{"id":"3d0128c9-91f7-4e53-811f-1b03dc19d7e4","shortId":"3deuyS","kind":"skill","title":"present-paper","tagline":"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","description":"# Present-Paper Skill\n\n## Purpose\n\nPrepare a polished academic presentation from a research paper. The skill walks through a 5-phase\npipeline: paper analysis, supporting research, script writing, slide note injection, and Q&A\npreparation.\n\nUse it when:\n\n- preparing a journal club or seminar presentation\n- presenting a paper for a graduate course\n- preparing grand rounds or conference talks based on a published paper\n- building speaker notes for an existing slide deck\n\n---\n\n## Communication Rules\n\n- Communicate with the user in their preferred language.\n- Use English for medical, statistical, and methodological terminology.\n- Add pronunciation guides for drug names and technical abbreviations in the user's language.\n- Be direct about paper limitations, but frame them constructively.\n\n---\n\n## Phase 0: Init & Outline\n\n### Step 0a — Load design references (read before drafting outline)\n\nBefore collecting inputs, the skill loads three reference files:\n\n1. **`references/slide_design_principles.md`** — Reynolds (Presentation Zen) +\n   Duarte (Slide:ology Glance Test™) + Knaflic (Storytelling with Data preattentive\n   attributes) + Tufte (Cognitive Style of PowerPoint). Defines the 5 design\n   principles, reading-time budgets per audience, cognitive-load ceilings, and the\n   anti-patterns this skill is built to avoid. **Read this first** — it shifts the\n   outline from \"what content fits\" to \"what should the audience remember 10 seconds\n   after each slide.\"\n2. **`references/medical_presentation_templates.md`** — Section structure, slide counts,\n   and design seeds for the 5 contexts: journal club, grand rounds, conference talk,\n   lecture, and academic lecture multi-paper survey. Pick the matching template after\n   Phase 0 inputs are collected, then customize.\n3. **`references/slide_visual_styles/`** — visual style specs (color palette, typography,\n   layout grid, slide-type templates) callable from any of the 5 context templates.\n   Currently available: `nature_lancet.md` (Nature/Lancet aesthetic — white background,\n   navy primary, coral accent, Inter/Pretendard). Default for academic lectures per\n   `~/.claude/rules/academic-lecture-style.md`. Paired with the generic builder\n   `templates/build_pptx_nature_lancet.py` and the PDF figure extractor\n   `scripts/extract_pdf_figures.py`.\n\nThese two files mirror the entry-point pattern used in\n`make-figures/references/design_principles.md` (Step 1 \"Specify\"). Both skills share\nthe same Reynolds / Knaflic / Tufte foundations — slide-level (this skill) and\nfigure-level (make-figures) are companions, not duplicates.\n\n### Required Inputs\n\nBefore starting, collect these from the user:\n\n| Input | Why |\n|-------|-----|\n| **Paper** | PDF path, DOI, or PMID |\n| **Presentation time** | Determines depth and slide count |\n| **Target audience** | Specialty mix, knowledge level — controls terminology depth |\n| **Context** | Course name, conference, journal club format, prior session topics |\n| **Extension section** | Optional topic to include (e.g., AI directions, clinical implications). Default: none |\n\n### Paper Analysis\n\nRead the paper and produce a structured analysis:\n\n```text\n## Paper Analysis\n\n### Citation\n[Full citation with DOI]\n\n### Background\n- What gap does this paper address?\n- What was known vs. unknown before this study?\n\n### Study Design\n- Type: [RCT / cohort / case series / meta-analysis / etc.]\n- Subjects: [n, inclusion/exclusion]\n- Methods: [key methodological choices]\n- Primary outcome: [what was measured]\n\n### Key Results\n1. [Finding 1 with effect size and CI/p-value]\n2. [Finding 2]\n3. [Finding 3]\n\n### Patient/Case Summary Table\n[If applicable — structured table of individual cases or subgroups]\n\n### Limitations\n1. [Limitation 1]\n2. [Limitation 2]\n\n### Significance\n- Why does this matter?\n- What changes because of this paper?\n```\n\n### Slide Outline\n\nCreate a slide-by-slide outline with time allocation:\n\n```text\n## Slide Outline ([N] slides, [M] minutes)\n\n| # | Title | Time | Key Content |\n|---|-------|------|-------------|\n| 1 | Title slide | 0:30 | Paper citation, presenter |\n| 2 | Context / Prior sessions | 1:00 | How this connects to prior knowledge |\n| 3 | Background | 1:30 | The gap this paper fills |\n| ... | ... | ... | ... |\n| N | Take-home messages | 0:30 | 3-5 key points |\n```\n\n**Gate: User approves outline before proceeding.**\n\n---\n\n## Phase 1: Supporting Research\n\n### Search Strategy\n\nFind references that strengthen the presentation:\n\n1. **Follow-up studies** — Has the main finding been replicated or extended?\n2. **Clinical trial data** — Large-scale data that contextualizes the findings\n3. **Review articles** — Authoritative summaries that frame the topic\n4. **Contradicting evidence** — Important for balanced Q&A preparation\n\n**Efficiency rule:** Limit supporting references to 5-8 total. Only search categories\nthat the approved outline (Phase 0) actually requires. Skip categories not needed for\nthe presentation type (e.g., skip clinical trials for a methods-focused paper).\n\n### Selection Criteria\n\nDo NOT summarize every paper found. Extract only:\n\n- Specific data points needed for slides (incidence rates, OR/HR, AUC values)\n- Findings that directly support or challenge the main paper\n- Context that helps the audience understand significance\n\n### Output\n\n```text\n## Verified References\n\n### Main Paper\n1. [Citation] — PMID: XXXXX, DOI: XX.XXXX/XXXXX\n\n### Supporting References\n2. [Citation] — PMID: XXXXX\n   → Used for: [specific data point or context]\n3. [Citation] — PMID: XXXXX\n   → Used for: [specific data point or context]\n\n### Key Data for Slides\n- [Statistic 1]: [value] — Source: [Ref #]\n- [Statistic 2]: [value] — Source: [Ref #]\n```\n\n**Every reference must have a verified DOI or PMID. Mark unverified references with [UNVERIFIED].