If you're making research posters for conferences or academic events, this handles the full LaTeX workflow using beamerposter, tikzposter, or baposter. The real value here is the strict emphasis on AI-generated visuals first, then assembling them in LaTeX, which is the right way to build modern posters. It's opinionated about preventing the classic mistakes: text overflow at edges, cramming too many sections into one poster, and tiny unreadable fonts in diagrams. The content overflow rules are especially practical, like limiting A0 posters to 5-6 sections max and 300-800 words total. It pushes you to generate simple graphics with giant text (120pt+) and minimal elements, which actually matches how posters get viewed at conferences from several feet away.

skills.sh installs
2.2K
GitHub stars
56.6K
last updated
Aug 21, 2026

Install

$ npx -y skills add k-dense-ai/scientific-agent-skills --skill latex-posters --agent claude-code

Installs into .claude/skills of the current project.

Files

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.

Choose the poster package

PackageUse whenReviewed target
beamerposterBeamer blocks or institutional Beamer themes fit the projectCTAN 1.13
tikzposterTikZ styling and automatically stacked blocks are usefulCTAN 2.0
baposterA supplied project uses its named, relative-positioned boxesArchived class v2.0, 2011/11/26; upstream site unavailable at review

The three bundled templates were compiled locally with pdfLaTeX (TeX Live 2025) and inspected using Poppler 26.09.0. baposter was tested using the pinned archival source described in references/latex_poster_packages.md. Do not interpret an old stable package version as proof of current tagged-PDF support. Other reference snippets are illustrative building blocks unless explicitly tested; they require the indicated class, packages, actual data, and figure files.

Workflow

Sponsors

Details

Repository
github.com/k-dense-ai/scientific-agent-skills
Categories
Frontend Development, AI & Agent Building, Data Science & ML, Design & UI/UX
First seen
Jun 3, 2026

More from k-dense-ai/scientific-agent-skills

All 137
1rjyo avatarmoshi-best-practicesrjyo/moshi-skillUse when preparing or verifying a host for Moshi remote coding. Trigger this for Easy Pair host setup, SSH or preferably Mosh readiness, non-interactive shell P2.1Kskills.sh installs
2nvidia avatarnemotron-customizenvidia/skillsPlan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or Mega2.1Kskills.sh installs
3enzed avatarr3f-postprocessingenzed/r3f-skillsReact Three Fiber post-processing - @react-three/postprocessing, bloom, DOF, screen effects. Use when adding visual effects, color grading, blur, glow, or creat2.1Kskills.sh installs
4browserbase avatarevent-prospectingbrowserbase/skillsEvent prospecting skill. Takes a conference / event speakers URL, extracts the people, filters their companies against the user's ICP, then deep-researches only2.1Kskills.sh installs
5enzed avatarr3f-materialsenzed/r3f-skillsReact Three Fiber materials - PBR materials, Drei materials, shader materials, material properties. Use when styling meshes, creating custom materials, working 2.1Kskills.sh installs
6enzed avatarr3f-geometryenzed/r3f-skillsReact Three Fiber geometry - built-in shapes, BufferGeometry, instancing with Drei. Use when creating 3D shapes, custom meshes, point clouds, lines, or optimizi2.1Kskills.sh installs