visualize
Use when content needs a diagram or visual — auto-detects content shape, picks the best format per the active-selection rule, and renders it.
What this skill does
# /visualize
Auto-detect content shape and render the appropriate visualization. Follows the active-selection rule from `ai-workspace/rules/visualizations.md`.
## Usage
```
/visualize # visualize the last discussed concept
/visualize <topic or file> # visualize specific content
/visualize --format mermaid <topic> # force a specific format
```
## Steps
1. **Identify content.** From args, recent conversation context, or a file path. Determine what needs visualizing.
2. **Classify content shape.** Use this decision table:
| Content shape | Signal | Format |
|---|---|---|
| Graph with nodes + edges | architecture, dependencies, flow between components | Mermaid `graph` or `flowchart` |
| Sequence / interaction | request flow, API calls, multi-step protocol | Mermaid `sequenceDiagram` |
| State transitions | modes, lifecycle, status changes | Mermaid `stateDiagram-v2` |
| Comparison (3+ items) | options, tradeoffs, feature matrix | Markdown table |
| Hierarchy / tree | file structure, org chart, simple nesting | ASCII art |
| Contrast (2 items) | before/after, good/bad, do/don't | Inline pairs |
| Entity relationships | data model, schema | Mermaid `erDiagram` |
3. **Check render surface.** Mermaid in committed `.md` files renders on iOS/web/GitHub/VS Code. In terminal chunks, Mermaid is literal text — use ASCII instead. When surface is unknown, default to ASCII.
4. **Render.**
- **ASCII / table / inline pairs**: output directly in the response.
- **Mermaid**: output as a fenced `mermaid` code block in the response. If high-resolution PNG is needed:
```bash
node --import tsx "${SKILL_DIR}/scripts/render-mermaid.ts" --input <mermaid-file> --output <png-path> --width 2400 --height 1800
```
- **Format override**: if user passed `--format`, use that format regardless of auto-detection.
5. **Present.** Show the visualization. If Mermaid PNG was rendered, display the path.
## Failure modes
| Condition | Behavior |
|---|---|
| Content shape ambiguous | Ask: "This could be a [X] or [Y] — which fits better?" |
| Mermaid syntax error | Show the error, offer to fix |
| mmdc not available | Fall back to fenced Mermaid block (renders on GitHub/web) |
## Cross-tool notes
- **Codex / Cursor**: run `scripts/render-mermaid.ts` directly for PNG rendering. Content-shape detection is agent reasoning, not script logic.
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.