present-paper

Name: present-paper
Author: Aperivue

41installs53forks

How to install present-paper?

aperivue/medsci-skills/present-paper

$npx -y skills add Aperivue/medsci-skills --skill present-paper

Installs into the current project.

Summary

Academic presentation preparation — paper-driven (journal club, grand rounds, seminar) and lecture/teaching decks (course material, workshop slides, conference talks). Analyzes source material, finds supporting references, drafts audience-adapted speaker scripts, generates or aug

Files · 1

View on GitHub

SKILL.md

1	# Present-Paper Skill
2
3	## Purpose
4
5	Prepare a polished academic presentation from a research paper. The skill walks through a 5-phase
6	pipeline: paper analysis, supporting research, script writing, slide note injection, and Q&A
7	preparation.
8
9	Use it when:
10
11	- preparing a journal club or seminar presentation
12	- presenting a paper for a graduate course
13	- preparing grand rounds or conference talks based on a published paper
14	- building speaker notes for an existing slide deck
15
16	---
17
18	## Communication Rules
19
20	- Communicate with the user in their preferred language.
21	- Use English for medical, statistical, and methodological terminology.
22	- Add pronunciation guides for drug names and technical abbreviations in the user's language.
23	- Be direct about paper limitations, but frame them constructively.
24
25	---
26
27	## Phase 0: Init & Outline
28
29	### Step 0a — Load design references (read before drafting outline)
30
31	Three of these are read now, in full — they change what you produce. The rest are read **when the
32	answer to Q0 tells you which one you need**, because a talk has one venue and one style, and reading
33	the others costs roughly seven thousand tokens to learn nothing you will use.
34
35	Read now (always):
36
37	A. `references/ai_slide_tells.md` — the marks a generated deck leaves. Read all of it, first.
38	The complaint about AI decks is not that they are ugly — templates solved ugly. It is that they
39	stop communicating, because they were built to make the maker comfortable rather than to serve the
40	audience. This file is why the deck does not need catching later; `scripts/check_slide_tells.py`
41	catches it after (Step 3.6). It overrules older guidance where they conflict — in particular the
42	eyebrow-on-every-slide and brand-footer rules this project used to mandate, which are the single
43	most-cited visual tell.
44
45	B. `references/presentation_archetypes.md` — the skeleton, chosen by where the speaker is
46	standing: conference oral, journal-club critique, case-anchored grand rounds, didactic lecture,
47	defence, keynote (Duarte's sparkline, the Jobs STAR moment, Takahashi/Lessig), lay talk, decision
48	brief (Minto's pyramid, action titles, Kawasaki's 10/20/30). A deck has two independent choices
49	and conflating them is why talks fail: the archetype is what the talk has to do; the *visual
50	style* is what it looks like. A conference oral in a keynote's skeleton dies (no data on the
51	slides); a keynote in a conference oral's skeleton dies harder. **The skin is a preference; the
52	skeleton is not.** Its mechanical half is `scripts/check_deck_budget.py`.
53
54	C. `references/presentation_design_guidelines.md` — the enforceable rules (assertion headlines,
55	24-pt floor, negative space, ≤3 colours, colourblind-safe palettes, redraw-don't-screenshot,
56	animation discipline) plus the G1–G10 self-check the Phase 3.5 critic scores against.
57
58	Read on demand — after Q0/Q2 tell you which one:
59
60	\| File \| Read it when \| Cost if read blindly \|
61	\|---\|---\|---\|
62	\| `references/medical_presentation_templates.md` \| the venue is one of the five medical ones — then read that section only \| ~3,700 tokens, of which you use a fifth \|
63	\| `references/slide_visual_styles/CATALOG.md` → one style file \| Q2 has chosen a style \| ~2,300 tokens per style \|
64	\| `references/slide_design_principles.md` \| you are stuck on why a slide is not landing — Reynolds / Duarte / Knaflic / Tufte, the theory under the rules in C \| ~2,600 tokens of theory you mostly already applied \|
65
66	These mirror the entry-point pattern used in
67	`make-figures/references/design_principles.md` (Step 1 "Specify"). Both skills share
68	the same Reynolds / Knaflic / Tufte foundations — slide-level (this skill) and
69	figure-level (make-figures) are companions, not duplicates.
70
71	### Required Inputs
72
73	Before starting, collect these from the user:
74
75	\| Input \| Why \|
76	\|-------\|-----\|
77	\| Paper \| PDF path, DOI, or PMID \|
78	\| Presentation time \| Determines depth and slide count \|
79	\| Target audience \| Specialty mix, knowledge level — controls terminology depth \|
80	\| Context \| Course name, conference, journal club format, prior session topics \|
81	\| Template / visual style \| Institutional template (.pptx/.potx) to fill, or a visual style to generate in. Default: ask (Step 0b) \|
82	\| Extension section \| Optional topic to include (e.g., AI directions, clinical

