Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Aperivue/medsci-skillsnpx agentmods add skills/aperivue/medsci-skills/present-paperWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aperivue/medsci-skills/present-paper)<a href="https://agentmods.dev/skills/aperivue/medsci-skills/present-paper"><img src="https://agentmods.dev/badge/skills/aperivue/medsci-skills/present-paper/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aperivue/medsci-skills/present-paper"><img src="https://agentmods.dev/badge/skills/aperivue/medsci-skills/present-paper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 866 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00059 | $0.08960 |
| Opus 5.5 | $0.00024 | $0.03584 |
| Sonnet 5.5 | $0.00012 | $0.01792 |
| Haiku 4.5 | $0.00006 | $0.00896 |
Grade A, and why
present-paper scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 21d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 722 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Present-Paper Skill
Phase 0: Init & Outline
Step 0a — Load design references (read before drafting outline)
Read three files now, in full. Read the rest only when the answer to Q0/Q2 tells you which one you need — a talk has one venue and one style, and reading the others teaches nothing you will use.
Read now (always):
A. references/ai_slide_tells.md — the marks a generated deck leaves. Read all of it, first.
Building against it is why the deck does not need catching later; scripts/check_slide_tells.py
catches what slips through (Step 3.6). Where another reference conflicts with it, it wins. Eyebrow labels and brand footers on every
slide are the single most-cited visual tell.
B. references/presentation_archetypes.md — the skeleton, chosen by where the speaker is
standing: conference oral, journal-club critique, case-anchored grand rounds, didactic lecture,
defence, keynote (Duarte's sparkline, the Jobs STAR moment, Takahashi/Lessig), lay talk, decision
brief (Minto's pyramid, action titles, Kawasaki's 10/20/30). The archetype (what the talk has to
do) and the visual style (what it looks like) are independent choices. The skin is a
preference; the skeleton is not. Its mechanical half is scripts/check_deck_budget.py.
C. references/presentation_design_guidelines.md — the enforceable rules (assertion headlines,
24-pt floor, negative space, ≤3 colours, colourblind-safe palettes, redraw-don't-screenshot,
animation discipline) plus the G1–G10 self-check the Phase 3.5 critic scores against.
Read on demand — after Q0/Q2 tell you which one:
| File | Read it when |
|---|---|
references/medical_presentation_templates.md |
the venue is one of the five medical ones — then read that section only |
references/slide_visual_styles/CATALOG.md → one style file |
Q2 has chosen a style |
references/slide_design_principles.md |
you are stuck on why a slide is not landing — the Reynolds / Duarte / Knaflic / Tufte theory under the rules in C |
references/generated_illustrations.md |
you are about to generate any image for a slide, or a text-only slide keeps failing the critic; its first rule (never generate a medical image) is not optional |
references/spoken_notes_and_bilingual.md |
you are drafting speaker notes, or the deck is not monolingual |
What ships with it
49 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/ai_slide_tells.md 11 KB
- references/critic_rubrics/slide.md 9.7 KB
- references/generate_pptx_templates.py 23 KB runs code
- references/generated_illustrations.md 6.2 KB
- references/medical_presentation_templates.md 15 KB
- references/presentation_archetypes.md 12 KB
- references/presentation_design_guidelines.md 7.3 KB
- references/slide_design_principles.md 10 KB
- references/slide_visual_styles/CATALOG.md 3.1 KB
- references/slide_visual_styles/clinical_blue.md 3.2 KB
- references/slide_visual_styles/dark_modern.md 3.1 KB
- references/slide_visual_styles/editorial_mono.md 3.0 KB
- references/slide_visual_styles/institutional_brand.md 4.3 KB
- references/slide_visual_styles/nature_lancet.md 10 KB
- references/spoken_notes_and_bilingual.md 8.8 KB
- references/workflow-checklist.md 3.7 KB
