medsci-skills 4.1.0

package/skills/fill-protocol/setup.sh

@@ -0,0 +1,162 @@
+#!/usr/bin/env bash
+# fill-protocol — environment setup
+#
+# Verifies and (optionally) installs the dependencies required by fill-protocol:
+#   - LibreOffice (only required for .doc → .docx conversion of legacy templates)
+#   - Python packages: docxtpl, python-docx, pyyaml
+#
+# Usage:
+#   bash setup.sh check         # report what is/isn't installed, do nothing
+#   bash setup.sh install       # install everything that's missing (asks before each step)
+#   bash setup.sh install --yes # install without prompting (for CI / Claude auto-install)
+#   bash setup.sh               # equivalent to `check`
+
+ACTION="${1:-check}"
+AUTO_YES=false
+[[ "${2:-}" == "--yes" ]] && AUTO_YES=true
+
+# ---------- helpers ----------
+
+prompt_yn() {
+    if $AUTO_YES; then return 0; fi
+    read -r -p "$1 [y/N] " answer
+    [[ "$answer" =~ ^[Yy]$ ]]
+}
+
+detect_os() {
+    case "$(uname -s)" in
+        Darwin)  echo "macos" ;;
+        Linux)
+            if command -v apt-get >/dev/null 2>&1; then echo "debian"
+            elif command -v dnf     >/dev/null 2>&1; then echo "fedora"
+            elif command -v pacman  >/dev/null 2>&1; then echo "arch"
+            else echo "linux-unknown"; fi
+            ;;
+        *) echo "unsupported" ;;
+    esac
+}
+
+find_soffice() {
+    for path in \
+        "/Applications/LibreOffice.app/Contents/MacOS/soffice" \
+        "/usr/bin/soffice" \
+        "/opt/homebrew/bin/soffice"; do
+        if [[ -x "$path" ]]; then echo "$path"; return 0; fi
+    done
+    if command -v soffice >/dev/null 2>&1; then
+        command -v soffice; return 0
+    fi
+    return 1
+}
+
+# ---------- check ----------
+
+OS=$(detect_os)
+echo "Detected OS: $OS"
+echo
+
+# 1. LibreOffice
+SOFFICE=$(find_soffice || true)
+if [[ -n "$SOFFICE" ]]; then
+    VER=$("$SOFFICE" --version 2>&1 | head -1 || echo "?")
+    echo "✅ LibreOffice: $SOFFICE"
+    echo "   $VER"
+    SOFFICE_OK=true
+else
+    echo "❌ LibreOffice: not installed"
+    echo "   (Only required for .doc → .docx conversion. .docx templates work without it.)"
+    SOFFICE_OK=false
+fi
+
+# 2. Python packages
+PYBIN="${PYTHON:-python3}"
+echo
+echo "Python: $($PYBIN --version 2>&1)"
+
+PY_MISSING=()
+for pkg in docx docxtpl yaml; do
+    if $PYBIN -c "import $pkg" 2>/dev/null; then
+        echo "✅ $pkg"
+    else
+        echo "❌ $pkg"
+        PY_MISSING+=("$pkg")
+    fi
+done
+
+# Map import-name → pip-name (function form for bash 3.2 compatibility — macOS default)
+pipname_for() {
+    case "$1" in
+        docx)    echo "python-docx" ;;
+        docxtpl) echo "docxtpl"    ;;
+        yaml)    echo "pyyaml"     ;;
+        *)       echo "$1"         ;;
+    esac
+}
+
+if [[ "$ACTION" == "check" ]]; then
+    echo
+    if $SOFFICE_OK && [[ ${#PY_MISSING[@]} -eq 0 ]]; then
+        echo "All dependencies present."
+        exit 0
+    else
+        echo "Run \`bash setup.sh install\` to install missing dependencies."
+        exit 1
+    fi
+fi
+
+# ---------- install ----------
+
+if [[ "$ACTION" != "install" ]]; then
+    echo "Unknown action: $ACTION (use 'check' or 'install')"
+    exit 2
+fi
+
+# Install LibreOffice if missing
+if ! $SOFFICE_OK; then
+    case "$OS" in
+        macos)
+            CMD="brew install --cask libreoffice"
+            ;;
+        debian)
+            CMD="sudo apt-get install -y libreoffice"
+            ;;
+        fedora)
+            CMD="sudo dnf install -y libreoffice"
+            ;;
+        arch)
+            CMD="sudo pacman -S --needed libreoffice-fresh"
+            ;;
+        *)
+            echo "❌ Cannot auto-install LibreOffice on $OS — install manually."
