Cardiology Trial Editorial Writer
Build thought leadership through evidence-based editorials on landmark cardiology trials, written in Eric Topol's authoritative Ground Truths style.
Core Workflow
Phase 1: Trial Discovery & Selection
Search target journals using PubMed:search_articles for recent publications (past 30-90 days):
- NEJM, JAMA, Lancet (tier 1 general)
- JACC, JACC: Cardiovascular Interventions, European Heart Journal (tier 1 cardiology)
- Circulation: Cardiovascular Interventions, EuroIntervention, JSCAI, CCI (interventional focus)
Score each trial using the importance scoring system (see references/trial-scoring.md):
- Extract metadata: design, sample size, endpoints, topic, novelty
- Calculate base score from design + sample + endpoints + topic + novelty
- Add venue bonus for top journals
- Optionally assess practice-change likelihood
- Sort by total importance_score
Present top candidates (top 3-5) to user with:
- Title, journal, publication date
- Importance score breakdown
- One-sentence summary of why it matters
- Ask user to select or request alternatives
Phase 2: Editorial Preparation
Once user approves a trial:
Determine content availability:
- Ask: "Do you have the full PDF, or should I work from the abstract?"
- If full text available via PubMed Central (PMCID), retrieve with PubMed:get_full_text_article
- If only abstract: work from PubMed:get_article_metadata
Gather contextual evidence:
- Search PubMed for prior landmark trials in same domain
- Identify 2-4 key comparator trials for context
- Extract relevant findings to position current trial
Analyze trial critically:
- Study design, population, intervention, endpoints
- Internal validity: randomization, blinding, missing data
- External validity: generalizability, exclusions, setting
- Statistical robustness: confidence intervals, subgroups
Phase 3: Editorial Writing
Follow the Eric Topol Ground Truths style (see references/topol-style-guide.md):
Structure (500 words, ~1500-1700 characters):
Opening hook (1-2 paragraphs):
- Start with clinical problem, not the trial
- Frame as bedside dilemma or unmet need
- Introduce trial as potential solution
Trial summary (1 tight paragraph):
- Population, intervention, comparator, design
- Primary outcome, headline effect size
- Keep numbers minimal and meaningful
Evidence quality (brief critical assessment):
- One paragraph on strengths ("why I trust this")
- One paragraph on limitations ("what makes me hesitate")
- Focus on validity and confidence, not trivia
Context and comparison:
- How this fits with prior trials
- Confirms trend, reverses evidence, or fills gap?
- Explain differences: population, endpoints, timing
Clinical implications (most important section):
- Who should change practice Monday?
- Who should wait for more data?
- Specific, actionable guidance
- Conditional but clear language
Unanswered questions:
- Important outcomes not measured
- Subgroups with unclear signals
- 1-2 concrete future research directions
Closing (one strong sentence):
- Memorable take-home message
- Balanced stance on practice change
Topol Style Elements:
- Authoritative but accessible voice
- Dense with scientific concepts, assume MD audience
- Evidence-grounded every claim with citations
- Balanced skepticism, never promotional
- Numbers: absolute risk differences, NNT/NNH
- Patient-centered: QOL, treatment burden, preferences
Critical Rules:
- ALWAYS cite using PubMed references with DOIs
- For claims about trials: cite specific PMID
- Never make unsupported assertions
- If working from abstract only, explicitly acknowledge limitations
- Use phrases like "if confirmed in full publication" when from abstract
- Maintain intellectual humility while projecting expertise
Phase 4: Visual Infographic Creation
After writing the editorial, create an engaging visual infographic slide (see references/infographic-design.md):
Purpose: Increase platform dwell time by providing visual summary for those who don't read full text
Format: Single-page HTML slide with embedded graphics (1200x1600px optimal for mobile/desktop)
Key Elements:
- Header section (compelling title + trial name)
- Visual data presentation (key finding with icon/graphic)
- 3-panel comparison (who benefits, who waits, what's unknown)
- Clinical bottom line (action item in highlighted box)
- Footer (citation + user attribution)
Design principles:
- Medical professional aesthetic (clean, evidence-based, not flashy)
- Color palette: cardiology blues (#1E3A8A, #3B82F6, #60A5FA) with accent (#EF4444 for warnings)
- Typography: Clear hierarchy, readable at mobile size
- Icons: Simple, medical-appropriate (heart, stethoscope, chart symbols)
- Data visualization: Bar charts, simple comparisons, clear numbers
- White space: Professional, not cluttered
Content structure:
┌─────────────────────────────────────┐
│ TRIAL NAME: Bold Finding │ ← Header
├─────────────────────────────────────┤
│ [ICON] KEY RESULT │ ← Hero metric
│ XX% vs YY% (p=0.00X) │
│ NNT = Z │
├─────────────────────────────────────┤
│ ✓ CHANGE PRACTICE ⚠ WAIT ❓UNKNOWN│ ← 3-panel
│ [details] [details] [gaps]│
├─────────────────────────────────────┤
│ 🎯 BOTTOM LINE: [actionable] │ ← Takeaway
├─────────────────────────────────────┤
│ Source: [Journal] | Dr. [Name] │ ← Attribution