**\n\n---\n\n## Phase 2: Script & Content\n\n### Speaker Script\n\nDraft a complete speaker script with these requirements:\n\n1. **Language**: User's preferred language for narration; English for technical terms\n2. **Audience adaptation**: Adjust explanation depth based on Phase 0 audience profile\n   - For mixed audiences: add one-line plain-language explanations for specialty-specific terms\n   - Example: \"FLAIR sequence — an MRI technique that suppresses fluid signal to highlight edema\"\n3. **Pronunciation guide**: Include native-language pronunciation for drug names, abbreviations\n   - Example: \"lecanemab (leh-KAN-eh-mab)\" or local equivalent\n4. **Timing markers**: Note approximate time per slide\n5. **Transition phrases**: Connect each slide to the narrative arc\n\n### Structure\n\n```text\n## Speaker Script\n\n### Slide 1: Title (0:30)\n\"[Opening — introduce yourself and the paper]\"\n\n### Slide 2: Context (1:00)\n\"[Connect to prior knowledge or clinical relevance]\"\n\n...\n\n### Slide N: Take-home Messages (0:30)\n\"[Summarize 3-5 key points. Thank audience. Invite questions.]\"\n```\n\n### Extension Section (Optional)\n\nOnly include if user requested in Phase 0. Examples:\n\n- AI/computational research directions stemming from the paper\n- Clinical practice implications\n- Policy or guideline implications\n- Connections to the user's own research\n\n**Gate: User reviews script before proceeding.**\n\n---\n\n## Phase 3: Slides & Notes\n\n### Two Modes\n\n**Mode A: Generate new slide deck**\n\nGenerate a fully-editable PPTX from structured inline data using `python-pptx`. Two\ncanonical template libraries:\n\n- `${CLAUDE_SKILL_DIR}/references/generate_pptx_templates.py` — generic T_lead /\n  T_text / T_table / T_image_right / etc. templates with smoke-tested `main()`. Use\n  for journal club, grand rounds, conference talk, and short paper talks.\n- `${CLAUDE_SKILL_DIR}/templates/build_pptx_nature_lancet.py` — Nature/Lancet visual\n  style (white + navy + coral, Inter/Pretendard, 47-slide academic lecture proven).\n  Use for **academic lecture multi-paper survey** (template #5). Functions:\n  `new_presentation`, `add_title_slide`, `add_toc_slide`, `add_section_divider`,\n  `add_transition_slide`, `add_content_slide`, `add_glossary_slide`,\n  `add_closing_slide`, plus `fix_app_xml()` helper. Style spec:\n  `references/slide_visual_styles/nature_lancet.md`.\n\nFor lecture decks pulling figures from PDFs (rather than from `/make-figures`\noutput), use `${CLAUDE_SKILL_DIR}/scripts/extract_pdf_figures.py` — pdftoppm + PIL\ncrop with normalized (0–1) box coordinates. Supports both single-crop CLI and YAML\nbatch config.\n\nAfter raw extraction, run `${CLAUDE_SKILL_DIR}/scripts/trim_caption.py` to\n**auto-remove journal headers / figure captions / surrounding whitespace** so\nthat only the figure body remains — the Adobe-Acrobat-crop equivalent in\nautomation. The script uses horizontal-projection segmentation plus\ntext-band detection (height + density + gap + line-pattern signature) and\npreserves multi-panel figures intact:\n\n```bash\npython3 \"${CLAUDE_SKILL_DIR}/scripts/trim_caption.py\" \\\n  --in-dir  figures/extracted \\\n  --out-dir figures/cropped\n```\n\nHandles four common journal layouts: top running-head bar, bottom multi-line\ncaption (sparse text), bottom caption *fused* with figure body (no clear gap,\ndetected via narrow dark/light alternation), and multi-row tables with\nfootnotes (footnote cut, table rows preserved). No tesseract / OCR\ndependency — Pillow + numpy only. Verified on 12-figure academic deck\n(80–95% height retention; captions, journal banners, and CellPress-style\nheaders all removed). When the deck slot expects only the figure body\n(default for `build_pptx_nature_lancet.py`), point `FIG_DIR` at the cropped\noutput dir.\n\n### Architecture\n\n```\ninline structured data (lists/dicts in build_*_slides())\n    ↓ template functions (T_lead / T_text / T_table / ...)\neditable PPTX with native text frames (selectable, restyleable in PowerPoint)\n```\n\nThree rules that keep slides stable:\n\n1. **No markdown parsing.** Every slide is a function call with explicit inline data.\n2. **No `cur_top` cumulative position tracking.** Use the fixed coordinate zones below — `cur_top` accumulates rounding errors and breaks layout after ~10 slides.\n3. **No Marp.** Marp renders to images; the deck becomes uneditable and reviewers cannot copy text or restyle.\n\n### Slide-type templates\n\n| Template | Use for | Required fields |\n|----------|---------|-----------------|\n| `T_lead` | Title slide, section divider | `title`, `subtitle?`, `extra?` |\n| `T_text` | Bullet body (most common) | `title`, `body_lines[]`, `subtitle?` |\n| `T_table` | Cohort tables, comparisons | `title`, `headers[]`, `rows[][]`, `body_before?` |\n| `T_image_right` | Body + figure on right | `title`, `body_lines[]`, `img_path`, `img_pct?` (PNG ≥300dpi or vector PDF — see Figure source formats below) |\n| `T_quote_slide` | Verbatim citations, witness quotes | `title`, `quotes[]`, `body_after?`, `img_path?` |\n| `T_two_col` | Compare/contrast | `title`, `left_lines[]`, `right_lines[]` |\n| `T_two_col_with_box` | Compare + emphasis | as above + `metaphor_col`, `metaphor_lines[]` |\n| `T_highlight_slide` | Single key result | `title`, `highlight_lines[]`, `body_before?` |\n| `T_metaphor_body` | Body + analogy footer | `title`, `body_lines[]`, `metaphor_lines[]` |\n| `T_table_two_col` | Take-aways + numeric table | `title`, `left_lines[]`, `headers[]`, `rows[][]` |\n\n### Figure source formats (when consuming `/make-figures` output)\n\nWhen the deck pulls figures from `analysis/figures/` produced by `/make-figures`:\n\n- **Preferred for slides**: PNG at ≥300 dpi. python-pptx `add_picture()` handles this directly. Set `img_pct` (template `T_image_right`) so the figure occupies ≥40 % of slide width on a 13.33 × 7.5-in widescreen layout.