Agent skill
academic-slides
Use this skill for creating or refining an academic slide deck and the talk built around it: structuring a conference talk, thesis defense, lab meeting, or paper-to-slides deck; deciding the narrative arc and slide breakdown; improving slide design and visual hierarchy; planning rehearsal, timing, Q&A, and backup slides; or generating the .pptx. Reach for it when the user is shaping the presentation itself. Do not use for writing the paper, producing standalone speaker notes/scripts/transcripts, making posters, creating isolated figures/charts outside a slide deck, or building non-academic presentations.
Install this agent skill to your Project
npx add-skill https://github.com/EvoScientist/EvoSkills/tree/main/skills/academic-slides
Metadata
Additional technical details for this skill
- tags
-
core writing presentation academic-writing
- author
- EvoScientist
- version
- 1.0.0
SKILL.md
Academic Slides
A structured approach to creating academic presentation slides and preparing research talks. Covers narrative structure, slide design, visual hierarchy, delivery technique, and Q&A preparation.
When to Use This Skill
- User wants to create presentation slides for a research talk
- User asks about structuring an academic presentation
- User needs to prepare for a conference talk, thesis defense, or lab meeting
- User wants to design a slide deck from a paper or research project
- User mentions "slides", "presentation", "talk", "defense", "poster talk"
Before You Start: Three Questions
Before designing any slides, answer these questions clearly:
-
What works are you presenting? They must share a coherent research direction. If presenting multiple works, they should form a narrative arc — not a disconnected list.
-
What problems do these works solve in that direction? Each work should map to a specific problem. If you cannot articulate the problem in one sentence, you are not ready to present.
-
How do you use related work to naturally introduce these problems? Related work is not citation duty. It builds the motivation for YOUR problem. Each related work you mention should advance the audience toward understanding why your approach is needed.
Core Workflow
Step 1: Define scope and audience
Step 2: Draft narrative arc (outline)
Step 3: Design slide structure (section breakdown)
Step 4: Create individual slides (one idea per slide)
Step 5: Add visual elements (figures, diagrams, animations)
Step 6: Rehearse and time
Step 7: Prepare backup / Q&A slides
Step 1: Define Scope and Audience
| Audience | Adjust |
|---|---|
| Domain experts | Skip basics, go deep on method and results |
| Broad CS / engineering | Explain task context, moderate technical depth |
| Interdisciplinary | Start from the application, minimize jargon |
| Industry | Lead with impact and demo, light on theory |
Rule of thumb: Duration in minutes = approximate slide count. A 20-minute talk needs about 20 slides.
Step 2: Draft Narrative Arc
Use the outline template at assets/talk-outline-template.md to plan your talk before making any slides. The outline forces you to articulate your key takeaway and narrative arc.
Step 3: Design Slide Structure
Break your outline into sections with claim-style headers. See talk-structure.md for two complete talk structures and section-by-section guidance.
Step 4: Create Individual Slides
One idea per slide. Follow the 10 design rules in slide-design.md for visual hierarchy and layout.
Step 5: Build the .pptx File
Use slide-creation.md for practical .pptx creation — color palettes, layout code, charts, tables, figures, and QA workflow.
Step 6: Rehearse and Time
See references/delivery-and-qa.md for the rehearsal protocol, delivery principles, and Q&A preparation.
Step 7: Prepare Backup Slides
Backup slides go after your "Thank You" slide. They are not part of the talk — they are your safety net for Q&A:
- Full quantitative comparison table
- Failure cases (shows honesty and preparation)
- Additional ablations or analysis
- Slides addressing anticipated tough questions
Artifact Sources from Other Skills
If you used other EvoSkills earlier in the pipeline, pull these artifacts directly:
| Source Skill | Artifact | Use In Slides |
|---|---|---|
paper-planning |
Story summary (task → challenge → insight) | Motivation slides |
paper-planning |
Pipeline figure sketch | Method overview slide |
paper-planning |
Experiment plan | Results structure |
paper-writing |
Finalized figures and tables | Method + results slides |
paper-review |
Anticipated reviewer concerns | Backup Q&A slides |
See slide-creation.md for detailed layout patterns using each artifact.
Counterintuitive Presentation Rules
For the 10 design rules (one idea per slide, claim-style titles, max 6 elements, etc.), see slide-design.md. The rules below are higher-level mindset shifts.
1. Your slides are not your paper
A talk is an advertisement, not a lecture. Your goal is to make the audience interested enough to read the paper. Cut 80% of your paper's content. If someone can reconstruct your paper from your slides alone, your slides have too much.
2. Reading and listening compete
Text-heavy slides force the audience to choose between reading your slides and listening to you. They will read — and stop hearing you. When you put text on a slide, you are choosing to be ignored.