+            exit 3
+            ;;
+    esac
+    echo
+    echo "About to install LibreOffice (~700 MB):"
+    echo "  $CMD"
+    if prompt_yn "Proceed?"; then
+        eval "$CMD"
+    else
+        echo "Skipped LibreOffice install."
+    fi
+fi
+
+# Install Python packages if missing
+if [[ ${#PY_MISSING[@]} -gt 0 ]]; then
+    PIP_PKGS=""
+    for m in "${PY_MISSING[@]}"; do PIP_PKGS="$PIP_PKGS $(pipname_for "$m")"; done
+    PIP_CMD="$PYBIN -m pip install --user --break-system-packages$PIP_PKGS"
+    echo
+    echo "About to install Python packages:"
+    echo "  $PIP_CMD"
+    if prompt_yn "Proceed?"; then
+        eval "$PIP_CMD"
+    else
+        echo "Skipped Python package install."
+    fi
+fi
+
+echo
+echo "Re-running check…"
+echo
+exec bash "$0" check

package/skills/fill-protocol/skill.yml

@@ -0,0 +1,37 @@
+schema_version: 2
+name: fill-protocol
+layer: A
+owner_domain: form_filling
+
+when_to_use: "Fill an institutional Word (.doc/.docx) template (IRB protocol, ethics application, grant form) while preserving styles, tables, fonts, and page geometry."
+when_NOT_to_use: "Drafting the scientific content (use write-protocol); ICMJE COI forms (use fill-icmje-coi)."
+
+inputs:
+  - "institutional Word template"
+  - "content mapping (fill_*.yaml)"
+outputs:
+  - "filled .docx preserving the institutional template"
+deterministic_scripts:
+  - scripts/fill_form.py
+  - scripts/inspect_template.py
+  - scripts/doc_to_docx.py
+side_effects:
+  - writes_docx_forms
+downstream_consumers:
+  - render-pdf-doc
+forbidden_actions:
+  - rebuild_template_from_blank_document
+  - drop_template_styles_or_logos
+
+# v2.1 quality card
+purpose: "Render approved content into an institutional Word template without losing its layout, styles, or page geometry."
+safety_boundaries:
+  - "Operates on the original template (never rebuilds from a blank Document, which strips logos/headers/styles)."
+  - "CJK eastAsia fonts and table cantSplit are enforced for Korean templates."
+known_limitations:
+  - "Requires the institutional template file; cannot invent a missing one."
+  - "Content-controlled (SDT) fields may need manual handling in Word."
+validation_commands:
+  - "confirm [MISS] count is 0 after fill"
+  - "soffice --headless --convert-to pdf for visual check"
+evidence_surface: bundled_script

package/skills/find-cohort-gap/SKILL.md

@@ -0,0 +1,309 @@
+---
+name: find-cohort-gap
+description: >
+  Research gap finder for longitudinal cohort databases. Profiles cohort strengths,
+  matches PI expertise, scans literature saturation, and outputs ranked topic proposals
+  with gap evidence. Works with any cohort: NHIS, UK Biobank, institutional EMR, health
+  checkup registries, or disease-specific registries.
+triggers: cohort gap, research topic, DB 주제, 코호트 갭, gap analysis, 연구주제 찾기, find research gap, 주제 발굴
+tools: Read, Write, Edit, Bash, Grep, Glob
+model: opus
+---
+
+# Find-Cohort-Gap Skill
+
+You are assisting a medical researcher in systematically discovering novel, publishable
+research topics from a cohort database. Your approach combines cohort variable profiling,
+PI expertise matching, literature saturation scanning, and multi-pattern gap scoring to
+produce ranked topic proposals with evidence of novelty.
+
+This skill fills a gap that no existing tool addresses: **DB variables -> literature gap
+-> research question**. Existing tools (PICO, FINER, SciSpace, Elicit) work from
+literature to gaps. This skill works from the data outward.