\n- **Vector source available**: prefer PDF only if the slide will be projected at >1080p or printed as a handout — convert PDF → PNG at the target DPI (`pdftoppm -r 300 input.pdf out_prefix`) before insertion, because python-pptx PDF embedding is unreliable across PowerPoint versions.\n- **Forbidden**: TIFF (Mac PowerPoint silently drops it — see Mac compatibility checklist below); JPEG for line art (compression artifacts on diagonal lines); raw SVG (PowerPoint Mac handles it inconsistently).\n- **Caption / legend**: re-draft for spoken-narration context, not the journal legend verbatim. The journal legend assumes a reader; the slide caption assumes a listener with 5–10 seconds of attention.\n\n### Helpers (used by templates — usually you do not call directly)\n\n| Helper | Role |\n|--------|------|\n| `_text` | Single text box with `**bold**` inline markup |\n| `_multiline` | Multi-line block with bullet (`- `, `✓ `) and `### subhead` support |\n| `_title_block` | Title + teal underline + optional subtitle |\n| `_table` | Styled table (teal header row, alternating rows) |\n| `_quote` | Blockquote — teal left bar + light-blue background |\n| `_highlight` | Yellow rounded box + orange 2pt border |\n| `_metaphor` | Same shape as quote, lighter font |\n| `_image` | PIL aspect-preserving image insert (handles iPhone EXIF if you transpose first) |\n| `_slidenum` | Bottom-right page number |\n\n### Design tokens (defaults — change to fit institution/journal)\n\n```python\nNAVY    = #1B2A4A   # title text, section divider background\nTEAL    = #0072B2   # subtitle, underline, table header bg, quote bar\nORANGE  = #D55E00   # highlight box border\nGRAY    = #333333   # body text\nFONT    = 'Apple SD Gothic Neo'   # use a Latin-only font on non-Korean decks\n```\n\n### Fixed coordinate zones (16:9 = 13.333\" × 7.5\")\n\n```\nML / MR = 0.8\"     MT = 0.5\"     CW = SW − ML − MR = 11.733\"\n\nTITLE_Y = 0.5\"    TITLE_H = 0.8\"\nSUB_Y   = 1.3\"    SUB_H   = 0.5\"\nBODY_Y  ≈ 1.9\"    BODY_H  ≈ 5.1\"\n```\n\n### Build script responsibilities\n\nA from-scratch generation script must:\n\n- Convert TIFF images to PNG before `add_picture` (Mac PowerPoint silently drops TIFF).\n- Apply EXIF transpose to iPhone photos before insertion.\n- After inserting/removing slides, sync `docProps/app.xml` (`<Slides>`, `<Notes>`, `HeadingPairs`, `TitlesOfParts`) to the actual count, or PowerPoint Mac will raise a recovery dialog on open.\n- If you copy `<a:srcRect>` from another deck, copy the values verbatim — they are 1/1000-percent (cap 100000), never EMU. A unit conversion bug here crops 99% of the image off-slide.\n- Print slide count, notes count, file size, and editability check at the end.\n\n### Forbidden in Mode A\n\n- ❌ Marp CLI for PPTX (always image-rendered, uneditable).\n- ❌ Markdown auto-parsing into slides (layout drifts on every regeneration).\n- ❌ `cur_top` cumulative top tracking (accumulates rounding error).\n- ❌ Direct iPhone photo insert without EXIF transpose (rotated 90° in PowerPoint).\n- ❌ Using `python-pptx` from-scratch rebuild to *edit* an existing deck — see Patch over Rebuild below.\n\n### Mac PowerPoint compatibility checklist\n\nPowerPoint Mac is stricter than Windows / Keynote / LibreOffice on OOXML defects.\nVerify before delivering any deck destined for a Mac viewer:\n\n| Defect | Detect | Fix |\n|---|---|---|\n| **TIFF images** | `find ppt/media -iname '*.tif*'` | `sips -s format png in.tif --out out.png` + replace `.tif`→`.png` in `_rels/*.rels` |\n| **`<a:sp3d>` in rPr** | `grep -l '<a:sp3d>' ppt/slides/*.xml` | Regex-strip the `<a:sp3d>...</a:sp3d>` block (renders as red outline only on Mac) |\n| **`app.xml` count mismatch** | `<Slides>` value + `HeadingPairs` count + `TitlesOfParts` size vs actual slide files | Sync all four fields to real count |\n| **`srcRect` corruption** | Any value > 100000 (1/1000-percent cap) | Compare with original deck; restore verbatim |\n\nValidation must run on **PDF export AND Mac PowerPoint** — neither alone catches all four. PDF misses `sp3d` outlines and `srcRect` corruption.\n\n### Patch over Rebuild — editing an existing PPTX\n\nWhen the user supplies an existing deck and asks for surgical edits (textbox width, image\ncrop, font swap, sp3d removal), prefer **regex/sed patching of the unzipped XML** over\nregenerating with `python-pptx`. From-scratch rebuild loses:\n\n- `<a:srcRect>` image crops\n- `<a:sp3d>` / `<a:scene3d>` (when intentional)\n- Slide master / layout / theme details\n- `app.xml` and `core.xml` metadata\n\n```bash\nunzip -q original.pptx -d /tmp/work\npython3 -c \"\nimport re; from pathlib import Path\np = Path('/tmp/work/ppt/slides/slide23.xml')\ns = p.read_text()\ns = s.replace('cx=\\\"9504720\\\"', 'cx=\\\"11200000\\\"')\np.write_text(s)\n\"\ncd /tmp/work && zip -rq ../patched.pptx . -x '*.DS_Store'\n```\n\n`python-pptx` is reserved for (a) brand-new decks built via the templates above, or\n(b) appending speaker notes via `slide.notes_slide.notes_text_frame.text`. The skill's\n`scripts/inject_speaker_notes.py` is the canonical example of (b).\n\n### Standard structure (10–15 min paper talk)\n\n1. Title slide (`T_lead`) — paper citation + presenter\n2. Background (`T_text` × 1–2)\n3. Study design / Methods (`T_text` or `T_two_col`)\n4. Key results with figures (`T_image_right` / `T_table` × 2–3)\n5. Discussion (`T_text`)\n6. Limitations (`T_two_col_with_box` works well)\n7. Take-home (`T_text` or `T_highlight_slide`)\n\n### Output\n\nSave to `output/presentation.pptx`. Speaker notes go into the notes pane only — never\nmodify slide design when adding notes.\n\n### Step 3.5 — Slide critic (run before delivering deck)\n\nAfter exporting the PPTX, run the slide critic rubric at\n`references/critic_rubrics/slide.md`. Score each slide and the deck-level Mac\ncompatibility checks (Section F) as PASS / PARTIAL / FAIL. Produce concrete edits for\nevery FAIL or PARTIAL item before treating the deck as ready.