapping `<diagram>` wrapping `<mxGraphModel>` - [ ] `background="none"` set on `<mxGraphModel>` (transparent, not white) - [ ] Cells `id="0"` and `id="1" parent="0"` present - [ ] At least 2 layers defined (content + annotations) - [ ] All cell IDs are unique - [ ] All `parent` references point to existing cells - [ ] All `source`/`target` on edges point to existing vertices ### 2. Layout Quality - [ ] Shapes are grid-aligned (x, y coordinates are multiples of 10) - [ ] No overlapping shapes (check x, y, width, height for collisions) - [ ] Consistent spacing between related elements (60-80px gaps) - [ ] Logical flow direction (top-to-bottom or left-to-right) - [ ] Container/group boundaries have 20px+ padding around children - [ ] Title annotation present at top-left ### 3. Edge/Connection Quality (critical — prevents ugly routing) - [ ] ALL edges use `rounded=1;jettySize=auto;` (no sharp 90-degree bends) - [ ] Primary flow edges use `strokeWidth=2;` - [ ] Edges between non-aligned shapes specify `exitX/exitY/entryX/entryY` - [ ] No edges crossing through shapes (reroute or add waypoints) - [ ] Crossing edges use `jumpStyle=arc;jumpSize=16;` - [ ] Return/response edges use `dashed=1;dashPattern=8 4;` - [ ] Edge labels are positioned to not overlap shapes ### 4. Visual Quality - [ ] All primary shapes have `shadow=1;` for depth - [ ] HTML labels enabled (`html=1;`) with `<b>` for titles - [ ] Font size >= 11pt for shape labels, >= 9pt for edge labels - [ ] Fill colors use the standard palette (not random hex values) - [ ] Text has sufficient contrast against fill (dark text on light fills, white text on dark fills) - [ ] fontColor explicitly set (use `#333333` for light fills, `#FFFFFF` for dark fills) - [ ] Container headers use `fontStyle=1;` (bold) ### 5. Sophistication - [ ] Related elements grouped in containers (`container=1;collapsible=1;`) - [ ] Semantic layers used (not all elements on default layer) - [ ] Color coding is consistent and meaningful (blue=services, green=data, etc.) - [ ] Legend present if 3+ color categories used - [ ] Metadata via `<object>` tags where appropriate (services, APIs) - [ ] Multi-page used for complex diagrams (10+ major elements → drill-down pages) ### 6. Platform Compatibility - [ ] Azure DevOps: export as PNG (not SVG) — SVG rendering is broken - [ ] GitHub: use `.drawio.svg` with `--embed-diagram` for editability - [ ] Transparent background for clean embedding in all contexts ## Contrast Reference | Fill Color | Recommended fontColor | Example | |-----------|----------------------|---------| | `#DAE8FC` (blue) | `#333333` | Services | | `#D5E8D4` (green) | `#333333` | Data stores | | `#FFF2CC` (yellow) | `#333333` | Decisions | | `#F8CECC` (red) | `#333333` | Errors | | `#E1D5E7` (purple) | `#333333` | External | | `#F5F5F5` (gray) | `#333333` | Containers | | `#08427B` (C4 blue) | `#FFFFFF` | C4 person | | `#438DD5` (C4 mid) | `#FFFFFF` | C4 system | | `#1B1B1B` (dark) | `#FFFFFF` | Dark mode | | `#143642` (blueprint) | `#DADADA` | Blueprint | ## Auto-Fix Patterns When critique finds issues, apply these automatic fixes: | Issue | Fix | |-------|-----| | Missing `rounded=1` on edge | Add `rounded=1;jettySize=auto;` to edge style | | Missing `shadow=1` on shape | Add `shadow=1;` to vertex style | | Missing layers | Add `<mxCell id="layer-notes" value="Annotations" parent="0"/>` | | `background` not set | Add `background="none"` to `<mxGraphModel>` | | No `html=1` on labeled shape | Add `html=1;` and wrap value in `<b>` tags | | Sharp edge corners | Add `rounded=1;` to edge style | | Thin primary edges | Add `strokeWidth=2;` to primary flow edges | | No title | Add text cell on annotations layer |
Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.