- scripts/check_deck_budget_challenge/make_fixtures.py 6.5 KB runs code
- scripts/check_deck_budget_challenge/verify.sh 7.5 KB runs code
- scripts/check_deck_budget.py 16 KB runs code
- scripts/check_diagram_edges_challenge/make_fixtures.py 2.1 KB runs code
- scripts/check_diagram_edges_challenge/verify.sh 3.1 KB runs code
- scripts/check_diagram_edges.py 6.1 KB runs code
- scripts/check_font_portability_challenge/make_fixtures.py 7.3 KB runs code
- scripts/check_font_portability_challenge/verify.sh 4.9 KB runs code
- scripts/check_font_portability.py 16 KB runs code
- scripts/check_slide_tells_challenge/make_fixtures.py 6.6 KB runs code
- scripts/check_slide_tells_challenge/verify.sh 3.4 KB runs code
- scripts/check_slide_tells.py 32 KB runs code
- scripts/check_text_overflow_challenge/make_fixtures.py 4.4 KB runs code
- scripts/check_text_overflow_challenge/verify.sh 4.7 KB runs code
- scripts/check_text_overflow.py 17 KB runs code
- scripts/extract_pdf_figures.py 10 KB runs code
- scripts/inject_pronunciation_notes.py 5.9 KB runs code
- scripts/inject_speaker_notes.py 9.6 KB runs code
- scripts/inspect_pptx_template.py 5.0 KB runs code
- scripts/strip_notes_for_sharing.py 13 KB runs code
- scripts/trim_caption.py 9.2 KB runs code
- skill.yml 3.4 KB
- templates/build_pptx_nature_lancet.py 32 KB runs code
- tests/test_backup_off_the_clock.py 9.3 KB runs code
- tests/test_builder_layout.py 7.4 KB runs code
- tests/test_builder_no_chrome.py 8.1 KB runs code
- tests/test_deck_reading.py 7.5 KB runs code
- tests/test_extract_pdf_figures.py 3.5 KB runs code
- tests/test_md_parity.py 5.2 KB runs code
- tests/test_overflow_pdf.py 5.1 KB runs code
- tests/test_slide_page_numbers.sh 2.9 KB runs code
- tests/test_speaker_notes_markdown.py 4.3 KB runs code
- tests/test_strip_notes_for_sharing.py 8.6 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 21d ago Changed 50bc7056660b
- 23d ago Changed · +9 lines e185d2b8e091
- 25d ago Changed · -351 lines · -8 tokens per session d4ac2791ea3f
- 26d ago Changed · +6 lines 1629253aba89
- 1mo ago Changed · -2 lines 768f1e4a044f
- 1mo ago Changed · +17 lines f57f6bfcfdf4
- 1mo ago Changed · +11 lines d94632764cd4
- 1mo ago First seen · 1,032 lines · 67 tokens per session scan A 61bf339f3c77
present-paper is a skill published in the GitHub repository Aperivue/medsci-skills (349 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 8,960 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
clinical-trials-search
Search ClinicalTrials.gov with natural language queries. Find clinical trials, enrollment, and outcomes using Valyu semantic search.
java-test-updater
Update Java test classes and methods to work with new code versions after refactoring or modifications. Use when code changes break existing tests due to signature changes, refactoring, or behavior modifications. Takes old and new code versions plus old tests as input, and outputs updated tests that compile and pass…
library-advisor
Recommend relevant Isabelle/HOL or Coq standard library theories, lemmas, and tactics based on proof goals. Use when: (1) Users need library lemmas for their proof, (2) Proof goals match standard library patterns, (3) Users ask what libraries to import, (4) Specific lemmas are needed for list/set/arithmetic…
tactic-suggestion-assistant
Analyze proof states in Isabelle or Coq and suggest applicable tactics to make progress. Use when users need help with: (1) Choosing the next tactic in an interactive proof, (2) Understanding what tactics apply to their current goal, (3) Getting unstuck in a proof, (4) Learning which tactics work for specific goal…
verified-pseudocode-extractor
Extract language-agnostic pseudocode from formally verified programs (Isabelle/HOL, Coq) while preserving verified control flow, data dependencies, and algorithmic logic. Use when: (1) Users have verified code and need readable pseudocode, (2) Documenting verified algorithms for broader audiences, (3) Translating…
shidi
A Chinese-language research assistant role that turns a user’s ideas into literature reviews, experiment plans, figures and organised data.