└─────────────────────────────────────┘
Technical implementation:
- Create standalone HTML file with inline CSS
- Use simple SVG icons or Unicode symbols (♥, ⚕, 📊)
- Responsive design (flexbox/grid)
- No external dependencies
- Ready to screenshot or embed
Always deliver:
- Editorial text (500 words)
- HTML infographic file
- Brief note: "Screenshot this slide for social media posting"
Phase 5: Quality Assurance
Before delivering:
- Verify all citations link to actual PubMed articles
- Check word count (target 500 ± 50 words)
- Ensure character count fits 1500-1700 range
- Confirm Eric Topol voice consistency
- Validate that user appears as authoritative cardiologist
- Test infographic renders properly in browser
- Ensure infographic visual hierarchy is clear
Abstract-Only Workflow
When only abstract available (common for conference presentations or embargoed trials):
Set ethical boundaries upfront:
- Frame as "commentary on emerging result, not practice verdict"
- Never recommend standard-of-care change from abstract alone
- Use "promising but provisional" tone throughout
Mine abstract systematically:
- Background: clinical problem (can write confidently)
- Methods: extract headlines only (population, intervention, design, endpoint)
- Results: direction of effect, key numbers presented
- Explicitly note missing pieces: inclusion/exclusion details, statistical plan, safety profile
Structure shifts:
- Include "honesty paragraph": "As with any report available only in abstract form, important details are not yet accessible..."
- List 3-5 specific unknowns that matter most
- Talk implications as questions, not prescriptions
- Close with "wait but pay attention" message
Language safety:
- "Based on limited information currently available"
- "If these findings are confirmed in full report"
- "Abstract suggests, but does not yet establish"
- Avoid: "game changer", "paradigm shift", "definitive"
Alternative Paths
If user rejects machine's trial selection:
- Show next-ranked trials (positions 6-10)
- Ask user for specific topic preferences
- Search by user-specified criteria
- Offer manual trial entry (user provides PMID or abstract)
If no recent landmark trials:
- Search expanded timeframe (3-6 months)
- Consider meta-analyses or guidelines updates
- Look for high-impact controversies or debates
- Suggest editorial on emerging trends across multiple studies
Topic-specific editorial requests:
- User can specify: coronary intervention, structural heart, heart failure, EP, imaging
- Filter trials by topic_class before scoring
- Adjust scoring weights for user's subspecialty focus
Integration Points
PubMed MCP tools to use:
PubMed:search_articles - discover recent trials
PubMed:get_article_metadata - retrieve abstracts, titles, authors
PubMed:get_full_text_article - retrieve full text when PMCID available
PubMed:convert_article_ids - convert PMID to PMCID for full text check
PubMed:find_related_articles - discover prior trials for context
For each editorial:
- Minimum 3-5 PubMed citations
- At least 1 citation for the primary trial being discussed
- At least 2-3 citations for contextual prior trials
- Include DOIs in all references
Quality Standards
User portrayal:
- Trusted interventional cardiologist with deep expertise
- Well-read, synthesizing developments to guide peers
- Authority who knows the field comprehensively
- Thoughtful skeptic, not cheerleader
Audience assumption:
- Well-educated physicians (peers, juniors, seniors, referring MDs)
- Appreciate dense scientific concepts
- Value evidence-based analysis over opinion
- Want actionable insights for practice
Citation discipline:
- Every substantive claim grounded in Q1 journal references
- When needing context (e.g., PARTNER 1/2 for PARTNER 3 discussion), explicitly request additional references
- If user doesn't have references, search PubMed systematically
- Focus on: NEJM, JACC family, JAMA family, Lancet, BMJ, Circulation, JAHA, EHJ, similar tier-1
Success Metrics
A successful editorial delivery includes:
- Identifies genuinely important/landmark trial
- Provides critical evidence-based analysis
- Positions trial in broader literature context
- Offers specific, actionable clinical guidance
- Maintains Eric Topol's authoritative voice
- Cites all claims with high-quality references
- Portrays user as knowledgeable authority
- Fits 500-word, 1500-1700 character target
- Engages physician audience with dense concepts
- Balances enthusiasm with appropriate skepticism
- Delivers HTML infographic with clear visual hierarchy
- Infographic increases dwell time and engagement
Final Deliverables
For each editorial, always provide:
- Editorial text (500 words in markdown)
- HTML infographic file (1200×1600px, self-contained)
- Usage note: "Screenshot this infographic for social media posting (LinkedIn, Twitter, Instagram)"
- Reference list with PMIDs and DOIs