+
+## Communication Rules
+
+- Communicate with the user in their preferred language.
+- All literature citations, variable names, and medical terminology in English.
+- Be direct about weak topics — kill early, save time.
+
+## Key Directories
+
+- **Output**: User-specified directory (default: current working directory)
+- **References**: `${CLAUDE_SKILL_DIR}/references/` for templates and rubrics
+
+---
+
+## Phase 0: Cohort Intake
+
+Collect cohort metadata. Use the template at `${CLAUDE_SKILL_DIR}/references/cohort_profile_template.md`.
+
+Required information:
+1. **Cohort name and setting** (institution, country, population type)
+2. **Sample size** (N at baseline, N with follow-up)
+3. **Time span** (enrollment period, follow-up duration, measurement intervals)
+4. **Variable categories** (demographics, labs, imaging, questionnaires, medications, procedures)
+5. **Endpoints available** (mortality, cancer incidence, cardiovascular events, hospitalization)
+6. **Special strengths** (serial measurements, linkage to national registries, unique population)
+7. **Known limitations** (healthy volunteer bias, attrition, missing data patterns)
+8. **Existing publications** from this cohort (if known — to avoid duplication)
+
+If the user provides a data dictionary file (Excel/CSV), read it to extract variable
+categories and construct the variable cluster map automatically.
+
+**Gate:** Present the cohort profile summary. Confirm before proceeding.
+
+---
+
+## Phase 1: PI/CA Profiling
+
+Profile the intended PI or corresponding author to find topic-expertise alignment.
+
+1. **Search PubMed** for the PI's recent publications (last 5 years).
+   - Use `/search-lit` E-utilities: `bash "$EUTILS" search "AuthorLastName AuthorFirstInitial[Author]" 30`
+   - Extract top keyword clusters from titles/abstracts.
+2. **Identify specialty signals**:
+   - Academic society positions (president, board member, editor)
+   - Subspecialty focus areas
+   - Preferred journal tiers
+3. **Build a PI keyword map**: 5-10 keyword clusters ranked by publication frequency.
+
+If no PI is specified, skip this phase and use variable clusters alone in Phase 2.
+
+**Output:** PI profile card (name, affiliation, top keywords, society roles, preferred journals).
+
+---
+
+## Phase 2: Intersection Matrix
+
+Cross cohort variable clusters with PI expertise to generate candidate topics.
+
+### Method
+
+Create a matrix: rows = DB variable clusters, columns = PI keyword clusters.
+Score each cell 0-3:
+- **3**: PI has published in this exact intersection (direct match)
+- **2**: PI's subspecialty covers this area (strong relevance)
+- **1**: Tangential connection (possible but needs framing)
+- **0**: No connection
+
+### Candidate Generation
+
+1. Extract all cells scoring 2-3 as primary candidates.
+2. For cells scoring 1, apply the **A-B substitution test**: "Has someone published
+   [this analysis] with [a different exposure/outcome] in a similar cohort?" If yes,
+   substituting the PI's specialty variable creates a viable candidate.
+3. Generate 20-40 candidate topic statements in PICO format:
+   - **P**: Population from the cohort
+   - **E**: Exposure/predictor variable(s)
+   - **C**: Comparison group
+   - **O**: Outcome (preferably hard endpoint)
+
+### Discipline Alignment Filter
+
+Before advancing candidates to saturation scanning, apply a discipline filter:
+
+- **Who is the intended first author?** Identify their department/specialty.
+- **Does the primary exposure variable belong to that discipline?** The first
+  author's specialty must align with the study's core variable. For example:
+  - Radiology first author → imaging variable must be the primary exposure
+  - Cardiology first author → cardiac biomarker or ECG finding as exposure
+  - Neurology first author → neurological variable or brain imaging as exposure
+- **Kill candidates where the primary exposure is outside the first author's
+  discipline.** A strong PI match alone is insufficient if the first author
+  cannot claim ownership of the core variable.
+
+This filter prevents generating topics where the first author's contribution
+is not defensible at the variable level.
+
+**Gate:** Present the intersection matrix and top 20 candidates (post-discipline
+filter). User selects 8-12 for saturation scanning.
