scientific-slides
Skill3 starsChanged 8 months agoMITView on GitHub
Build and revise computer science research slides for conference talks, paper presentations, defenses, group meetings, demos, and project updates. Use when turning a paper, benchmark, experiment, system design, or research plan into clear slides with strong structure, visual hierarchy, and timing discipline.
17 other projects use a version of this.
Adopted by
Most recently taken up by
- BrightGold70/skillstheir own version, first seen Nov 8, 2026
- K-Dense-AI/claude-scientific-writertheir own version, first seen Nov 7, 2026
- MarieLynneBlock/arcanum-artifextheir own version, first seen Nov 1, 2026
- erafat/skillstheir own version, first seen Oct 15, 2026
- patoangolano/bio-stacktheir own version, first seen Oct 15, 2026
- Luooops/skillstheir own version, first seen Oct 13, 2026
Used with
Projects with it also use generate-image and pptx.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
GitHubSkillgenerate-image
Generate images using AI. Use when asked to generate, create, or make images, textures, icons, sprites, artwork, visual assets, or mockups. Supports OpenAI (gpt-image-2) and Google Gemini (Nano Banana). Requires an API key for the chosen provider.
Also in 3 projects that use this
AnthropicSkillpptx
Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.
Also in 3 projects that use this
Other versions17 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 17
- K-Dense-AI/claude-scientific-writer★ 2.6ksame name
- wu-yc/LabClaw★ 1.1ksame name
- LeonChaoX/qinyan-academic-skills★ 910same name
- jaechang-hits/SciAgent-Skills★ 386same name
- qinyan-ai/qinyan-academic-skills★ 80same name
- ZanderRuss/obsidian-claude★ 19same name
- erafat/skills★ 17same name
- echoleesong/claude-skills-plugin★ 4same name
- MarieLynneBlock/arcanum-artifex★ 4same name
- Oceanjackson1/Claude-Skill★ 2same name
7 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository43 other files it gives its agents.
- agent-codingSkill
- benchmark-designSkill
- citation-managementSkill
- code-reproductionSkill
- code-to-paperSkill
- daskSkill
- experiment-trackingSkill
- exploratory-data-analysisSkill
- get-available-resourcesSkill
- github-release-prepSkill
- latex-postersSkill
- literature-reviewSkill
- markdown-mermaid-writingSkill
- markitdownSkill
- matplotlibSkill
- modalSkill
- networkxSkill
- paper-to-codeSkill
- peer-reviewSkill
- plotlySkill
- polarsSkill
- pytorch-lightningSkill
- pyzoteroSkill
- repo-cleanupSkill
- research-planningSkill
- reviewer-responseSkill
- scholar-evaluationSkill
- scientific-critical-thinkingSkill
- scientific-schematicsSkill
- scientific-visualizationSkill
- scientific-writingSkill
- scikit-learnSkill
- seabornSkill
- shapSkill
- stable-baselines3Skill
- statistical-analysisSkill
- statsmodelsSkill
- sympySkill
- torch-geometricSkill
- transformersSkill
- umap-learnSkill
- vaexSkill
- venue-templatesSkill
The file
We split this skill into the rules it gives an agent
11 rules. 0 are common, 8 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 17 edited versions we read keep these.
8
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill for CS research presentations.
- Very specific: line 19
Read references/talk_types_guide.md or references/presentation_structure.md when structure needs help.
- Distinctive: line 32
Do not mirror the paper section-by-section if that hurts comprehension.
- Distinctive: line 36
Keep one main idea per slide.
- Distinctive: line 37
Prefer diagrams, tables, and concise bullets over paragraph text.
- Distinctive: line 40
Use animations sparingly and only when they reveal structure or sequence.
- Very specific: line 58
Read references/data_visualization_slides.md and references/slide_design_principles.md when revising cluttered result slides.
- Very specific: line 77
Only use scripts/generate_slide_image.py or scripts/generate_slide_image_ai.py if the user explicitly wants synthetic illustration support.
- Distinctive: line 81
Before finalizing a deck, check:
- Distinctive: line 83
every result slide has an interpretable takeaway
- Distinctive: line 90
When the user asks for slide help without specifying format, return:
“Common” is measured: kept by at least 6 in 10 of the 17 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Scientific Slides
Use this skill for CS research presentations. Optimize for technical clarity, narrative flow, and audience comprehension under time pressure.
Start With Talk Constraints
Clarify or infer:
- talk type: conference talk, paper reading, defense, seminar, lab update, demo, tutorial
- audience: subfield experts, broad CS audience, students, industry engineers, reviewers
- duration and Q&A budget
- medium: Beamer, PowerPoint, Markdown-to-slides, or another deck workflow
- whether the deck supports a paper, a project demo, a proposal, or a benchmark report
Read references/talk_types_guide.md or references/presentation_structure.md when structure needs help.
Narrative for CS Talks
Most strong computing talks follow this sequence:
- problem and why it matters
- why the problem is hard
- core idea, architecture, or system design
- how the method / system / study works
- evaluation setup
- key results and what they mean
- limitations, takeaways, and next steps
Do not mirror the paper section-by-section if that hurts comprehension.
Slide-Level Rules
- Keep one main idea per slide.
- Prefer diagrams, tables, and concise bullets over paragraph text.
- Make architecture, pipeline, benchmark setup, or experimental protocol visually explicit.
- Highlight the comparison that matters; do not dump full result tables when a distilled view is enough.
- Use animations sparingly and only when they reveal structure or sequence.
For result slides, answer three questions fast:
- what is being compared
- what the main result is
- why the result matters
Visual Content That Matters in CS
Prioritize visuals that clarify technical structure:
- model or system architecture
- data / control flow
- training or inference pipeline
- benchmark composition and evaluation protocol
- ablation summaries
- failure analysis or qualitative examples
- latency / memory / throughput tradeoffs
Read references/data_visualization_slides.md and references/slide_design_principles.md when revising cluttered result slides.
Use Local Assets and Scripts
For LaTeX/Beamer work:
assets/beamer_template_conference.texassets/beamer_template_defense.texassets/beamer_template_seminar.texreferences/beamer_guide.md
For PowerPoint-style work:
assets/powerpoint_design_guide.mdassets/timing_guidelines.md
For production and review:
scripts/slides_to_pdf.pyscripts/validate_presentation.pyscripts/pdf_to_images.py
Only use scripts/generate_slide_image.py or scripts/generate_slide_image_ai.py if the user explicitly wants synthetic illustration support. Do not default to decorative AI images.
Review Checklist
Before finalizing a deck, check:
- the first 3 slides establish the problem and context fast
- every result slide has an interpretable takeaway
- fonts and figure labels remain readable at presentation distance
- timing is realistic for the allotted slot
- backup slides exist for details that may come up in Q&A
Default Deliverables
When the user asks for slide help without specifying format, return:
- a talk outline
- slide-by-slide message plan
- recommendations for figures and tables
- timing notes
- revision priorities for clarity
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