\n\nMandatory deck-level checks (cross-link with `~/.claude/rules/pptx-mac-compatibility.md`):\n\n```bash\n# F.22 No TIFF\nfind ppt/media -iname '*.tif*' || true   # must be empty\n\n# F.23 No 3-D bevel\ngrep -l '<a:sp3d>' ppt/slides/*.xml      # must be empty\n\n# F.24 app.xml count sync\ngrep -c '<Slides>\\|<Notes>' docProps/app.xml\nls ppt/slides/slide*.xml | wc -l         # must match\n\n# F.25 srcRect bounds (any value > 100000 = bug)\ngrep -oE '\"[0-9]{6,}\"' ppt/slides/*.xml | head\n```\n\nRecord `critic_pass: yes | partial | no` and `refine_rounds: N` in `_quick_review.md`.\n\n**Mode B: Add notes to existing slides** (more common)\n- Read existing PPTX to understand slide structure and count\n- Map speaker script sections to corresponding slides\n- Generate `inject_notes.py` script tailored to the specific presentation\n\n### Note Injection Script\n\nGenerate a tailored `inject_notes.py` following the pattern in\n`${CLAUDE_SKILL_DIR}/references/inject_speaker_notes.py`. The generated script should\ncontain only the `notes` dictionary customized for this presentation and the main\ninjection loop from the template.\n\n### Critical Rule\n\n**Speaker notes are injected without modifying slide design, layout, text, or images.**\nThe script only touches the notes pane. Verify by comparing slide content before and after.\n\n---\n\n## Phase 4: Q&A Preparation\n\n### Question Generation\n\nGenerate questions from multiple perspectives:\n\n1. **Methodology critics**: \"Why this design? Why not...?\"\n2. **Domain experts**: Deep technical questions about the specific field\n3. **Generalists**: \"What does this mean for clinical practice?\"\n4. **Students/trainees**: Clarification questions about unfamiliar concepts\n\n### Answer Structure\n\nEvery answer should follow the pattern:\n\n```\nAcknowledge → Evidence → Conclude\n\n\"That's an important limitation. [Acknowledge the concern honestly.]\nHowever, [cite specific supporting evidence — author, year, finding].\nSo while [restate limitation], [conclude with the paper's contribution despite it].\"\n```\n\n### Quick Review Sheet\n\nA single-page reference for last-minute review:\n\n```text\n## Quick Review\n\n### Must-Know Numbers\n| Metric | Value | Source |\n|--------|-------|--------|\n| [Key stat 1] | [value] | [Ref] |\n| [Key stat 2] | [value] | [Ref] |\n\n### Common Pitfalls\n- Don't confuse [X] with [Y]\n- [Classification A] and [Classification B] are independent frameworks\n- Slide says [rounded value], precise value is [exact value]\n\n### Key Takeaways (memorize these)\n1. [Point 1]\n2. [Point 2]\n3. [Point 3]\n```\n\n---\n\n## Output File Structure\n\nAll outputs go in the user's presentation directory:\n\n```\n{presentation_dir}/\n├── _analysis.md              # Phase 0: Paper analysis + outline\n├── _references.md            # Phase 1: Verified references + key data\n├── _script.md                # Phase 2: Speaker script\n├── _qa_prep.md               # Phase 4: Expected Q&A\n├── _quick_review.md          # Phase 4: Pre-presentation review sheet + critic_pass record\n├── _slide_critic.md          # Phase 3.5: Slide rubric scores per slide\n├── inject_notes.py           # Phase 3: Tailored note injection script\n├── figures/                  # Extracted paper figures (if needed)\n└── reference/                # Supporting paper PDFs (if downloaded)\n```\n\n## Cross-skill / Cross-rule integration\n\nThis skill composes with adjacent skills and global rules:\n\n| When | Use | Why |\n|---|---|---|\n| Need a figure on a slide (ROC, forest, KM, flow) | `/make-figures` first, then embed | Both skills share Reynolds/Knaflic/Tufte foundations; figure-level + slide-level companions |\n| Manuscript reporting checklist parallel | `/check-reporting` for the same paper | Paper presentations often shadow manuscript revision; reporting-guideline gaps surface in Q&A |\n| Visual abstract / Central Illustration | `/make-figures` visual-abstract templates | Then verify against `~/.claude/rules/journal-ai-image-policies.md` (JACC prohibits, Radiology allows with disclosure) |\n| PPTX edits to existing institutional template | `~/.claude/rules/pptx-mac-compatibility.md` | Patch over rebuild; preserve master/layout/srcRect |\n| Manuscript companion deck | `~/.claude/rules/manuscript-style-classical.md` | Heading style, AI-Disclosure policy, em-dash discipline carry over to slides for senior MA reviewer audiences |\n| References on slides | `/verify-refs` (audit-only) before delivery | Same anti-hallucination gate as manuscript references |\n\n---\n\n## Constraints\n\n- **Never fabricate references.** Every citation must be verified against PubMed, DOI, or the PDF itself.\n- **Never modify slide design** when injecting notes. Notes and slides are separate concerns.\n- **Always ask audience first.** Do not start drafting until the target audience is defined.\n- **Extension sections are opt-in.** Do not add AI/clinical/policy sections unless explicitly requested.\n- **Respect presentation time.** Script length must match allocated time (roughly 130-150 words per minute for academic presentations).\n\n## Anti-Hallucination\n\n- **Never fabricate references.** All citations must be verified via `/search-lit` with confirmed DOI or PMID. Mark unverified references as `[UNVERIFIED - NEEDS MANUAL CHECK]`.\n- **Never invent clinical definitions, diagnostic criteria, or guideline recommendations.** If uncertain, flag with `[VERIFY]` and ask the user.\n- **Never fabricate numerical results** — compliance percentages, scores, effect sizes, or sample sizes must come from actual data or analysis output.