academic plotting

Writing Community v1.0.0

Skill notes

When to Use Which Workflow

Figure Type · Tool · Why Architecture / system diagram · Gemini (Workflow 1) · Complex spatial layouts with boxes, arrows, labels Workflow / pipeline / lifecycle · Gemini (Workflow 1) · Multi-step processes with connections Bar chart, line plot, scatter · matplotlib (Workflow 2) · Precise numerical data, reproducible Heatmap, confusion matrix · matplotlib/seaborn (Workflow 2) · Structured grid data

Step 0: Context Analysis & Extraction

The user will typically provide one of these inputs — not a ready-made specification: Input Type · Example · What to Extract Full paper / section draft · "Here's our method section..." · System components, their relationships, data flow Description paragraph · "Our system has three layers that..." · Key entities, hierarchy, connections Raw results / data table · "MMLU: 85.2, HumanEval: 72.1..." · Metrics, methods, comparison structure

Extraction Workflow

For diagrams (research context → architecture figure): Read the provided context — paper section, abstract, or description paragraph Identify visual entities — What are the main components/modules/stages? Look for: nouns that represent system parts, named modules, layers, stages Count them: if >8 top-level entities, consider grouping into sections

Auto-Detection Examples

Context → Diagram: "Our system has a Planner, Executor, and Verifier. Planner sends plans to Executor, Executor returns results to Verifier, Verifier feeds back to Planner on failure." → 3 entities, cycle layout, dashed feedback arrow → Workflow 1 (Gemini) Data → Chart: "GPT-4: MMLU 86.4, HumanEval 67.0. Ours: 88.1, 71.2. Llama-3: 79.3, 62.1." → 3 methods × 2 benchmarks → Workflow 2 (grouped bar), highlight "Ours" in coral

Workflow 1: Architecture & System Diagrams (AI Image Generation)

Use Gemini 3 Pro Image Preview to generate diagrams. Choose a visual style first — this is the single biggest factor in whether the figure looks professional or generic.

Fluxly profile Runtime and permissions are inferred by Fluxly static checks, not author declarations or runtime test results.
Domain
Writing
Author-declared agents
No explicit declaration found; this is not inferred or tested compatibility
Static check
98 / 100 · heuristic scan, not runtime safety proof
Runtime evidence
Not run; no isolated runtime test evidence is currently recorded
Author / version / license
@Orchestra-Research · v1.0.0 · MIT
Token usage
Moderate
Setup complexity
Manual integration
External API key
Required · Gemini
Operating systems
macOS · Linux · Windows
Runtime requirements
Node.js · Python
Detected file/system behavior
  • Read-only
  • Write / modify
  • Shell exec
  • Env read
Network behavior
External requests
Install commands
None (reference only)

Heads up: allowed-tools includes 11 entries; the permission surface is broad.

Output preview academic-plotting.preview
# Auto-Detection Examples

**Context → Diagram**: "Our system has a Planner, Executor, and Verifier. Planner sends plans to Executor, Executor returns results to Verifier, Verifier feeds back to Planner on failure." → 3 entities, cycle layout, dashed feedback arrow → **Workflow 1 (Gemini)** **Data → Chart**: "GPT-4: MMLU 86.4, HumanEval 67.0. Ours: 88.1, 71.2. Llama-3: 79.3, 62.1." → 3 methods × 2 benchmarks → **Workflow 2 (grouped bar)**, highlight "Ours" in coral ---

Discussion

Powered by GitHub Discussions. Sign in with GitHub to comment, react, or subscribe.