domains / documents / latex-research-poster / latex-posters

latex-posters

Skill card

combined

The four copies overlap on the core task (beamerposter/tikzposter/baposter, 300-800 words, 2-3 columns, figure integration, and PDF preflight), but each contains material steps or constraints the others lack. K-Dense provides a tested compilation and Poppler inspection workflow plus an optional OpenRouter schematic helper; Vibe-Skills adds explicit typography, color, and standard poster-size guidance; aipoch frames the skill as a writing package with a refusal/recovery contract and hard density constraints; FreedomIntelligence mandates AI-generated visuals with strict prompt limits and overflow-prevention rules. Crowning one copy would hide these real alternatives.

Repositories

RepositoryPath
K-Dense-AI/scientific-agent-skillsskills/latex-posters/SKILL.md
foryourhealth111-pixel/Vibe-Skillsbundled/skills/latex-posters/SKILL.md
aipoch/medical-research-skillsscientific-skills/Academic Writing/latex-posters/SKILL.md
FreedomIntelligence/OpenClaw-Medical-Skillsskills/latex-posters/SKILL.md

Other copies

RoleRepositoryPath
peerK-Dense-AI/scientific-agent-skillsskills/latex-posters/SKILL.md
peerforyourhealth111-pixel/Vibe-Skillsbundled/skills/latex-posters/SKILL.md
peeraipoch/medical-research-skillsscientific-skills/Academic Writing/latex-posters/SKILL.md
peerFreedomIntelligence/OpenClaw-Medical-Skillsskills/latex-posters/SKILL.md

Combined skill

# LaTeX Research Posters

Create a conference-sized PDF from scientific content, editable LaTeX, and verified figures. Use for new posters, paper-to-poster adaptation, institutional templates, and poster compilation or print preflight.

## 1. Establish content and output requirements
- Record exact paper width, height, orientation, venue rules, and printer requirements.
- Choose 1-3 main messages and the results needed to support them.
- Use a starting budget of 300-800 words with 3-5 figures; adjust to audience and space.
- Preserve study design, sample sizes, units, effect sizes, uncertainty, limitations, and data provenance.
- Include relevant citations, contact, and acknowledgments.
- Use actual analysis outputs for plots and original research images for evidence. Do not use an image model to invent numerical charts, microscopy, spectra, or results.

## 2. Choose the poster package
- Use beamerposter when Beamer blocks or institutional Beamer themes fit the project.
- Use tikzposter when TikZ styling and automatically stacked blocks are useful.
- Use baposter when a supplied project uses its named, relative-positioned boxes.
- If the user does not specify a package, default to tikzposter for modern research posters, switch to beamerposter for formal thesis-defense aesthetics, and switch to baposter when content is block-heavy and highly modular.

## 3. Prepare and review figures
- Prefer vector PDF for numerical plots, TikZ for precise diagrams, and suitable PNG/JPEG for photographs or conceptual artwork.
- Convert SVG to PDF before ordinary `\includegraphics`; SVG is not a directly supported pdfLaTeX image format.
- Optional AI schematics can help explain a concept. Generate them only when useful; there is no required AI-image quota.
- Keep titles, citations, numerical values, and QR codes editable in LaTeX or a deterministic plotting tool. Use official logo assets.
- If using AI-generated visuals, enforce strict prompt limits: maximum 3-4 elements per graphic, maximum 10 words total, no complex workflows with 5+ steps, no multi-level nested diagrams, all text giant bold (80pt+ for labels, 120pt+ for key numbers), high contrast only, mandatory 50% white space minimum, thick lines only (5px+ minimum), large icons (200px+ minimum), and one single message per graphic.
- Inspect every figure before assembly: relationships, labels, units, colors, license, and accuracy. Check actual placed size, pixel dimensions, and raster PPI.

## 4. Create the layout
- Copy one of the three template files from `assets/` into the project: `beamerposter_template.tex`, `tikzposter_template.tex`, or `baposter_template.tex`.
- Use 2-3 columns as a starting layout. Keep sufficient page margins and gaps between blocks.
- Figure widths must fit the containing box; `0.85\linewidth` is a reasonable starting point, not a universal maximum.
- Body text around 24-36 pt at final print size is a starting range. Font commands vary with class and scale; verify the actual rendered sizes rather than assuming that `\Large` is always a fixed size.
- Limit content sections to a maximum of 5-6 major blocks for A0 posters to prevent overflow.
- Set safe margins in LaTeX to prevent content from touching page boundaries.

## 5. Compile and inspect the actual PDF
Run these from the poster project directory:

```bash
pdflatex -interaction=nonstopmode -halt-on-error poster.tex
pdflatex -interaction=nonstopmode -halt-on-error poster.tex
pdfinfo poster.pdf
pdffonts poster.pdf
pdfimages -list poster.pdf
pdftoppm -scale-to 2000 -singlefile -png poster.pdf poster-preview
rg -n 'Overfull|Underfull|Warning|undefined' poster.log
```

- Use LuaLaTeX/XeLaTeX if a project needs `fontspec` and installed OpenType fonts; changing engines still requires compilation and visual verification.
- Run BibTeX or Biber only when citations require it.
- Check for overfull hbox warnings and visual overflow at 100% zoom.
- Verify that no text or content is cut off at edges.

## 6. Final quality checklist
- Package choice is explicit.
- Section order is clear.
- Word budget is realistic (300-800 words for A0).
- Figure plan is readable with one message per figure.
- No fake script requirement appears.
- No impossible density request is accepted.
- All figures are verified for accuracy, labels, units, and license.
- PDF compiles without overfull or underfull warnings.
- Visual inspection confirms no content overflow at page boundaries.

## Conflicts
- K-Dense-AI/scientific-agent-skills treats AI schematics as optional and warns against inventing numerical charts, while FreedomIntelligence/OpenClaw-Medical-Skills mandates generating all major visual elements with AI and targets 60-70% AI-generated area.
- K-Dense-AI/scientific-agent-skills and foryourhealth111-pixel/Vibe-Skills give body text around 24-36 pt, while FreedomIntelligence/OpenClaw-Medical-Skills requires 80pt+ labels and 120pt+ key numbers inside AI-generated graphics.
- aipoch/medical-research-skills limits major content blocks to 5-6 and includes a refusal contract, while the other copies do not impose the same hard block limit or refusal format.