\n- If a reporting guideline item, journal policy, or clinical standard is uncertain, state the uncertainty rather than guessing.","tags":["present","paper","medsci","skills","aperivue","agent-skills","biostatistics","claude-code","claude-skills","clinical-research","diagnostic-accuracy","irb-protocol"],"capabilities":["skill","source-aperivue","skill-present-paper","topic-agent-skills","topic-biostatistics","topic-claude-code","topic-claude-skills","topic-clinical-research","topic-diagnostic-accuracy","topic-irb-protocol","topic-literature-review","topic-manuscript","topic-medical-ai","topic-medical-research","topic-meta-analysis"],"categories":["medsci-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/Aperivue/medsci-skills/present-paper","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add Aperivue/medsci-skills","source_repo":"https://github.com/Aperivue/medsci-skills","install_from":"skills.sh"}},"qualityScore":"0.499","qualityRationale":"deterministic score 0.50 from registry signals: · indexed on github topic:agent-skills · 98 github stars · SKILL.md body (23,051 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T18:56:31.097Z","embedding":null,"createdAt":"2026-05-13T12:57:46.076Z","updatedAt":"2026-05-18T18:56:31.097Z","lastSeenAt":"2026-05-18T18:56:31.097Z","tsv":"'-150':3013 '-5':594,943 '-8':665 '-9':2458 '/.claude/rules/academic-lecture-style.md':320 '/.claude/rules/journal-ai-image-policies.md':2886 '/.claude/rules/manuscript-style-classical.md':2908 '/.claude/rules/pptx-mac-compatibility.md':2409,2899 '/check-reporting':2855 '/make-figures':1120,1535,1546,2835,2878 '/patched.pptx':2227 '/references/design_principles.md':347 '/references/generate_pptx_templates.py':1022 '/references/inject_speaker_notes.py':2522 '/scripts/extract_pdf_figures.py':1126 '/scripts/trim_caption.py':1153,1210 '/search-lit':3032 '/templates/build_pptx_nature_lancet.py':1055 '/tmp/work':2199,2224 '/tmp/work/ppt/slides/slide23.xml':2210 '/verify-refs':2931 '/xxxxx':746 '0':152,275,560,591,675,834,913,939,960,1132,2457,2746 '0.5':1838,1846,1855 '0.8':1836,1849 '00':570,925 '0072b2':1794 '0a':156 '1':173,349,490,492,517,519,557,569,579,604,615,739,776,813,911,924,1133,1341,2271,2283,2585,2684,2721,2723,2752 '1.3':1852 '1.9':1858 '1/1000-percent':1926,2107 '10':237,1377,1686,2266 '100000':1928,2106,2453 '1080p':1597 '11.733':1843 '11200000':2219 '12':1271 '13.33':1579 '13.333':1832 '130':3012 '15':2267 '16':1830 '1b2a4a':1787 '2':242,498,500,520,522,565,628,749,781,800,825,922,1355,2279,2284,2305,2593,2689,2724,2726,2759 '2pt':1749 '3':281,501,503,577,593,640,760,866,942,990,1379,2285,2306,2424,2603,2727,2729,2789 '3.5':2350,2781 '30':561,580,592,914,940 '300':1552,1612 '300dpi':1450 '333333':1808 '4':649,888,2295,2574,2612,2764,2770 '40':1573 '47':1063 '5':58,196,253,300,664,896,1077,1685,2307 '5.1':1861 '6':2311,2459 '7':2320 '7.5':1580,1833 '80':1275 '9':1831 '90':1997 '95':1276 '9504720':2217 '99':1937 'abbrevi':136,877 'abstract':2875,2881 'academ':4,47,263,317,1065,1070,1273,3018 'accent':313 'accumul':1370,1986 'acknowledg':2627,2635 'acrobat':1174 'across':1626 'actual':676,1902,2092,3079 'ad':2347 'adapt':33,827 'add':128,840,1081,1084,1087,1090,1093,1096,1099,1557,1878,2477,2996 'address':456 'adjac':2817 'adjust':828 'adob':1173 'adobe-acrobat-crop':1172 'aesthet':307 'ai':426,2912 'ai-disclosur':2911 'ai/clinical/policy':2997 'ai/computational':962 'alloc':545,3009 'allow':2890 'alon':2125 'altern':1249,1733 'alway':1965,2974 'analog':1509 'analysi':62,433,441,444,474,2748,3082 'analysis.md':2744 'analysis/figures':1543 'analyz':24 'anoth':1918 'answer':2619,2622 'anti':212,2939,3021 'anti-hallucin':2938,3020 'anti-pattern':211 'app':1104 'app.xml':2083,2190,2435 'append':2249 'appl':1812 'appli':1885 'applic':508 'approv':599,672 'approxim':892 'arc':905 'architectur':1309 'art':1644 'articl':642 'artifact':1646 'ask':2151,2975,3061 'aspect':1761 'aspect-preserv':1760 'assum':1675,1681 'attent':1689 'attribut':188 'auc':715 'audienc':32,204,235,401,730,826,835,839,947,2927,2976,2985 'audience-adapt':31 'audit':2933 'audit-on':2932 'aug':38 'author':2644 'authorit':643 'auto':1156,1972 'auto-pars':1971 'auto-remov':1155 'autom':1178 'avail':304,1586 'avoid':219 'away':1522 'b':2248,2263,2476,2704 'background':309,450,578,1743,1792,2280 'balanc':654 'band':1189 'banner':1281 'bar':1228,1739,1801 'base':97,831 'bash':1205,2194,2410 'batch':1144 'becom':1388 'bevel':2426 'bg':1799 'block':1714,1721,2075 'blockquot':1736 'blue':1742 'bodi':1169,1241,1297,1418,1422,1433,1438,1443,1468,1503,1507,1508,1512,1809,1856,1859 'bold':1707 'border':1750,1806 'bottom':1229,1236,1774 'bottom-right':1773 'bound':2450 'box':1134,1485,1705,1747,1805,2317 'brand':2239 'brand-new':2238 'break':1374 'budget':202 'bug':1934,2454 'build':102,1315,1862 'build_pptx_nature_lancet.py':1300 'builder':325 'built':217,2242 'bullet':1417,1716 'c':2201,2439 'call':1350,1698 'callabl':295 'cannot':1392 'canon':1016,2260 'cap':1927,2108 'caption':1161,1233,1237,1279,1657,1680 'carri':2919 'case':470,513 'catch':2126 'categori':669,679 'cd':2223 'ceil':208 'cellpress':1284 'cellpress-styl':1283 'central':2876 'challeng':722 'chang':529,1781 'check':1953,2378,2404,3045 'checklist':1639,2021,2853 'choic':482 'ci/p-value':497 'citat':445,447,563,740,750,761,1463,2277,2950,3027 'cite':2640 'clarif':2614 'classif':2700,2703 'claud':1019,1052,1123,1150,1207,2519 'clear':1243 'cli':1141,1962 'clinic':428,629,688,931,969,2610,3048,3092 'close':1100 'club':11,80,256,414,1043 'cognit':190,206 'cognitive-load':205 'cohort':469,1427 'col':1474,1483,1491,1519,2294,2315 'collect':165,278,380 'color':286 'come':3077 'common':1221,1420,2483,2692 'communic':110,112 'companion':373,2850,2906 'compar':1486,2109,2567 'compare/contrast':1475 'comparison':1429 'compat':1638,2020,2377 'complet':807 'complianc':3068 'compos':2815 'compress':1645 'concept':2618 'concern':2637,2973 'conclud':2629,2651 'concret':2386 'confer':22,95,259,412,1046 'config':1145 'confirm':3034 'confus':2696 'connect':573,899,926,976 'constraint':2945 'construct':150 'consum':1534 'contain':2527 'content':229,556,802,1094,2569 'context':254,301,409,566,726,759,770,923,1666 'contextu':637 'contradict':650 'contribut':2656 'control':406 'convers':1933 'convert':1603,1872 'coordin':1135,1365,1828 'copi':1393,1916,1920 'coral':312,1061 'core.xml':2192 'correspond':2498 'corrupt':2103,2135 