More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Poster Layout: Print-Ready Conference Posters

    1

    Paper figures shrunk into paragraphs of text lose them.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Poster Layout: Print-Ready Conference Posters

    Poster Layout: Print-Ready Conference Posters

    Example session with this skill installed

    Make my poster for the Urban Climate Workshop from the abstract in abstract.md and my paper figures in figures/. The data and the script that made the figures are in data/ and scripts/. I will be standing next to it during the evening poster session.

    • Read your context and instructions
    • Compiled the poster layout

    Your poster is ready: poster/poster.pdf, A0 portrait (841 × 1189 mm) as the abstract specifies. The final build reports no layout problems, and I checked the far view, the 1 m view and each zone close-up.

    How to print: the PDF is already at full size. Print at 100 % and turn off "fit to page", and ask the print shop for A0 exactly.

    • Title: "Bus stops under street trees have surfaces 4.1 °C cooler on summer afternoons"

    Zone 2: each 10 points of canopy cover goes with 0.8 °C cooler surfaces (the scatter plot, with dashed lines for the two groups' means).

    Zone 3: shade matters most between 14:00 and 16:00 (panels (a) and (b) of paper Fig. 1, stacked, with the 14:00–16:00 bars highlighted).

    • Zone 4: a big 0.7 °C for the air-temperature difference, set against 4.1 °C at the surface.

    Figures: I redrew both from data/ at the size they print, using a copy of your plotting code in poster/make_poster_figures.py. The data and the least-squares fit are the same as in your script; only the size, colours and labels changed.

    Numbers: every number on the poster reproduces from your data (50.8 vs 46.7 °C, n = 13 and 14; 0.8 °C per 10 points; 0.7 °C for the air).

    Before you present: the hourly data (4 days) shows a 4.4 °C gap at 15:00, while the 12-day mean in the title is 4.1 °C. The zone 3 caption explains this, but expect the question. A fresh reader who saw only the poster image found the main result within 30 seconds; I fixed four things they flagged. poster/walkthrough.md has a one-minute and a three-minute talk and answers to four likely questions.

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

    About this skill

    What it does

    A poster session is a crowd walking past at one to three metres, deciding in seconds whether to stop. Paper figures shrunk into paragraphs of text lose them. This skill turns your agent into a careful poster designer. Give it your abstract or paper, your figures, and (if you have them) the data and plotting script, and it:

    • Writes the story before the layout: a title that states the main result with its number, and three to six zones whose headlines each make one claim and together summarise the study.
    • Keeps every number traceable: each value on the poster is traced to your figures, results or text, with the same rounding, n and interval. Nothing is invented: no sample size, comparison or next step that isn't in your material.
    • Redraws your figures at printed size: from a copy of your script and your data, at the exact space the build reports for each zone, with poster type sizes and the data each headline is about in one accent colour. Your originals are never touched.
    • Builds a print-ready PDF at the physical size (A0, A1, 36×48 in, 42×56 in or custom), one page, from a short JSON spec.
    • Measures the layout in a real browser engine: text cut off at a zone's edge, content past the page, figures under 150 dpi, figures squeezed by text or leaving their space half empty, half-empty zones, a title over two lines.
    • Looks at it like a visitor: a 4 m preview, a 1 m preview and a close-up of every zone, then a fresh-eyes test where a subagent sees only the poster image and says what the main result is.
    • Prepares the conversation: one-minute and three-minute walkthroughs that follow the zones, likely questions with answers from your material, and a handout link or QR code.

    What's included

    • SKILL.md: the workflow (facts, story, evidence, build, fit figures, measure and look, fresh-eyes test, walkthrough, delivery) and the design rules (grid, reading order, word budgets, type sizes, one accent colour)
    • scripts/build_poster.py: spec to HTML, PDF at physical size, 4 m and 1 m previews, per-zone close-ups and a layout report with the exact space for each figure. Finds Chrome, Chromium, Edge or Brave on macOS, Linux and Windows.
    • The poster style block (in SKILL.md): matplotlib settings for figures printed on a poster (sizes in printed inches, 28 pt text, direct labels, a check for text under 24 pt), pasted into the figure script you keep so it redraws with matplotlib alone
    • references/spec.md: every spec field, layout recipes and what each report line means
    • examples/: a complete synthetic A0 poster (spec plus the script that draws its figures)

    Part of the Aurora Lab research pipeline

    Works entirely on its own. With a research/ folder it reads figures, results, claims and the paper from there and writes to research/poster/. Pairs well with Aurora Lab's Paper Figures for designing figures from data, but needs none of the other skills.

    It lays out and checks posters from material you already have; it does not analyse your data beyond recomputing the numbers it puts on the poster, and it cannot redraw a figure without its data (an image-only figure is used as is, or you are asked for a larger or vector export). The layout is a fixed style: a title band, white zones on a light background on a strict grid, one sans-serif font and one accent colour; it does not import institutional PowerPoint or LaTeX poster templates, and the output is a PDF (and HTML), not an editable .pptx. Rendering needs Chrome, Chromium, Edge or Brave; Firefox and Safari cannot be driven, and without a Chrome-family browser you get the HTML only, with no layout checks. PDF figures must be converted to SVG or PNG first. The layout report measures text and space; legibility inside figures and whether each figure shows its claim are judged by the agent from the previews. Venues differ in size and template rules: check your conference's current poster instructions.

    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+
    Pillow
    Matplotlib
    NumPy
    Chromium-based browser
    Python
    macOS

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    File Scopes

    poster/**
    research/poster/**
    research/figures/**
    research/results/**
    research/paper/**

    Reads the abstract, paper, figures, data and plotting scripts you point it at (with a research/ folder: research/figures/, research/results/, research/claims.md, research/paper/). Writes the spec, redrawn figures, a copy of your plotting script, the HTML, PDF, previews, zone close-ups and walkthrough notes to poster/ (or research/poster/). Runs a Chrome-family browser headless, locally, with a temporary profile, only to print the PDF and measure the layout. Never modifies your figures, data or scripts. No network access; installs nothing without asking, and only into the project's environment.

    Listed29 days ago
    Updated28 days ago

    What's inside

    Frequently Asked Questions

    Your abstract or paper, your figures, and ideally the data and plotting script behind them so it can redraw the figures at poster size. Tell it the size if you know it (A0 portrait if nobody knows, and it says it assumed that).

    Python 3.10+ with Pillow, plus matplotlib and numpy to redraw figures, and Google Chrome, Chromium, Microsoft Edge or Brave. The browser is found automatically on macOS, Linux and Windows, or you can give its path. Without one you get the HTML poster to print from any browser, but no PDF, previews or layout checks.

    No. It redraws figures from a copy of your script with the same data, fit and intervals, changing only size, type, line weight, colour emphasis and labels. Every number on the poster is traced to your material, and it never invents a sample size, comparison or result.

    A0 and A1 in portrait or landscape, 36×48 in, 48×36 in, 42×56 in, or any custom size in mm or inches. The PDF is one page at the physical size: print it at 100 %.

    Yes, through the JSON spec: text, zones, sizes and colours, then rebuild in seconds. It does not produce PowerPoint or LaTeX files.

    Paper Figures designs individual figures from data for a paper. Poster Layout arranges your results into a poster and redraws figures for print at poster size. Each works on its own; they pair well.

    New in Research & Analysis