Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add QuantumBFS/sci-brain --skill how-to-review-figuregit clone --depth 1 https://github.com/QuantumBFS/sci-brainWrote 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.
[](https://agentmods.dev/skills/quantumbfs/sci-brain/how-to-review-figure)<a href="https://agentmods.dev/skills/quantumbfs/sci-brain/how-to-review-figure"><img src="https://agentmods.dev/badge/skills/quantumbfs/sci-brain/how-to-review-figure/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.
<a href="https://agentmods.dev/skills/quantumbfs/sci-brain/how-to-review-figure"><img src="https://agentmods.dev/badge/skills/quantumbfs/sci-brain/how-to-review-figure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 34 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00031 | $0.02475 |
| Opus 5.5 | $0.00012 | $0.00990 |
| Sonnet 5.5 | $0.00006 | $0.00495 |
| Haiku 4.5 | $0.00003 | $0.00248 |
Grade A, and why
how-to-review-figure 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Installed resources
Keep the working directory at the user's project. Resolve this loaded SKILL.md
with Path(path).resolve() before locating resources; follow symlinks. Bare
helpers/, references/, and template paths are relative to that real skill
directory. A path written as skills/<name>/... means the installed <name>
skill's directory from the agent's skill catalog, not a path in the user's project.
Locate each dependency by its public skill name; copied skills need not be siblings.
If a dependency is absent, report the missing skill and install it before that step.
Shared writing files are bundled in how-to-write-ideas-report/references/.
Before running the examples, set REVIEW_FIGURE_DIR to the absolute directory of how-to-review-figure. Quote these variables as shown.
Figure Taste
Run a structured visual-design review over one or more figures and print a scorecard. The skill renders the figure to a raster so it can see it, reads the source (matplotlib .py, Typst .typ, SVG) so suggestions can name the exact line or parameter to change, scores it against an 18-rule rubric, and delivers severity-ranked findings with concrete fixes.
Scope note. This judges how a figure looks — the artifact itself. It is not review-paper, which checks whether figures are referenced and discussed in the manuscript (orphan figures, undiscussed features, caption sufficiency). It is not write-paper, which authors figures figures-first. Use how-to-review-figure when a figure already exists and the user wants its visual quality assessed. For the why behind a plotting convention, consult write-paper's Figure Rulebook rather than restating it here.
The full rubric — each rule's "good looks like" and "flag when" — lives in skills/how-to-review-figure/checklist.md.
Operating principle
Source-aware, report-only, terminal-first.
- Source-aware — always look at a rendered raster before scoring (never judge a figure you have not seen); when source exists, read it too so a fix can cite a line or parameter.
- Report-only — never edit the figure or its source. Suggest concrete changes; the user applies them.
- Terminal-first — print the scorecard to the chat by default. Write a file only when the user asks.
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.
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.
- 1mo ago Changed · +14 lines 939bb5d13fea
- 1mo ago First seen · 147 lines · 31 tokens per session scan A 87ad63cc9f33
how-to-review-figure is a skill published in the GitHub repository QuantumBFS/sci-brain (101 stars, last pushed 23d ago), licensed MIT. It adds 31 tokens to every session and 2,475 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
scientific-schematics
Generates scientific diagram drafts using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.7 Flash for quality review. Refines when the review requests improvement, with at most two generations. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex…
paper-poster-html
A workflow for building an academic conference poster as one HTML/CSS file and printing it to a PDF at an exact page size. It uses the paper’s real figures and checks layout details before review.
paperFig
Design, implement, revise, and validate publication-quality scientific figures from references, existing plotting code, and real project data. Trace every figure to source code and inputs; deconstruct reference figures; plan the scientific story and multi-panel structure; build complex model architecture and…
latex-posters
Use when creating or revising LaTeX research posters with beamerposter, tikzposter, or baposter, including poster layout, typography, color, print sizing, figure placement, QR codes, compilation, and print-ready PDF checks.
figure-composer
Compose a publication-grade multi-panel scientific figure from a claim, dataset, or draft result. Use when the task needs panel planning, consistent figure layout, figure review, or final figure assembly.
schematics
Creates or refines publication-quality technical diagrams with the native generateimage tool (Nano Banana Pro through Ace or a Gemini key, GPT Image 2 through an OpenAI key), method and architecture overviews, pipelines, CONSORT and PRISMA flows, experimental workflows, biological pathways, circuits and conceptual…