People who liked this also viewed

6 picks

Type

present-paper

41installs53forks

View on GitHub

How to install present-paper?

aperivue/medsci-skills/present-paper

$npx -y skills add Aperivue/medsci-skills --skill present-paper

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Present-Paper Skill
2
3	## Purpose
4
5	Prepare a polished academic presentation from a research paper. The skill walks through a 5-phase
6	pipeline: paper analysis, supporting research, script writing, slide note injection, and Q&A
7	preparation.
8
9	Use it when:
10
11	- preparing a journal club or seminar presentation
12	- presenting a paper for a graduate course
13	- preparing grand rounds or conference talks based on a published paper
14	- building speaker notes for an existing slide deck
15
16	---
17
18	## Communication Rules
19
20	- Communicate with the user in their preferred language.
21	- Use English for medical, statistical, and methodological terminology.
22	- Add pronunciation guides for drug names and technical abbreviations in the user's language.
23	- Be direct about paper limitations, but frame them constructively.
24
25	---
26
27	## Phase 0: Init & Outline
28
29	### Step 0a — Load design references (read before drafting outline)
30
31	Three of these are read now, in full — they change what you produce. The rest are read **when the
32	answer to Q0 tells you which one you need**, because a talk has one venue and one style, and reading
33	the others costs roughly seven thousand tokens to learn nothing you will use.
34
35	Read now (always):
36
37	A. `references/ai_slide_tells.md` — the marks a generated deck leaves. Read all of it, first.
38	The complaint about AI decks is not that they are ugly — templates solved ugly. It is that they
39	stop communicating, because they were built to make the maker comfortable rather than to serve the
40	audience. This file is why the deck does not need catching later; `scripts/check_slide_tells.py`
41	catches it after (Step 3.6). It overrules older guidance where they conflict — in particular the
42	eyebrow-on-every-slide and brand-footer rules this project used to mandate, which are the single
43	most-cited visual tell.
44
45	B. `references/presentation_archetypes.md` — the skeleton, chosen by where the speaker is
46	standing: conference oral, journal-club critique, case-anchored grand rounds, didactic lecture,
47	defence, keynote (Duarte's sparkline, the Jobs STAR moment, Takahashi/Lessig), lay talk, decision
48	brief (Minto's pyramid, action titles, Kawasaki's 10/20/30). A deck has two independent choices
49	and conflating them is why talks fail: the archetype is what the talk has to do; the *visual
50	style* is what it looks like. A conference oral in a keynote's skeleton dies (no data on the
51	slides); a keynote in a conference oral's skeleton dies harder. **The skin is a preference; the
52	skeleton is not.** Its mechanical half is `scripts/check_deck_budget.py`.
53
54	C. `references/presentation_design_guidelines.md` — the enforceable rules (assertion headlines,
55	24-pt floor, negative space, ≤3 colours, colourblind-safe palettes, redraw-don't-screenshot,
56	animation discipline) plus the G1–G10 self-check the Phase 3.5 critic scores against.
57
58	Read on demand — after Q0/Q2 tell you which one:
59
60	\| File \| Read it when \| Cost if read blindly \|
61	\|---\|---\|---\|
62	\| `references/medical_presentation_templates.md` \| the venue is one of the five medical ones — then read that section only \| ~3,700 tokens, of which you use a fifth \|
63	\| `references/slide_visual_styles/CATALOG.md` → one style file \| Q2 has chosen a style \| ~2,300 tokens per style \|
64	\| `references/slide_design_principles.md` \| you are stuck on why a slide is not landing — Reynolds / Duarte / Knaflic / Tufte, the theory under the rules in C \| ~2,600 tokens of theory you mostly already applied \|
65
66	These mirror the entry-point pattern used in
67	`make-figures/references/design_principles.md` (Step 1 "Specify"). Both skills share
68	the same Reynolds / Knaflic / Tufte foundations — slide-level (this skill) and
69	figure-level (make-figures) are companions, not duplicates.
70
71	### Required Inputs
72
73	Before starting, collect these from the user:
74
75	\| Input \| Why \|
76	\|-------\|-----\|
77	\| Paper \| PDF path, DOI, or PMID \|
78	\| Presentation time \| Determines depth and slide count \|
79	\| Target audience \| Specialty mix, knowledge level — controls terminology depth \|
80	\| Context \| Course name, conference, journal club format, prior session topics \|
81	\| Template / visual style \| Institutional template (.pptx/.potx) to fill, or a visual style to generate in. Default: ask (Step 0b) \|
82	\| Extension section \| Optional topic to include (e.g., AI directions, clinical

People who liked this also viewed

6 picks

Type