figure-review

figure-review is a skill for Claude Code from dgilford/ai-science-toolkit. It costs 144 tokens per session (2,040 once invoked), scanned A, original, MIT.

A review process for checking whether a scientific figure is ready for publication. It examines items such as color choices, uncertainty, axis labels, captions, and whether the figure supports its claims.

In plain words
What is it for?
Use it to review a figure, one panel of a multi-panel figure, its plotting code, caption, or surrounding claims, while marking missing inputs that cannot be assessed.
Why use it?
It catches presentation and evidence problems that can make a research figure misleading or hard to interpret.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the ai-science-toolkit plugin — 21 skills, 4 agents shipped together

Good fit Use it to review a figure, one panel of a multi-panel figure, its plotting code, caption, or surrounding claims, while marking missing inputs that cannot be assessed.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add dgilford/ai-science-toolkit
Claude Code
/plugin install ai-science-toolkit

Made for: Claude Code.

Or install ai-science-toolkit, the plugin that ships this one along with the rest of its 21 skills, 4 agents.

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.

agentmods badge for figure-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/dgilford/ai-science-toolkit/figure-review/github.svg)](https://agentmods.dev/skills/dgilford/ai-science-toolkit/figure-review)
Your own site
<a href="https://agentmods.dev/skills/dgilford/ai-science-toolkit/figure-review"><img src="https://agentmods.dev/badge/skills/dgilford/ai-science-toolkit/figure-review/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.

agentmods 80×15 button for figure-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/dgilford/ai-science-toolkit/figure-review"><img src="https://agentmods.dev/badge/skills/dgilford/ai-science-toolkit/figure-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 144 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,040 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00144 $0.02040
Opus 5 $0.00072 $0.01020
Sonnet 5 $0.00029 $0.00408
Haiku 4.5 $0.00014 $0.00204

Measured 10d ago against content hash 82e22929bc43, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

figure-review 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.

skills/figure-review/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Colorblind reference

D="${CLAUDE_PLUGIN_ROOT:+$CLAUDE_PLUGIN_ROOT/skills/figure-review}"; D="${D:-$HOME/.claude/skills/figure-review}"; cat "$D/COLORBLIND.md" 2>/dev/null || echo "(colorblind guide not found)"

House style

D="${CLAUDE_PLUGIN_ROOT:+$CLAUDE_PLUGIN_ROOT/skills/figure-review}"; D="${D:-$HOME/.claude/skills/figure-review}"; cat "$D/CC-STYLE.md" 2>/dev/null || echo "(no house style configured — criterion 6 skipped)"

Inputs

Accept any subset of: figure image, plotting code, caption, surrounding text claim. Mark cant-assess for any criterion that requires input not provided.

Scope — establish this before applying any criterion

Determine each of the following from the inputs.

Standalone figure, or one panel of a composite? Look for siblings before deciding — list the directory, and if plotting code is an input, check whether one script saves several panels. Signals: a panel-style filename (fig2C.pdf, Fig_3B.pdf); a sibling differing by one letter. A panel delegates its legend and symbol definitions to the composite; do not flag those. It does not reliably delegate n or data source — a composite caption routinely covers several panels without mapping which is which — so keep checking them. When the composite is not itself an input, mark delegated items cant-assess; never pass them silently.

Draft, or published? Published means post-peer-review: apparent defects are far more likely to be considered choices, journal requirements, or context carried by the caption. For a published figure, raise concerns as by-design? rather than flag.

Deliberate-choice discipline

An author's considered tradeoff is not a defect. Before flagging, ask whether a competent author would plausibly have chosen this on purpose — journal or house constraints, panel economy, or fidelity to a figure being reproduced. If so, use by-design? and name why it might be intentional, so the author can confirm or overrule in one line.

Read the full file on GitHub · 116 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 10d ago First seen · 116 lines · 144 tokens per session scan A 82e22929bc43

Subscribe to this mod's changes

figure-review is a skill published in the GitHub repository dgilford/ai-science-toolkit (62 stars, last pushed 21d ago), licensed MIT. It adds 144 tokens to every session and 2,040 once invoked, about $0.0007 per session on Opus 5. 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.

Related

Other skills, from other repositories

thesis-figure-skill

An academic-diagram skill for creating research-paper figures as TikZ/LaTeX code or draw.io XML. TikZ is code that embeds precisely into LaTeX papers, while draw.io XML creates diagrams editable in the draw.io app.

0xE1337/thesis-figure-skill · 107 tokens

metforge-model-diagnose

Diagnose atmospheric-model and dynamical-core experiments. Use for idealized tests, balanced flow, hydrostatic rest, density currents, advection, gravity/acoustic waves, mountain waves, baroclinic instability, conservation and budget closure, error growth, convergence, timestep/resolution/domain/MPI sensitivity…

yuanruichen/MetForge · 135 tokens

metforge-analysis

Perform reproducible atmospheric-science calculations and statistical diagnostics. Use when the agent needs to calculate established or custom climate indices, derive meteorological variables, compute trends, detrend or filter time series, perform EOF/PCA, regression, correlation, composites, bootstrap or significance…

yuanruichen/MetForge · 138 tokens

metforge-data

Acquire and prepare atmospheric, climate, and Earth-system datasets reproducibly. Use when the agent needs to find an authoritative dataset, choose among ERA5/CMIP/GPM/MERRA-2/NOAA or similar products, download or subset NetCDF/GRIB/Zarr data, write CDS/Earthdata/ESGF/OPeNDAP acquisition code, inspect coordinates and…

yuanruichen/MetForge · 119 tokens

metforge-figure

Design, create, revise, and audit atmospheric-science figures. Use for maps, map differences, vertical sections, Hovmöller diagrams, profiles, spectra, budgets, convergence plots, conservation/error-growth diagnostics, ensemble comparisons, and publication multi-panel figures from NetCDF/xarray or tabular data. Also…

yuanruichen/MetForge · 121 tokens

omh-apple-design

This is a Hermes-native apple-design workflow skill.

rlaope/oh-my-hermes · 73 tokens