What is evaluate-diagram?

A diagram-checking tool that compares a generated diagram with a human-made reference image. It uses the surrounding methodology and figure caption to judge the result.

Use it to assess diagrams on faithfulness, conciseness, readability, and visual quality from an image pair.

It helps identify whether a generated diagram matches the intended content and presentation, instead of relying only on visual guesswork.

How llmsresearch/paperbanana configures Claude Code

About the project

PaperBanana is an open-source tool that generates academic diagrams, statistical plots, and other research illustrations from text descriptions. Researchers can use it through a command-line interface, Python API, local web interface, or MCP server, while the catalogue add-ons support agent-driven use.

llmsresearch/paperbanana · 2,344 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to llmsresearch/paperbanana. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/llmsresearch/paperbanana/main/.claude/skills/evaluate-diagram/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/llmsresearch/paperbanana

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/llmsresearch/paperbanana/evaluate-diagram/github.svg)](https://agentmods.dev/skills/llmsresearch/paperbanana/evaluate-diagram)

Your own site

<a href="https://agentmods.dev/skills/llmsresearch/paperbanana/evaluate-diagram"><img src="https://agentmods.dev/badge/skills/llmsresearch/paperbanana/evaluate-diagram/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/llmsresearch/paperbanana/evaluate-diagram"><img src="https://agentmods.dev/badge/skills/llmsresearch/paperbanana/evaluate-diagram.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 311 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00311
Opus 5	$0.00000	$0.00156
Sonnet 5	$0.00000	$0.00062
Haiku 4.5	$0.00000	$0.00031

Measured 10d ago against content hash 489c16b0f3fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

evaluate-diagram scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

evaluate-diagram — 92% identical, 4 lines differ

.claude/skills/evaluate-diagram/SKILL.md · 40 lines

What it actually says

Evaluate Diagram

Evaluate a generated diagram against a human reference using PaperBanana's VLM-as-Judge scoring.

Instructions

$ARGUMENTS[0] is the path to the generated image.
$ARGUMENTS[1] is the path to the human reference image.
Ask the user for:
- Source context: the methodology text (or a file path to read it from). If the user provides a file path, read that file to get the text.
- Figure caption: a description of what the diagram communicates.
Call the MCP tool evaluate_diagram with:
- generated_path: the generated image path
- reference_path: the reference image path
- context: the methodology text content
- caption: the figure caption
Present the evaluation scores to the user. Scores cover 4 dimensions: Faithfulness, Conciseness, Readability, and Aesthetics.

CLI Fallback

If the MCP tool is not available, fall back to the CLI:

paperbanana evaluate --generated <generated-img> --reference <reference-img> --context <context-file> --caption "<caption>"

Example

/evaluate-diagram output.png reference.png

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 40 lines · 0 tokens per session scan A 489c16b0f3fe

Subscribe to this mod's changes

evaluate-diagram is a skill published in the GitHub repository llmsresearch/paperbanana (2,344 stars, last pushed 23d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 311 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Design and UX LLM academic-research arxiv gemini llms mcp

design-expert

Expert-level system design, architecture patterns, scalability, and distributed systems. Use when the user mentions system design, architecture, scalability, distributed systems, or patterns, or when the task involves Architecture Patterns or Design Principles.

personamanagmentlayer/pcl · 47 tokens

pydantic-ai

Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.

davila7/claude-code-templates · 32 tokens

liquid-glass

Apple Liquid Glass design system. Use when building UI with translucent, depth-aware glass morphism following Apple's design language. Provides CSS tokens, component patterns, dark/light mode, and animation specs.

fengshao1227/ccg-workflow · 43 tokens

infographic-creator

An information-graphic creation guide that turns written information into a visual layout using AntV Infographic, a description language for rendering infographics.

antvis/Infographic · 25 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

neuron-structured-output

Design and implement structured output classes for Neuron AI agents using SchemaProperty attributes and validation rules. Use this skill when the user mentions structured output, JSON schema extraction, data validation, output classes, DTOs for AI responses, extracting structured data from LLM, or configuring property…

neuron-core/neuron-ai · 104 tokens

paperbanana: Skill for Claude Code