3. Enthusiasm > polish
A passionate speaker with rough slides beats a bored speaker with beautiful slides. The audience remembers your energy and clarity, not your color scheme. If you only have time to improve one thing, rehearse more — don't redesign slides.
4. Related work is not citation duty
Use related work to BUILD your problem motivation, not to show you have read papers. Each related work slide should advance the narrative: "This approach solved X, but Y remains open — which is exactly what we address."
Reference Navigation
| Topic | Reference File | When to Use |
|---|---|---|
| Talk structures | talk-structure.md | Organizing the narrative arc |
| Slide design | slide-design.md | Visual design and layout rules |
| Slide creation | slide-creation.md | Building .pptx files with code |
| Delivery and Q&A | delivery-and-qa.md | Rehearsal, timing, Q&A preparation |
| Talk outline template | talk-outline-template.md | Starting a new presentation |
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
paper-writing
Guides writing academic papers section by section using an 11-step workflow with LaTeX templates and counterintuitive writing tactics. Covers Abstract, Introduction, Method, Experiments, Related Work, Conclusion, and Supplementary. Use when: user asks to write or draft a paper section, needs LaTeX templates, wants to improve academic writing quality, optimize novelty framing, or mentions 'write introduction', 'draft method', 'paper writing'. Do NOT use for pre-submission review (use paper-review), experiment execution (use experiment-pipeline), or paper planning/story design (use paper-planning).
evo-memory
Manages persistent research memory across ideation and experimentation cycles. Maintains two stores: Ideation Memory M_I (feasible/unsuccessful directions) and Experimentation Memory M_E (reusable strategies for data processing, model training, architecture, debugging). Three evolution mechanisms: IDE (after idea-tournament), IVE (after experiment failure — classifies failures as implementation vs fundamental), ESE (after experiment success — extracts reusable strategies). Use when: updating memory after completing idea tournaments or experiment pipelines, classifying why a method failed (implementation vs fundamental failure), starting a new research cycle needing prior knowledge, user mentions 'update memory', 'classify failure', 'what worked before', 'research history', 'evolution'. Do NOT use for running experiments (use experiment-pipeline), debugging experiment code (use experiment-craft), or generating ideas (use idea-tournament).
paper-navigator
End-to-end academic paper workflow: disambiguate queries, discover papers (search, citation traversal, recommendations, arXiv monitoring, trending, GitHub search), evaluate (TLDR, citations, code, SOTA), read with structured analysis (3-level strategy), and organize into literature maps or reports. Use when: finding papers, reading a paper, related work, literature survey, citation analysis, research trends, SOTA results, datasets, or literature reports. Do NOT use for writing a literature review section (use paper-writing), comparing research ideas (use idea-tournament), or planning paper structure (use paper-planning).
paper-review
Guides self-review of YOUR OWN academic paper before submission with adversarial stress-testing. Core method: 5-aspect checklist (contribution sufficiency, writing clarity, results quality, testing completeness, method design), counterintuitive protocol (reject-first simulation, delete unsupported claims, score trust, promote limitations, attack novelty), reverse-outlining, and figure/table quality checks. Use when: user wants to self-review or self-check their own paper draft before submission, stress-test their claims, prepare for reviewer criticism, or mentions 'self-review', 'check my draft', 'is my paper ready'. Do NOT use for writing a peer review of someone else's paper, and do NOT use after receiving actual reviews (use paper-rebuttal instead).
experiment-craft
Use this skill when the user wants to debug, diagnose, or systematically iterate on an experiment that already exists, or when they need a structured experiment log for tracking runs, hypotheses, failures, results, and next steps during active research. Apply it to underperforming methods, training that will not converge, regressions after a change, inconsistent results across datasets, aimless experimentation without progress, and questions like 'why doesn't this work?', 'no progress after many attempts', or 'how should I investigate this failure?'. Also use it for setting up practical experiment logging/record-keeping that supports debugging and iteration. Do not use it for designing a brand-new experiment pipeline or full experiment program (use experiment-pipeline), generating research ideas, fixing isolated coding/syntax errors, or writing retrospective summaries into research memory/notes/knowledge bases.
experiment-pipeline
Guides structured 4-stage experiment execution with attempt budgets and gate conditions: Stage 1 initial implementation (reproduce baseline), Stage 2 hyperparameter tuning, Stage 3 proposed method validation, Stage 4 ablation study. Integrates with evo-memory (load prior strategies, trigger IVE/ESE) and experiment-craft (5-step diagnostic on failure). Use when: user has a planned experiment, needs to reproduce baselines, organize experiment workflow, or systematically validate a method. Do NOT use for debugging a specific experiment failure (use experiment-craft) or designing which experiments to run (use paper-planning).
Didn't find tool you were looking for?