+
+---
+
+## Phase 3: Literature Saturation Scan
+
+For each selected candidate, determine how saturated the literature is.
+
+### Search Strategy
+
+For each candidate:
+1. Build a PubMed query: `(exposure terms) AND (outcome terms) AND (cohort OR longitudinal OR prospective)`
+2. Execute search via `/search-lit` E-utilities.
+3. Count total results and classify:
+
+| Grade | Count | Longitudinal? | Interpretation |
+|-------|-------|---------------|----------------|
+| **Blue Ocean** | 0-2 papers | N/A | First report possible. Verify the topic has audience interest. |
+| **Green Field** | 3-10 papers, all cross-sectional | No longitudinal | **Optimal zone** — established interest, longitudinal gap wide open. |
+| **Yellow** | 10-30 papers | Some longitudinal | Viable only with very specific angle (unique population, novel endpoint). |
+| **Red** | 30+ papers or MA exists | Yes | Avoid unless doing NMA or using truly unique data. |
+
+### Critical Filter
+
+For each candidate in Green/Yellow, ask: **"Has anyone published this with serial/repeated
+measurements?"** If no — automatic upgrade by one grade.
+
+### "So What" Test
+
+For each candidate, articulate 2-3 potential clinical implications of the findings.
+If you cannot state why a clinician or policymaker would care about the result,
+the topic fails regardless of gap score.
+
+**Output:** Saturation table with grade, paper count, longitudinal gap status, and
+"So What" statement for each candidate.
+
+**Gate:** Present saturation results. User selects 3-5 finalists for deep scoring.
+
+---
+
+## Phase 4: 6-Pattern Scoring + Comparison Table
+
+Apply the 6-Pattern framework to each finalist. Score each pattern 0 or 1.
+
+### 6 Patterns (Universal)
+
+Read the detailed rubric at `${CLAUDE_SKILL_DIR}/references/pattern_scoring_rubric.md`.
+
+| # | Pattern | Question | Score 1 if... |
+|---|---------|----------|---------------|
+| P1 | **Longitudinal Advantage** | Does the cohort's serial/repeated measurement structure create a clear edge over existing cross-sectional studies? | Cohort has 3+ timepoints for key variables AND no prior study used serial data for this topic. |
+| P2 | **Endpoint Upgrade** | Can we escalate to a harder endpoint than existing studies? | Cohort links to mortality/cancer/CVD registries AND existing studies stop at surrogate endpoints. |
+| P3 | **Cohort Uniqueness** | Is the cohort's population, scale, or setting distinctive? | Largest in this population, unique ethnic group, screening-based (no referral bias), or novel linkage. |
+| P4 | **PI-Topic Alignment** | Does the PI's expertise and reputation strengthen this topic? | PI has society role or 5+ papers directly in this domain. Skip if no PI specified. |
+| P5 | **Comparison Table Gaps** | Does the THIS STUDY column show 3+ differences vs existing papers? | Build comparison table (see below). 3+ checkmarks in THIS STUDY that are absent in all prior papers. |
+| P6 | **Complementary Design** | Can this topic pair with another study from the same cohort? | Two studies using the same DB but different populations or complementary variables (e.g., viral vs non-viral). |
+
+### Comparison Table Construction
+
+For each finalist, build a table comparing the top 3-5 existing papers against THIS STUDY:
+
+```
+| Feature | Author1 (Year) | Author2 (Year) | Author3 (Year) | THIS STUDY |
+|---------|----------------|----------------|----------------|------------|
+| Design | Cross-sectional | Cohort (5yr) | Cross-sectional | Cohort (20yr) |
+| N | 3,200 | 8,500 | 12,000 | ~200,000 |
+| Serial data | No | No | No | Yes (avg 5 visits) |
+| Hard endpoint | Surrogate | Surrogate | All-cause mortality | CVD + all-cause mortality |
+| Population | Referral | General | Screening | Health checkup (no referral bias) |
+| Ethnicity | Western | Western | Asian (Japan) | Asian (Korea) |
+| Subgroup analysis | No | Age only | No | Age + sex + comorbidity |
+```
+
+### Score Interpretation
+
+| Total Score | Recommendation |
+|-------------|----------------|
+| 5-6 | Top-tier journal target (Lancet sub, JACC, J Hepatol level) |
+| 3-4 | Specialty journal target (solid publication) |
+| 1-2 | Restructure or kill — find a stronger angle before proceeding |
+
+**Gate:** Present scoring results and comparison tables. User approves final ranking.
