agentleFS
jxtsejxtse/scientific-research-skills/skills/academic-figure-generation/SKILL.md

academic-figure-generation

Skill68 starsChanged 7 months agoMITView on GitHub

Generates publication-quality academic figures (framework diagrams, pipeline illustrations, system architectures, method overviews) from a paper's method text and a target caption, using a local PaperBanana multi-agent pipeline (Retriever → Planner → Stylist → Visualizer → Critic).

  • Reads credentials
  • Installs packages

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. Erin-1919/claude-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository6 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use Gemini if you have a Google AI key.

    line 44
  2. Distinctive:

    If the user only gives a vague request, ask:

    line 59
  3. Distinctive:

    Whitespace: don't overcrowd — reviewers skim figures in seconds

    line 107
  4. Very specific:

    No PNGs in output dir: check out_dir/results.json for the raw per-candidate response and any error messages.

    line 127

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Academic Figure Generation

Thin CLI wrapper around PaperBanana (a.k.a. PaperVizAgent), a multi-agent figure-generation pipeline for academic papers.

The skill provides exactly one script: scripts/generate.py. It feeds your method text + caption into PaperBanana and writes N candidate PNGs. Model selection and API keys come from PaperBanana's own configs/model_config.yaml — the wrapper does not override them.

One-time setup

  1. Clone PaperBanana somewhere convenient:

    git clone https://github.com/dwzhu-pku/PaperBanana.git ~/PaperBanana
    cd ~/PaperBanana
    uv venv && uv pip install -r requirements.txt
  2. Configure configs/model_config.yaml — set the image model and the matching API key. Two common setups:

    defaults:
      image_model_name: "gemini-3-pro-image-preview"   # or "openai/gpt-5.4-image-2"
      model_name: "gemini-3.1-pro-preview"             # text model for Planner/Stylist/Critic
    
    api_keys:
      google_api_key: "..."        # required for Gemini models
      openrouter_api_key: ""       # required for openai/gpt-5.4-image-2

    Use Gemini if you have a Google AI key; use GPT-Image-2 via OpenRouter if you have an OpenRouter key. Pick one — there's nothing else to wire up.

Workflow

Step 1: Gather inputs

You need:

  1. Method text: the relevant section of the paper describing the approach (./method.md or ./method.tex).
  2. Figure caption: the target caption, e.g. "Figure 1: Overview of our framework".

If the user only gives a vague request, ask:

  • What aspect of the method should the figure focus on?
  • Style? (block diagram, flowchart, pipeline, architecture, comparison)
  • Venue / column width? (ACL ≤ 7.5", NeurIPS single-column 5.5")

Step 2: Generate

~/PaperBanana/.venv/bin/python scripts/generate.py \
  --paperbanana-root ~/PaperBanana \
  --method-file ./method.md \
  --caption "Figure 1: Overview of our framework" \
  --out-dir ./figures/v1 \
  --candidates 3 \
  --aspect-ratio 16:9
FlagDefaultNotes
--paperbanana-root(required)Path to your PaperBanana checkout
--method-file(required)Method section as a text/markdown file
--caption(required)Target figure caption
--out-dir(required)Where PNGs land
--candidates3Independent diagram candidates
--max-concurrent2Cap concurrent runs (be gentle on quota)
--exp-modedemo_fullFull pipeline (Planner+Stylist+Visualizer+Critic). Use demo_planner_critic to skip Stylist, or vanilla for single-shot.
--aspect-ratio16:9One of 21:9, 16:9, 3:2, 1:1
--max-critic-rounds2Critique → revise loops (early-exits if critic says "No changes needed")

Step 3: Present & iterate

  • Show all candidates to the user.
  • Common refinements: color scheme, layout, label text, font size.
  • Re-run with a tweaked caption or more candidates.

Step 4: Export

  • PNGs are written as candidate_0.png, candidate_1.png, … in --out-dir.
  • For camera-ready PDFs: magick candidate_0.png candidate_0.pdf.

Style guidelines

  • Color: consistent, colorblind-friendly palette
  • Fonts: match the paper's body font (Times for ACL/EMNLP, Helvetica/Arial for many ML venues)
  • Labels: concise; no full sentences inside the diagram
  • Arrows: solid for data flow, dashed for optional / feedback loops
  • Whitespace: don't overcrowd — reviewers skim figures in seconds

Common figure types

TypeWhen to useKey elements
Pipeline / FlowchartSequential processingBoxes + arrows, L→R or T→B
ArchitectureSystem overviewNested boxes, clear module boundaries
ComparisonBefore/after, baseline vs proposedSide-by-side panels
AblationComponent contributionsBar charts, highlighted rows
FrameworkHigh-level conceptual overviewAbstract shapes, minimal detail

Troubleshooting

  • 429 RESOURCE_EXHAUSTED on Gemini: monthly Google AI Studio spending cap hit. Raise it at https://ai.studio/spend or switch image_model_name to openai/gpt-5.4-image-2 and set OPENROUTER_API_KEY.
  • OpenRouter Client not initialized: OPENROUTER_API_KEY not in env and openrouter_api_key not in yaml.
  • No PNGs in output dir: check out_dir/results.json for the raw per-candidate response and any error messages.
  • Long latency (>5 min): most wall time is the image model. Lower --candidates or use --exp-mode vanilla for faster iteration.

Links

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.