'count':247,399,1903,1946,1948,2084,2088,2101,2436,2492 'cours':18,90,410 'creat':536 'criteria':697,3051 'critic':2352,2364,2464,2544,2587,2776 'crop':1129,1140,1175,1306,1936,2158,2182 'cross':2406,2807,2810 'cross-link':2405 'cross-rul':2809 'cross-skil':2806 'cumul':1359,1983 'cur':1357,1368,1981 'current':303 'custom':280,2532 'cut':1258 'cw':1839 'cx':2216,2218 'd':2198,2425 'd55e00':1803 'dark/light':1248 'dash':2917 'data':186,631,635,707,756,767,772,1010,1312,1354,2756,3080 'deck':17,109,1000,1112,1274,1291,1387,1539,1826,1919,2012,2037,2112,2149,2241,2356,2374,2397,2402,2907 'deck-level':2373,2401 'deep':2596 'default':315,430,1298,1780 'defect':2032,2043 'defin':194,2987 'definit':3049 'deliv':2035,2355 'deliveri':2936 'densiti':1192 'depend':1265 'depth':396,408,830 'design':158,197,249,466,1778,2287,2345,2553,2590,2964 'despit':2657 'destin':2038 'detail':2189 'detect':1190,1245,2044 'determin':395 'diagnost':3050 'diagon':1648 'dialog':1911 'dictionari':2531 'dir':1021,1054,1125,1152,1209,1213,1217,1303,1308,2521,2743 'direct':143,427,719,964,1561,1699,1989 'directori':2741 'disciplin':2918 'disclosur':2892,2913 'discuss':2308 'divid':1089,1411,1791 'docprops/app.xml':1897,2440 'doi':390,449,743,791,2956,3035 'domain':2594 'download':2805 'dpi':1553,1609 'draft':30,162,805,1661,2981 'drift':1977 'driven':9 'drop':1634,1883 'drug':132,875 'ds':2229 'duart':178 'duplic':375 'e.g':425,686 'edema':865 'edit':1005,1325,1952,2009,2139,2154,2387,2894 'effect':494,3071 'effici':658 'eh':883 'em':2916 'em-dash':2915 'emb':2838 'embed':1623 'emphasi':1487 'empti':2421,2433 'emu':1930 'end':1956 'english':121,821 'entri':339 'entry-point':338 'equival':887,1176 'error':1372,1988 'etc':475,1033 'everi':701,785,1345,1979,2389,2621,2949 'evid':651,2628,2643 'exact':2715 'exampl':853,878,961,2261 'exif':1767,1886,1994 'exist':107,2011,2141,2148,2480,2485,2896 'expect':1293,2765 'expert':2595 'explan':829,847 'explicit':1352,3000 'export':2120,2358 'extend':627 'extens':419,950,2988 'extra':1414 'extract':704,1148,2795 'extractor':331 'f':2380 'f.22':2411 'f.23':2422 'f.24':2434 'f.25':2448 'fabric':2947,3024,3065 'fail':2384,2390 'field':1405,2098,2602 'fig':1302 'figur':330,346,367,371,1114,1160,1168,1203,1240,1272,1296,1439,1455,1530,1541,1571,2299,2794,2797,2827,2845 'figure-level':366,2844 'figures/cropped':1218 'figures/extracted':1214 'file':172,335,1949,2094,2731 'fill':585 'find':27,491,499,502,609,623,639,717,2048,2414,2646 'first':222,1771,2836,2977 'fit':230,1783 'fix':1103,1364,1827,2045 'flag':3057 'flair':854 'flow':2834 'fluid':861 'focus':694 'follow':617,2515,2624 'follow-up':616 'font':1757,1811,1821,2159 'footer':1510 'footnot':1256,1257 'forbidden':1629,1957 'forest':2832 'format':415,1457,1532,2054 'found':703 'foundat':359,2843 'four':1220,2097,2128 'frame':148,646,1330 'framework':2707 'from-scratch':1866,2004,2176 'full':446 'fulli':1004 'fully-edit':1003 'function':1078,1318,1349 'fuse':1238 'gap':452,582,1193,1244,2869 'gate':597,983,2941 'generalist':2604 'generat':36,997,1001,1869,2500,2511,2524,2579,2580 'generic':324,1023 'glanc':181 'global':2820 'glossari':1097 'go':2336,2735 'gothic':1814 'graduat':89 'grand':12,92,257,1044 'gray':1807 'grep':2067,2427,2438,2455 'grid':290 'guess':3101 'guid':130,868 'guidelin':974,2868,3053,3087 'h':1848,1854,1860 'hallucin':2940,3022 'handl':1219,1559,1654,1765 'handout':1602 'head':1227,2462,2909 'header':1159,1286,1431,1528,1731,1798 'headingpair':1898,2087 'height':1191,1277 'help':728 'helper':1106,1690,1700 'highlight':864,1495,1501,1744,1804,2328 'home':589,937,2323 'honest':2638 'horizont':1183 'horizontal-project':1182 'howev':2639 'illustr':2877 'imag':1031,1385,1436,1567,1758,1763,1874,1940,1967,2047,2157,2181,2301,2557 'image-rend':1966 'img':1445,1447,1470,1563 'implic':429,971,975 'import':652,2202,2206,2633 'in-dir':1211 'in.tif':2056 'inam':2050,2416 'incid':712 'includ':424,869,954 'inclusion/exclusion':478 'inconsist':1656 'independ':2706 'individu':512 'init':153 'inject':69,2509,2539,2549,2792,2966 'inject_notes.py':2501,2514,2787 'inlin':1009,1310,1353,1708 'input':166,276,377,385 'input.pdf':1613 'insert':1617,1764,1892,1992 'inserting/removing':1894 'institut':2897 'institution/journal':1784 'intact':1204 'integr':2812 'intent':2184 'inter/pretendard':314,1062 'introduc':916 'invent':3047 'invit':948 'iphon':1766,1889,1990 'item':2393,3088 'jacc':2887 'journal':10,79,255,413,1042,1158,1222,1280,1669,1673,3089 'jpeg':1641 'kan':882 'keep':1338 'key':480,488,555,595,771,944,1498,2296,2682,2687,2717,2755 'keynot':2028 'km':2833 'knaflic':183,357 'know':2677 'knowledg':404,576,929 'known':459 'korean':1825 'l':2068,2428,2445 'languag':119,141,814,818,846,872 'larg':633 'large-scal':632 'last':2669 'last-minut':2668 'latin':1819 'latin-on':1818 'layout':289,1223,1375,1583,1976,2187,2554 'lead':1025,1320,1407,2275 'lecanemab':879 'lectur':261,264,318,1066,1071,1111 'lecture/teaching':16 'left':1477,1526,1738 'legend':1658,1670,1674 'leh':881 'leh-kan-eh-mab':880 'length':3006 'level':362,368,405,2375,2403,2846,2849 'librari':1018 'libreoffic':2029 'light':1741 'light-blu':1740 'lighter':1756 'limit':146,516,518,521,660,2312,2634,2650 'line':843,1195,1232,1423,1444,1478,1480,1493,1502,1513,1515,1527,1643,1649,1713 'line-pattern':1194 'link':2407 'listen':1683 'lists/dicts':1313 'load':157,169,207 'local':886 'loop':2540 'lose':2180 'ls':2441 'm':551 'ma':2925 'mab':884 'mac':1631,1637,1653,1880,1906,2018,2023,2041,2082,2122,2376 'main':622,724,737,1039,2538 'make':345,370 'make-figur':344,369 'mandatori':2400 'manual':3044 'manuscript':2851,2864,2905,2943 'map':2493 'mark':794,3038 'markdown':1343,1970 'marker':890 'markup':1709 'marp':1381,1382,1961 'master':2186 'master/layout/srcrect':2904 'match':271,2447,3008 'materi':19,26 'matter':527 'mean':2608 'measur':487 'medic':123 'memor':2719 'messag':590,938 'meta':473 'meta-analysi':472 'metadata':2193 'metaphor':1490,1492,1506,1514,1751 'method':479,693,2288 