+
+---
+
+## Phase 5: Feasibility Gate
+
+For each scored finalist, verify practical feasibility.
+
+### Checks
+
+1. **Sample size adequacy**:
+   - Cox regression: minimum 10 events per predictor variable (EPV rule)
+   - Logistic regression: same EPV rule
+   - For large cohorts (N>100K): warn about p-value inflation — statistically
+     significant results are nearly guaranteed, so focus on **effect size thresholds**
+     (e.g., HR >1.2 or <0.8 for clinical relevance)
+   - Consider negative control strategy (EPCV) for very large samples
+
+2. **Missing data**:
+   - Key exposure variable: <20% missing acceptable
+   - Key outcome: <5% missing
+   - If serial data: assess attrition pattern (MCAR/MAR/MNAR)
+
+3. **Follow-up adequacy**:
+   - Outcome must have plausible latency within available follow-up
+   - Cancer outcomes: minimum 5 years
+   - CVD events: minimum 3 years
+   - Mortality: minimum 5 years
+
+4. **Operational definition**:
+   - Can the exposure be defined from available variables?
+   - For claims data: ICD codes alone = 40-60% accuracy. Require combination
+     strategy (diagnosis + prescription + visit frequency + special codes)
+   - Cross-check expected prevalence against known epidemiological data
+
+5. **IRB/ethics**:
+   - Is the data already IRB-approved for this type of analysis?
+   - Any additional approvals needed for data linkage?
+
+6. **Disease Novelty Bonus** (informational, not Go/No-Go):
+   - Idiopathic etiology or debated mechanism → higher journal interest
+   - Established mechanism → needs stronger methodological novelty
+
+### Decision
+
+- **Go**: All checks pass.
+- **Conditional Go**: Minor issues solvable (e.g., missing data manageable with imputation).
+- **No-Go**: Fatal flaw (insufficient events, no valid endpoint, key variable unavailable).
+
+**Output:** Feasibility report for each finalist with Go/Conditional/No-Go status.
+
+---
+
+## Phase 6: Output — Ranked Proposals + One-Pagers
+
+Generate the final deliverables.
+
+### Ranked Summary Table
+
+```
+| Rank | Topic (PICO) | Saturation | 6-Pattern Score | Feasibility | Target Journal | Timeline |
+|------|--------------|------------|-----------------|-------------|----------------|----------|
+| 1 | ... | Green (0 longitudinal) | 5/6 | Go | JACC | 6 months |
+| 2 | ... | Green (1 longitudinal) | 4/6 | Go | Eur Heart J | 6 months |
+| 3 | ... | Blue (0 papers) | 3/6 | Conditional | Radiology | 8 months |
+```
+
+### One-Pager for Each Finalist
+
+Use the template at `${CLAUDE_SKILL_DIR}/references/onepager_template.md`.
+
+Each one-pager includes:
+1. **Title**: Working title for the study
+2. **Background**: 3-4 sentences establishing the gap (with "Zero Papers" claim if applicable)
+3. **Comparison Table**: THIS STUDY vs existing papers
+4. **Objective**: Primary research question in PICO format
+5. **Methods Summary**: Study design, key variables, statistical approach
+6. **PI Role**: Why this PI is the right corresponding author
+7. **Target Journal**: With rationale (PI alignment, scope match, gap fit)
+8. **Timeline**: Realistic estimate (data preparation → analysis → drafting → submission)
+9. **6-Pattern Score Card**: Visual breakdown of each pattern
+
+Save one-pagers as markdown files: `{output_dir}/gap_proposal_{rank}_{short_topic}.md`
+
+---
+
+## Skill Integration
+
+| Phase | Calls to other skills |
+|-------|----------------------|
+| Phase 1 (PI profiling) | `/search-lit` E-utilities for PubMed author search |
+| Phase 3 (Saturation scan) | `/search-lit` E-utilities for topic searches |
+| Phase 4 (Comparison table) | `/search-lit` for retrieving paper metadata |
+| **Downstream** | Output feeds into `/design-study` → `/write-paper` pipeline |
+
+## What This Skill Does NOT Do
+
+- Does not perform the actual statistical analysis (use `/analyze-stats`)
+- Does not write the full manuscript (use `/write-paper`)
+- Does not validate study design (use `/design-study`)
+- Does not generate references (use `/search-lit`)
+- Does not make publication-ready figures (use `/make-figures`)
+
+## Anti-Hallucination
+
+- **Never fabricate references.** All citations must be verified via `/search-lit` with confirmed DOI or PMID. Mark unverified references as `[UNVERIFIED - NEEDS MANUAL CHECK]`.
