Use this skill whenever the user wants to create or improve a presentation for an academic context — conference papers, seminar talks, thesis defenses, grant briefings, lab meetings, invited lectures, or any presentation where the audience will evaluate reasoning and evidence. Triggers include: 'conference talk', 'seminar slides', 'thesis defense', 'research presentation', 'academic deck', 'academic presentation'. Also triggers when the user asks to 'make slides' in combination with academic content (e.g., 'make slides for my paper on X', 'create a presentation for my dissertation defense', 'build a deck for my grant proposal'). This skill governs CONTENT and STRUCTURE decisions. For the technical work of creating or editing the .pptx file itself, also read the pptx SKILL.md.
npx skills add https://github.com/Gabberflast/academic-pptx-skill --skill academic-pptx
This skill has two layers:
Always read both before writing any code or creating any files.
| Task | Guide |
|------|-------|
| Content planning, argument structure, slide-by-slide rules | content_guidelines.md |
| Per-slide-type patterns (title, methods, results, etc.) | slide_patterns.md |
| Technical creation from scratch | PPTX skill → pptxgenjs.md |
| Technical editing of an existing file | PPTX skill → editing.md |
Before planning a single slide, determine which mode applies.
Use for: conference papers, seminar talks, thesis defenses, dissertation chapters, grant briefings, internal lab presentations, policy briefings, consulting-style research deliverables.
Priority order: argument structure → data → layout → aesthetics.
Follow content_guidelines.md in full.
Use for: public engagement talks, science communication to non-specialist audiences, funding pitches to lay panels, event keynotes.
Follow the PPTX skill's design-forward guidelines. Argument structure still matters, but visual storytelling and emotional engagement take priority.
Default to Structured Argument. If the user mentions a paper, a study, a dataset, a thesis, a grant, or a conference, they almost certainly want structured argument mode.
Produce a slide-by-slide outline (title, action title, exhibit type) and confirm with the user if the deck is more than 10 slides or if the content is complex. Do not start building until the outline is agreed.
Use the ghost deck test during planning: read only the proposed action titles in sequence. They must tell the complete argument. If they don't, fix the outline before building.
Academic presentations use communication-first design. These rules override the PPTX skill's design-forward defaults.
1F4E79), mid-blue accent (2E75B6), white or off-white background.| Element | Size | Weight |
|---------|------|--------|
| Action title | 24–28 pt | Bold |
| Section header | 20–22 pt | Bold |
| Body bullets | 20 pt | Regular |
| Chart labels / annotations | 16–18 pt | Regular |
| Source citations on slides | 12–14 pt | Regular, muted color |
Single font face. Use size and weight for hierarchy — never multiple typefaces.
Follow the PPTX skill's QA procedure in full, including:
markitdownAdditionally, run the academic-specific checks:
Academic QA checklist:
□ Every content slide has an action title (complete sentence stating the takeaway)
□ Ghost deck test passes (action titles alone tell the full argument)
□ One exhibit per results slide; each exhibit has a "so what" annotation
□ Every borrowed figure or data point has an in-slide citation
□ A References slide exists at the end
□ Conclusions slide is the last non-appendix slide (not "Thank You" or a blank)
□ Contact information and/or QR code/link on the final slide
□ Font sizes are readable from the back of a room (≥ 20 pt body text)
□ No decorative elements that don't carry content
□ Section dividers or breadcrumb bar present for decks > 15 slides
Action titles, not topic labels. Every slide title is a complete sentence stating the takeaway. Reading titles alone should tell the whole argument (ghost deck test).
One argument, made well. Don't present your whole paper. Pick the claim that can be made convincingly in the allotted time. Everything else goes in the appendix.
One insight per slide. One exhibit per results slide. Highlight the key finding directly on the chart — don't make the audience hunt for it.
Slides support speech; they don't replace it. Body text is for orientation, not information transfer. The presenter carries the argument; the slide carries the evidence.
Cite everything borrowed. Academic integrity applies to slides. In-text citations on the slide, full references on the References slide.
End on conclusions. The conclusions slide stays on screen during Q&A. Never end on "Thank You" or a blank slide.
Same as PPTX skill:
pip install "markitdown[pptx]" — text extractionnpm install -g pptxgenjs — creating from scratchsoffice) — PDF conversionpdftoppm) — PDF to imagesSearches across your Notion workspace, synthesizes findings from multiple pages, and creates comprehensive research documentation saved as new Notion pages. Turns scattered information into structured reports with proper citations and actionable insights.
Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management. Includes SMART goal frameworks, evidence-based interventions with minimal text citations, regulatory compliance (HIPAA), and professional formatting. Prioritizes brevity and clinical actionability.
Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management. Includes SMART goal frameworks, evidence-based interventions with minimal text citations, regulatory compliance (HIPAA), and professional formatting. Prioritizes brevity and clinical actionability.
Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management. Includes SMART goal frameworks, evidence-based interventions with minimal text citations, regulatory compliance (HIPAA), and professional formatting. Prioritizes brevity and clinical actionability.
【强制】所有技术文档查询必须使用本技能,禁止在主对话中直接使用 mcp__context7-mcp 工具。触发关键词:查询/学习/了解某个库或框架的文档、API用法、配置参数、错误解释、版本差异、代码示例、最佳实践。本技能通过 context7-researcher agent 执行查询,避免大量文档内容污染主对话上下文,保持 token 效率。
Generates rich technical documentation pages with dark-mode Mermaid diagrams, source code citations, and first-principles depth. Use when writing documentation, generating wiki pages, creating technical deep-dives, or documenting specific components or systems.
Maximum-saturation research orchestration: ALWAYS proposes the final materials first (PDF+DOCX default), then parallel explore+librarian swarms across codebase, web, official docs, and OSS repos — max-roster teammode when the harness has it — with live journaling, a recursive EXPAND loop driven by leads workers return in message text, empirical verification by running code, and a cited synthesis with charts/Mermaid/assets behind a mandatory visual-QA gate. ACTIVATES ONLY on an explicit user demand for research — the word 'ulw-research' ('/ulw-research', '$ulw-research'), any 'ulw' research wording, 'ultradebate' or 'hyperdebate' research requests, or an explicit request for research / deep research / an ultra-precise investigation, in any language. Never self-activates for ordinary questions, debugging, or implementation context-gathering. While active it overrides exploration-bounding defaults: exhaustive coverage is the goal.
"Solve competition math problems (IMO, Putnam, USAMO, AIME) with adversarial verification that catches the errors self-verification misses. Activates when asked to 'solve this IMO problem', 'prove this olympiad inequality', 'verify this competition proof', 'find a counterexample', 'is this proof correct', or for any problem with 'IMO', 'Putnam', 'USAMO', 'olympiad', or 'competition math' in it. Uses pure reasoning (no tools) — then a fresh-context adversarial verifier attacks the proof using specific failure patterns, not generic 'check logic'. Outputs calibrated confidence — will say 'no confident solution' rather than bluff. If LaTeX is available, produces a clean PDF after verification passes."
Take gabberflast/academic-pptx from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference pip, npm.
Without those the skill loads but fails at the first command.