More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Paper Figures: Publication-Ready Figures

    1

    Turn results into journal-ready scientific figures that never overstate the data: the right plot for the claim, a colour-blind-safe journal style, and a check before submission.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Paper Figures: Publication-Ready Figures

    Paper Figures: Publication-Ready Figures

    Example session with this skill installed

    Here are my dose-response results for two compounds (research/results/dose_response.json) and the per-condition measurements (research/results/conditions.json). Make Figure 2 for a Nature-family journal, single column.

    • Read your context and instructions
    • Compiled the paper figures

    Figure plan (2 panels, 89 mm wide):

    a Dose-response for compounds A and B: every replicate, mean with 95% CI, four-parameter logistic fit, log dose axis.

    • b Fold change vs control as a dot plot with the mean and 95% CI, n printed under each condition.

    Files written

    • research/figures/fig2.pdf and fig2.png (89 x 55 mm, Okabe-Ito colours, panel labels a and b)
    • research/figures/fig2.md: caption draft, data sources, and how the figure was built

    Checks

    • Fonts: Type 42 embedded, no Type 3 (pass)
    • Every interval is named in the caption; n is shown for every condition
    • Caption headline reworded: "B is more potent" became "B shifts the curve right", because only point estimates of EC50 were provided.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    What it does

    Your agent becomes a careful figure collaborator for scientific papers. Give it results, a data file, or just "we need a Figure 1", and it:

    • Picks the plot that fits the claim: dot plots over bar charts, every interval named (SD, SEM or 95% CI), n shown, accurate axis ranges.
    • Backs every claim with the data: no cherry-picked examples, schematics marked as schematics, equations checked against the code, captions that match the evidence.
    • Applies a journal style with a bundled matplotlib helper: Okabe-Ito colour-blind-safe palette, exact column widths for Nature, Cell, PNAS, Elsevier and IEEE (or any width in mm), embedded Type 42 fonts, PDF and PNG export.
    • Verifies before calling it done, including a font check that catches the Type 3 fonts many journals reject.
    • Writes a caption and spec file next to every figure, so the figure can be rebuilt and the caption reviewed.

    Two ways to work

    • Unguided: hand over results and get a proposed figure plan, then the figure.
    • Guided: you specify the panels and it builds and iterates with you.

    What's included

    • SKILL.md: the full workflow, from choosing the plot to the final check
    • scripts/figure_style.py: style helper (Python 3.10+, matplotlib only)
    • examples/make_example_figure.py: a complete two-panel example (dose-response with intervals and fit, plus a dot plot with n)
    • references/matplotlib-traps.md: layout, text and export pitfalls and their fixes

    Part of the Aurora Lab research pipeline

    Works entirely on its own. If you keep results in a research/ folder (results/*.json), it reads them and writes figures to research/figures/, the same convention the other Aurora Lab research skills use. No skill calls another.

    Rendering uses Python and matplotlib. With other plotting tools the design and review guidance still applies, but the bundled style helper does not. It plots and documents the results you provide; it does not choose or run your statistical analysis. Built-in column widths cover Nature-family, Cell Press, PNAS, Elsevier and IEEE journals; confirm against the current author guidelines before submitting.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 28 days ago

    Requires

    Python 3.10+
    matplotlib
    numpy (bundled example only)
    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    File Scopes

    research/results/**
    research/figures/**

    Reads the results you point it to (default research/results/*.json). Writes figures and their caption/spec files only to the folder you choose (default research/figures/). Runs local Python to render; no network access, no installs.

    Listed1 month ago
    Updated28 days ago

    What's inside

    Frequently Asked Questions

    Any agent that loads SKILL.md skills, including Claude Code, Codex CLI, Cursor and Gemini CLI. The agent needs to be able to run Python locally for the rendering step.

    Python 3.10+ with matplotlib, plus numpy for the bundled example. Nothing else, and no network access.

    Partly. Export size and the font check (it catches Type 3 fonts many journals reject) are automatic through the bundled helper. The integrity checks (example selection, named intervals, axis ranges, schematics, caption claims) are a review procedure your agent follows and reports on, not a linter.

    No. It plots what you give it and names every interval. If no interval is provided, the figure and caption say so instead of inventing one.

    No. It works on its own. If you keep a research/ folder, it reads results/*.json and writes to research/figures/, which the other Aurora Lab research skills also use.

    Single and double column widths for Nature-family, Cell Press, PNAS, Elsevier and IEEE journals, or any width in millimetres. Check your journal's current guidelines before final submission.

    New in Research & Analysis