+- **Never invent clinical definitions, diagnostic criteria, or guideline recommendations.** If uncertain, flag with `[VERIFY]` and ask the user.
+- **Never fabricate numerical results** — compliance percentages, scores, effect sizes, or sample sizes must come from actual data or analysis output.
+- If a reporting guideline item, journal policy, or clinical standard is uncertain, state the uncertainty rather than guessing.

package/skills/find-cohort-gap/references/cohort_profile_template.md

@@ -0,0 +1,93 @@
+# Cohort Profile Template
+
+Fill in the sections below to describe the cohort database. This profile drives
+the intersection matrix and feasibility checks.
+
+---
+
+## Basic Information
+
+- **Cohort name:**
+- **Institution/Organization:**
+- **Country:**
+- **Population type:** (general population / health checkup / disease registry / claims data / hospital EMR)
+- **Enrollment period:** (e.g., 2002-2019)
+- **Total N at baseline:**
+- **N with follow-up data:**
+- **Mean/median follow-up duration:**
+- **Measurement intervals:** (e.g., annual, biennial, at-event)
+
+## Variable Categories
+
+Check all that apply and list key variables in each category:
+
+- [ ] **Demographics**: (age, sex, BMI, smoking, alcohol, exercise, income, education)
+- [ ] **Laboratory**: (CBC, metabolic panel, lipid panel, liver function, kidney function, tumor markers, HbA1c, ...)
+- [ ] **Imaging**: (chest X-ray, CT, ultrasound, DEXA, mammography, ...)
+- [ ] **Questionnaires**: (PHQ-9, IPAQ, diet, sleep, quality of life, ...)
+- [ ] **Vital signs**: (BP, heart rate, ...)
+- [ ] **Anthropometry**: (height, weight, waist circumference, body composition, ...)
+- [ ] **Medications**: (prescription records, drug categories, ...)
+- [ ] **Procedures**: (surgery codes, intervention records, ...)
+- [ ] **Diagnoses**: (ICD codes, physician diagnosis, ...)
+
+## Endpoints Available
+
+Check all that apply:
+
+- [ ] **All-cause mortality** (linkage to: ___)
+- [ ] **Cause-specific mortality** (categories: ___)
+- [ ] **Cancer incidence** (linkage to: ___)
+- [ ] **Cardiovascular events** (definition: ___)
+- [ ] **Hospitalization** (source: ___)
+- [ ] **Disease incidence** (ICD-based / physician-confirmed / registry)
+- [ ] **Other**: ___
+
+## Special Strengths
+
+What makes this cohort unique? (check all that apply)
+
+- [ ] **Serial measurements** (same variables measured repeatedly over time)
+- [ ] **Large scale** (>100K participants)
+- [ ] **Long follow-up** (>10 years)
+- [ ] **National registry linkage** (mortality, cancer, insurance claims)
+- [ ] **Screening-based** (no referral bias — general population health checkups)
+- [ ] **Unique population** (ethnicity, occupation, geography not well-studied)
+- [ ] **Rich phenotyping** (imaging + labs + questionnaires)
+- [ ] **Biobank/genetic data available**
+- [ ] **Other**: ___
+
+## Known Limitations
+
+- [ ] **Healthy volunteer bias** (participants may be healthier than general population)
+- [ ] **Attrition** (estimated dropout rate: ___%)
+- [ ] **Missing data** (key variables with >20% missing: ___)
+- [ ] **Limited demographics** (e.g., single sex, narrow age range, single institution)
+- [ ] **Claims-only diagnoses** (no clinical validation of ICD codes)
+- [ ] **No imaging data**
+- [ ] **No medication data**
+- [ ] **Other**: ___
+
+## Existing Publications
+
+List known papers already published from this cohort (to avoid topic duplication):
+
+1. (Author, Year, Topic, Journal)
+2. ...