'methodolog':126,481,2586 'methods-focus':692 'metric':2679 'min':2268 'minut':552,2670,3016 'mirror':336 'mismatch':2085 'miss':2130 'mix':403,838 'ml':1834,1841 'mode':994,995,1959,2475 'modifi':2343,2551,2962 'mr':1835,1842 'mri':857 'mt':1837 'multi':266,1073,1201,1231,1252,1712 'multi-lin':1230,1711 'multi-panel':1200 'multi-pap':265,1072 'multi-row':1251 'multilin':1710 'multipl':2583 'must':787,1871,2116,2419,2431,2446,2676,2951,3007,3028,3076 'must-know':2675 'n':477,549,586,934,2472 'name':133,411,876 'narrat':820,904,1665 'narrow':1247 'nativ':871,1328 'native-languag':870 'nature/lancet':306,1056 'nature_lancet.md':305 'navi':310,1060,1786 'need':681,709,2799,2825,3043 'neither':2124 'neo':1815 'never':1929,2342,2946,2961,3023,3046,3064 'new':998,1079,2240 'non':1824 'non-korean':1823 'none':431 'normal':1131 'note':68,104,891,992,1947,2251,2335,2339,2348,2478,2508,2530,2547,2563,2791,2967,2968 'number':1777,2678 'numer':1523,3066 'numpi':1267 'occupi':1572 'ocr':1264 'oe':2456 'off-slid':1941 'often':2862 'olog':180 'one':842 'one-lin':841 'ooxml':2031 'open':915,1913 'opt':2992 'opt-in':2991 'option':421,952,1725 'or/hr':714 'orang':1748,1802 'origin':2111 'original.pptx':2197 'out-dir':1215 'out.png':2058 'outcom':484 'outlin':154,163,226,535,542,548,600,673,2079,2132,2749 'output':733,1121,1307,1536,2330,2730,2734,3083 'output/presentation.pptx':2333 'p':2208 'p.read':2212 'p.write':2220 'page':1776,2665 'pair':321 'palett':287 'pane':2340,2564 'panel':1202 'paper':3,8,41,52,61,86,101,145,267,387,432,436,443,455,533,562,584,695,702,725,738,920,968,1050,1074,2269,2276,2654,2747,2796,2802,2859,2860 'paper-driven':7 'parallel':2854 'pars':1344,1973 'partial':2383,2392,2467 'pass':2382,2465,2777 'patch':2014,2136,2165,2900 'path':389,1446,1471,2207,2209 'pathlib':2205 'patient/case':504 'pattern':213,341,1196,2517,2626 'pct':1448,1564 'pdf':329,388,1453,1588,1604,1622,2119,2129,2959 'pdfs':1116,2803 'pdftoppm':1127,1610 'per':203,319,894,2785,3015 'percentag':3069 'perspect':2584 'phase':59,151,274,603,674,799,833,959,989,2573,2745,2751,2758,2763,2769,2780,2788 'photo':1890,1991 'phrase':898 'pick':269 'pictur':1558,1879 'pil':1128,1759 'pillow':1266 'pipelin':60 'pitfal':2693 'plain':845 'plain-languag':844 'plus':1102,1186 'pmid':392,741,751,762,793,3037 'png':1449,1550,1605,1876,2055,2061 'point':340,596,708,757,768,945,1301,2722,2725,2728 'polici':972,2914,3090 'polish':46 'posit':1360 'powerpoint':193,1334,1627,1632,1652,1881,1905,1999,2019,2022,2123 'ppt/media':2049,2415 'ppt/slides':2069,2429,2460 'ppt/slides/slide':2442 'pptx':1006,1014,1326,1556,1621,1964,2003,2142,2175,2233,2360,2486,2893 'practic':970,2611 'pre':2772 'pre-present':2771 'preattent':187 'precis':2712 'prefer':118,817,1547,1587,2163 'prefix':1615 'prepar':6,44,73,77,91,657,2577 'present':2,5,40,48,83,84,176,393,564,614,684,1080,2278,2507,2535,2740,2742,2773,2861,3003,3019 'present-pap':1,39 'preserv':1199,1261,1762,2903 'primari':311,483 'principl':198 'print':1599,1944 'prior':416,567,575,928 'proceed':602,988 'produc':438,1544,2385 'profil':836 'prohibit':2888 'project':1184,1595 'pronunci':129,867,873 'proven':1067 'publish':100 'pubm':2955 'pull':1113,1540 'purpos':43 'python':1013,1555,1620,1785,2002,2174,2232 'python-pptx':1012,1554,1619,2001,2173,2231 'python3':1206,2200 'q':71,655,2196,2575,2766,2872 'qa_prep.md':2762 'question':949,2578,2581,2598,2615 'quick':2659,2673 'quick_review.md':2474,2768 'quot':1460,1465,1467,1735,1755,1800 'r':1611 'radiolog':2889 'rais':1908 'rate':713 'rather':1117,3099 'raw':1147,1650 'rct':468 're':1660,2203 're-draft':1659 'read':160,200,220,434,2484 'reader':1677 'readi':2399 'reading-tim':199 'real':2100 'rebuild':2007,2016,2138,2179,2902 'recommend':3054 'record':2463,2778 'recoveri':1910 'red':2078 'ref':779,784,2686,2691 'refer':29,159,171,610,662,736,748,786,796,2666,2754,2800,2928,2944,2948,3025,3040 'references.md':2750 'references/critic_rubrics/slide.md':2367 'references/medical_presentation_templates.md':243 'references/slide_design_principles.md':174 'references/slide_visual_styles':282 'references/slide_visual_styles/nature_lancet.md':1109 'refin':2470 'regener':1980,2171 'regex':2072 'regex-strip':2071 'regex/sed':2164 'rel':2063,2064 'relev':932 'remain':1170 'rememb':236 'remov':1157,1288,2162 'render':1383,1968,2076 'replac':2059 'replic':625 'report':2852,2867,3086 'reporting-guidelin':2866 'request':957,3001 'requir':376,677,812,1404 'research':51,64,606,963,982 'reserv':2235 'respect':3002 'respons':1864 'restat':2649 'restor':2113 'restyl':1332,1396 'result':489,1499,2297,3067 'retent':1278 'review':641,985,1391,2660,2671,2674,2774,2926 'revis':2865 'reynold':175,356 'reynolds/knaflic/tufte':2842 'right':1032,1437,1441,1479,1568,1775,2302 'roc':2831 'role':1701 'rotat':1996 'rough':3011 'round':13,93,258,1045,1371,1746,1987,2471,2710 'row':1253,1260,1432,1529,1732,1734 'rpr':2066 'rq':2226 'rubric':2365,2783 'rule':111,659,1336,2545,2811,2821 'run':1149,1226,2117,2353,2361 'running-head':1225 's.replace':2215 'sampl':3074 'save':2331 'say':2709 'scale':634 'score':2368,2784,3070 'scratch':1868,2006,2178 'script':35,65,801,804,809,909,986,1180,1863,1870,2495,2502,2510,2525,2559,2761,2793,3005 'script.md':2757 'scripts/extract_pdf_figures.py':332 'scripts/inject_speaker_notes.py':2257 'sd':1813 'search':607,668 'second':238,1687 'section':244,420,951,1088,1410,1790,2379,2496,2989,2998 'see':1454,1636,2013 'seed':250 'segment':1185 'select':696,1331 'seminar':14,82 'senior':2924 'separ':2972 'sequenc':855 'seri':471 'session':417,568 'set':1562 'shadow':2863 'shape':1753 'share':353,2841 'sheet':2661,2775 'shift':224 'short':1049 'signal':862 'signatur':1197 'signific':523,732 'silent':1633,1882 'singl':1139,1497,1703,2664 'single-crop':1138 'single-pag':2663 'sip':2052 'size':495,1950,2090,3072,3075 'skill':42,54,168,215,352,364,1020,1053,1124,1151,1208,2255,2520,2808,2814,2818,2840 'skill-present-paper' 'skip':678,687 