Skip to content
Claude CodedocsCLI & tooling

Explore PaperBanana codebase to learn figure generation workflow

Session from traceweave on Hugging Face by Samarth0710 · MIT · condensed by Coders Talk

1msession
0interventions
GOAL

Understand the PaperBanana repo — what it is, how to generate figures, its available scripts/tools, and its documentation — by reading through the code and docs.

  1. Prompt · +0
    Explore the paperbanana directory thoroughly: what it is, how to generate figures, available tools/scripts, docs, and supported figure types.
  2. Agent did · +0m
    Searched for docs/config files and read README.md, docs/paperbanana.md, requirements.txt, and directory listing to get an overview.
  3. Agent did · +0m
    Read paperbanana.py, config.py, and all agent modules (retriever, planner, visualizer, stylist) to understand the multi-agent pipeline architecture.
  4. Agent did · +0m
    Read critic.py, aesthetic_guidelines.py, and examples.py to understand the refinement loop and styling guidelines.
  5. Agent did · +0m
    Inspected load_reference_set.py, generate_paper_figures.py, and app.py (the Gradio HuggingFace Spaces interface) to see end-to-end usage.
  6. Agent did · +0m
    Explored agents/__init__.py, data/ and examples/ directories, utils.py, scripts/ folder, and enumerated all Python files in the repo.
  7. Agent did · +0m
    Read scripts/generate_self_diagram.py and sampled the spotlight_reference_set.json to see the reference example format.
  8. Outcome · +1m
    Produced a comprehensive written overview of PaperBanana: its 5-agent pipeline (Retriever, Planner, Stylist, Visualizer, Critic), usage scripts, and supported figure/diagram types.
VERDICT

I'd start with a more targeted prompt pointing straight at the entry-point scripts (paperbanana.py, app.py, generate_paper_figures.py) instead of asking for a full directory sweep, since most of the value came from the agent files anyway. Letting it read everything did work here with no corrections needed, so for a pure exploration task like this the thoroughness paid off.

I tried this · 0

Discussion · 0

How Builds work