+
+## Data Access
+
+- **IRB status:** (approved / needs application)
+- **Access method:** (on-site analysis center / remote access / direct download)
+- **Estimated turnaround:** (application to data receipt)
+- **Cost:** (if applicable)
+
+---
+
+## Variable Cluster Map (Auto-generated)
+
+If a data dictionary is provided, the skill will auto-generate clusters below:
+
+| Cluster | Variables | Serial? | Endpoint Link? |
+|---------|-----------|---------|----------------|
+| (auto-filled) | | | |

package/skills/find-cohort-gap/references/onepager_template.md

@@ -0,0 +1,84 @@
+# Research Topic Proposal — One-Pager
+
+## [Working Title]
+
+**Rank:** #X of Y | **6-Pattern Score:** X/6 | **Saturation Grade:** Green Field
+**Target Journal:** [Journal Name] | **Estimated Timeline:** X months
+
+---
+
+### Background
+
+[3-4 sentences establishing the clinical problem, current evidence gaps, and why this
+topic matters now. End with the "Zero Papers" claim if applicable: "To our knowledge,
+no study has examined [specific gap] using serial measurements in a [population type]."]
+
+### Comparison Table
+
+| Feature | Author1 (Year) | Author2 (Year) | Author3 (Year) | **THIS STUDY** |
+|---------|----------------|----------------|----------------|----------------|
+| Design | | | | |
+| N | | | | |
+| Serial data | | | | |
+| Hard endpoint | | | | |
+| Population | | | | |
+| Ethnicity | | | | |
+| Follow-up | | | | |
+| Key gap | | | | |
+
+**Unique differentiators: X** (minimum 3 required)
+
+### Objective
+
+**Primary:** [PICO format research question]
+
+**Secondary (optional):** [1-2 secondary questions]
+
+### Methods Summary
+
+- **Study design:** Retrospective cohort study
+- **Population:** [Inclusion/exclusion criteria]
+- **Exposure:** [Key variable(s) and operational definition]
+- **Outcome:** [Primary endpoint and ascertainment method]
+- **Statistical approach:** [Key methods — Cox regression, trajectory analysis, etc.]
+- **Sample size justification:** [N eligible, expected events, EPV ratio]
+
+### 6-Pattern Score Card
+
+| Pattern | Status | Evidence |
+|---------|--------|----------|
+| P1 Longitudinal Advantage | [+/-] | [one-line justification] |
+| P2 Endpoint Upgrade | [+/-] | [one-line justification] |
+| P3 Cohort Uniqueness | [+/-] | [one-line justification] |
+| P4 PI-Topic Alignment | [+/-] | [one-line justification] |
+| P5 Comparison Table 3+ | [+/-] | [one-line justification] |
+| P6 Complementary Design | [+/-] | [one-line justification] |
+
+### PI Role
+
+**Corresponding Author:** [Name, Title, Affiliation]
+**Relevance:** [Why this PI is the right CA — society role, expertise, journal connections]
+
+### Feasibility
+
+- **Go / Conditional Go / No-Go**
+- **Sample size:** N = X, expected events = Y, EPV = Z
+- **Key variables:** Available / needs derivation / missing
+- **IRB:** Covered / needs new application
+- **Data access:** Ready / X weeks to obtain
+
+### Timeline
+
+| Phase | Duration | Milestone |
+|-------|----------|-----------|
+| Data preparation | X weeks | Clean dataset, operational definitions |
+| Analysis | X weeks | Primary + sensitivity analyses |
+| Drafting | X weeks | Full manuscript |
+| Internal review | X weeks | Co-author feedback |
+| Submission | Target date | [Journal] |
+
+### Clinical Implications ("So What")
+
+1. [Implication for clinical practice]
+2. [Implication for screening/prevention policy]
+3. [Implication for future research directions]