'slide':21,67,108,179,241,246,292,361,398,534,539,541,547,550,559,711,774,895,901,910,921,933,991,999,1064,1083,1086,1092,1095,1098,1101,1316,1339,1346,1378,1398,1409,1461,1496,1549,1575,1592,1679,1895,1943,1945,1975,2093,2185,2273,2329,2344,2351,2363,2370,2481,2489,2499,2552,2568,2708,2782,2786,2830,2848,2922,2930,2963,2970 'slide-by-slid':538 'slide-level':360,2847 'slide-typ':291,1397 'slide.notes_slide.notes_text_frame.text':2253 'slide_critic.md':2779 'slidenum':1772 'slot':1292 'smoke':1037 'smoke-test':1036 'sourc':25,778,783,1456,1531,1585,2681 'source-aperivue' 'sp3d':2131,2161 'spars':1234 'speaker':34,103,803,808,908,2250,2334,2494,2546,2760 'spec':285,1108 'specialti':402,850 'specialty-specif':849 'specif':706,755,766,851,2506,2601,2641 'specifi':350 'spoken':1664 'spoken-narr':1663 'srcrect':2102,2134,2449 'stabl':1340 'standard':2264,3093 'start':379,2980 'stat':2683,2688 'state':3096 'statist':124,775,780 'stem':965 'step':155,348,2349 'store':2230 'storytel':184 'strategi':608 'strengthen':612 'stricter':2025 'strip':2073 'structur':245,440,509,906,1008,1311,2265,2490,2620,2732 'students/trainees':2613 'studi':464,465,619,2286 'style':191,284,1058,1107,1285,1728,2910 'sub':1850,1853 'subgroup':515 'subhead':1718 'subject':476 'subtitl':1413,1424,1726,1795 'summar':700,941 'summari':505,644 'suppli':2146 'support':28,63,605,661,720,747,1136,1719,2642,2801 'suppress':860 'surfac':2870 'surgic':2153 'surround':1162 'survey':268,1075 'svg':1651 'sw':1840 'swap':2160 'sync':1896,2095,2437 'tabl':506,510,1029,1254,1259,1324,1426,1428,1517,1524,1727,1729,1797,2304 'tailor':2503,2513,2790 'take':588,936,1521,2322 'take-away':1520 'take-hom':587,935,2321 'takeaway':2718 'talk':23,96,260,1047,1051,2270 'target':400,1608,2984 'teal':1723,1730,1737,1793 'technic':135,823,2597 'techniqu':858 'templat':272,294,302,1017,1034,1076,1317,1400,1401,1565,1693,2245,2543,2882,2898 'templates/build_pptx_nature_lancet.py':326 'term':824,852 'terminolog':127,407 'tesseract':1263 'test':182,1038 'text':442,546,734,907,1027,1188,1235,1322,1329,1394,1416,1702,1704,1789,1810,2213,2221,2282,2290,2310,2325,2555,2672 'text-band':1187 'textbox':2155 'thank':946 'theme':2188 'three':170,1335 'tif':2051,2060,2417 'tiff':1630,1873,1884,2046,2413 'time':201,394,544,554,889,893,3004,3010 'titl':553,558,912,1082,1408,1412,1421,1430,1442,1466,1476,1500,1511,1525,1720,1722,1788,1844,1847,2272 'titlesofpart':1899,2089 'toc':1085 'token':1779 'top':1224,1358,1369,1982,1984 'topic':418,422,648 'topic-agent-skills' 'topic-biostatistics' 'topic-claude-code' 'topic-claude-skills' 'topic-clinical-research' 'topic-diagnostic-accuracy' 'topic-irb-protocol' 'topic-literature-review' 'topic-manuscript' 'topic-medical-ai' 'topic-medical-research' 'topic-meta-analysis' 'total':666 'touch':2561 'track':1361,1985 'transit':897,1091 'transpos':1770,1887,1995 'treat':2395 'trial':630,689 'true':2418 'tuft':189,358 'two':334,993,1015,1473,1482,1518,2293,2314 'type':293,467,685,1399 'typographi':288 'uncertain':3056,3095 'uncertainti':3098 'underlin':1724,1796 'understand':731,2488 'unedit':1389,1969 'unfamiliar':2617 'unit':1932 'unknown':461 'unless':2999 'unreli':1625 'unverifi':795,798,3039,3042 'unzip':2168,2195 'use':74,120,342,753,764,1011,1040,1068,1122,1181,1362,1402,1691,1816,2000,2823 'user':115,139,384,598,815,956,979,984,2145,2738,3063 'usual':1694 'valid':2115 'valu':716,777,782,1922,2086,2105,2452,2680,2685,2690,2711,2713,2716 'vector':1452,1584 'verbatim':1462,1671,1923,2114 'verifi':735,790,1269,2033,2565,2753,2884,2953,3030,3059 'version':1628 'via':1246,2243,2252,3031 'viewer':2042 'visual':283,1057,2874,2880 'visual-abstract':2879 'vs':460,2091 'walk':55 'wc':2444 'well':2319 'white':308,1059 'whitespac':1163 'widescreen':1582 'width':1576,2156 'window':2027 'wit':1464 'without':1993,2550 'word':3014 'work':2318 'workshop':20 'write':66 'x':2228,2697 'xml':1105,2070,2169,2430,2443,2461 'xx.xxxx':745 'xx.xxxx/xxxxx':744 'xxxxx':742,752,763 'y':1845,1851,1857,2699 'yaml':1143 'year':2645 'yellow':1745 'yes':2466 'zen':177 'zip':2225 'zone':1366,1829","prices":[{"id":"d2195245-d9f2-4df5-8df9-7ace995a03d2","listingId":"3d0128c9-91f7-4e53-811f-1b03dc19d7e4","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"Aperivue","category":"medsci-skills","install_from":"skills.sh"},"createdAt":"2026-05-13T12:57:46.076Z"}],"sources":[{"listingId":"3d0128c9-91f7-4e53-811f-1b03dc19d7e4","source":"github","sourceId":"Aperivue/medsci-skills/present-paper","sourceUrl":"https://github.com/Aperivue/medsci-skills/tree/main/skills/present-paper","isPrimary":false,"firstSeenAt":"2026-05-13T12:57:46.076Z","lastSeenAt":"2026-05-18T18:56:31.097Z"}],"details":{"listingId":"3d0128c9-91f7-4e53-811f-1b03dc19d7e4","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"Aperivue","slug":"present-paper","github":{"repo":"Aperivue/medsci-skills","stars":98,"topics":["agent-skills","biostatistics","claude-code","claude-skills","clinical-research","diagnostic-accuracy","irb-protocol","literature-review","manuscript","medical-ai","medical-research","meta-analysis","physician-researcher","prisma","pubmed","radiology","reporting-guidelines","strobe","systematic-review","tripod-ai"],"license":"other","html_url":"https://github.com/Aperivue/medsci-skills","pushed_at":"2026-05-17T20:50:52Z","description":"Claude Code skills for medical research — literature search, reporting guidelines, statistical analysis, publication figures. Built by a physician-researcher, tested on real publications. MIT licensed.","skill_md_sha":"520acd32951150d6d09ff1974010088e562ce693","skill_md_path":"skills/present-paper/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/Aperivue/medsci-skills/tree/main/skills/present-paper"},"layout":"multi","source":"github","category":"medsci-skills","frontmatter":{"name":"present-paper","description":"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 augments PPTX with speaker notes, and prepares Q&A."},"skills_sh_url":"https://skills.sh/Aperivue/medsci-skills/present-paper"},"updatedAt":"2026-05-18T18:56:31.097Z"}}