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
- Erin-1919/claude-skillstheir own version, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 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.
- literature-searchSkill
- paper-fulltext-harvestSkill
- paper-readingSkill
- related-work-surveySkill
- social-media-paper-triageSkill
- zotero-managementSkill
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
- Distinctive: line 44
Use Gemini if you have a Google AI key.
- Distinctive: line 59
If the user only gives a vague request, ask:
- Distinctive: line 107
Whitespace: don't overcrowd — reviewers skim figures in seconds
- Very specific: line 127
No PNGs in output dir: check out_dir/results.json for the raw per-candidate response and any error messages.
≈ “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.
Files
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
Clone PaperBanana somewhere convenient:
git clone https://github.com/dwzhu-pku/PaperBanana.git ~/PaperBanana cd ~/PaperBanana uv venv && uv pip install -r requirements.txtConfigure
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-2Use 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:
- Method text: the relevant section of the paper describing the
approach (
./method.mdor./method.tex). - 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| Flag | Default | Notes |
--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 |
--candidates | 3 | Independent diagram candidates |
--max-concurrent | 2 | Cap concurrent runs (be gentle on quota) |
--exp-mode | demo_full | Full pipeline (Planner+Stylist+Visualizer+Critic). Use demo_planner_critic to skip Stylist, or vanilla for single-shot. |
--aspect-ratio | 16:9 | One of 21:9, 16:9, 3:2, 1:1 |
--max-critic-rounds | 2 | Critique → 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
| Type | When to use | Key elements |
| Pipeline / Flowchart | Sequential processing | Boxes + arrows, L→R or T→B |
| Architecture | System overview | Nested boxes, clear module boundaries |
| Comparison | Before/after, baseline vs proposed | Side-by-side panels |
| Ablation | Component contributions | Bar charts, highlighted rows |
| Framework | High-level conceptual overview | Abstract shapes, minimal detail |
Troubleshooting
429 RESOURCE_EXHAUSTEDon Gemini: monthly Google AI Studio spending cap hit. Raise it at https://ai.studio/spend or switchimage_model_nametoopenai/gpt-5.4-image-2and setOPENROUTER_API_KEY.OpenRouter Client not initialized:OPENROUTER_API_KEYnot in env andopenrouter_api_keynot in yaml.- No PNGs in output dir: check
out_dir/results.jsonfor the raw per-candidate response and any error messages. - Long latency (>5 min): most wall time is the image model. Lower
--candidatesor use--exp-mode vanillafor faster iteration.
Links
- PaperBanana repo: https://github.com/dwzhu-pku/PaperBanana
- PaperVizAgent (Google Research version of the same project): https://github.com/google-research/papervizagent
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
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.