1---2name: cardiology-trial-editorial3description: "Identify landmark cardiology trials and write evidence-based editorials in Eric Topol's authoritative Ground Truths style. Use when the user wants to: (1) Discover and evaluate recent important trials from top cardiology journals (NEJM, JACC, Lancet, EHJ, Circulation), (2) Assess trial importance using systematic scoring, (3) Write 500-word editorials on cardiology/interventional cardiology advances for physician audiences, (4) Create thought leadership content that demonstrates deep domain expertise. Supports both full-text and abstract-only scenarios with PubMed integration for references."4metadata:5 source: https://skillmd.com/skills/drshailesh88/cardiology-trial-editorial6---78# Cardiology Trial Editorial Writer910Build thought leadership through evidence-based editorials on landmark cardiology trials, written in Eric Topol's authoritative Ground Truths style.1112## Core Workflow1314### Phase 1: Trial Discovery & Selection15161. **Search target journals** using PubMed:search_articles for recent publications (past 30-90 days):17 - NEJM, JAMA, Lancet (tier 1 general)18 - JACC, JACC: Cardiovascular Interventions, European Heart Journal (tier 1 cardiology)19 - Circulation: Cardiovascular Interventions, EuroIntervention, JSCAI, CCI (interventional focus)20212. **Score each trial** using the importance scoring system (see `references/trial-scoring.md`):22 - Extract metadata: design, sample size, endpoints, topic, novelty23 - Calculate base score from design + sample + endpoints + topic + novelty24 - Add venue bonus for top journals25 - Optionally assess practice-change likelihood26 - Sort by total importance_score27283. **Present top candidates** (top 3-5) to user with:29 - Title, journal, publication date30 - Importance score breakdown31 - One-sentence summary of why it matters32 - Ask user to select or request alternatives3334### Phase 2: Editorial Preparation3536Once user approves a trial:37381. **Determine content availability**:39 - Ask: "Do you have the full PDF, or should I work from the abstract?"40 - If full text available via PubMed Central (PMCID), retrieve with PubMed:get_full_text_article41 - If only abstract: work from PubMed:get_article_metadata42432. **Gather contextual evidence**:44 - Search PubMed for prior landmark trials in same domain45 - Identify 2-4 key comparator trials for context46 - Extract relevant findings to position current trial47483. **Analyze trial critically**:49 - Study design, population, intervention, endpoints50 - Internal validity: randomization, blinding, missing data51 - External validity: generalizability, exclusions, setting52 - Statistical robustness: confidence intervals, subgroups5354### Phase 3: Editorial Writing5556Follow the Eric Topol Ground Truths style (see `references/topol-style-guide.md`):5758**Structure (500 words, ~1500-1700 characters):**59601. **Opening hook** (1-2 paragraphs):61 - Start with clinical problem, not the trial62 - Frame as bedside dilemma or unmet need63 - Introduce trial as potential solution64652. **Trial summary** (1 tight paragraph):66 - Population, intervention, comparator, design67 - Primary outcome, headline effect size68 - Keep numbers minimal and meaningful69703. **Evidence quality** (brief critical assessment):71 - One paragraph on strengths ("why I trust this")72 - One paragraph on limitations ("what makes me hesitate")73 - Focus on validity and confidence, not trivia74754. **Context and comparison**:76 - How this fits with prior trials77 - Confirms trend, reverses evidence, or fills gap?78 - Explain differences: population, endpoints, timing79805. **Clinical implications** (most important section):81 - Who should change practice Monday?82 - Who should wait for more data?83 - Specific, actionable guidance84 - Conditional but clear language85866. **Unanswered questions**:87 - Important outcomes not measured88 - Subgroups with unclear signals89 - 1-2 concrete future research directions90917. **Closing** (one strong sentence):92 - Memorable take-home message93 - Balanced stance on practice change9495**Topol Style Elements:**96- Authoritative but accessible voice97- Dense with scientific concepts, assume MD audience98- Evidence-grounded every claim with citations99- Balanced skepticism, never promotional100- Numbers: absolute risk differences, NNT/NNH101- Patient-centered: QOL, treatment burden, preferences102103**Critical Rules:**104- ALWAYS cite using PubMed references with DOIs105- For claims about trials: cite specific PMID106- Never make unsupported assertions107- If working from abstract only, explicitly acknowledge limitations108- Use phrases like "if confirmed in full publication" when from abstract109- Maintain intellectual humility while projecting expertise110111### Phase 4: Visual Infographic Creation112113After writing the editorial, create an **engaging visual infographic slide** (see `references/infographic-design.md`):114115**Purpose:** Increase platform dwell time by providing visual summary for those who don't read full text116117**Format:** Single-page HTML slide with embedded graphics (1200x1600px optimal for mobile/desktop)118119**Key Elements:**1201. **Header section** (compelling title + trial name)1212. **Visual data presentation** (key finding with icon/graphic)1223. **3-panel comparison** (who benefits, who waits, what's unknown)1234. **Clinical bottom line** (action item in highlighted box)1245. **Footer** (citation + user attribution)125126**Design principles:**127- Medical professional aesthetic (clean, evidence-based, not flashy)128- Color palette: cardiology blues (#1E3A8A, #3B82F6, #60A5FA) with accent (#EF4444 for warnings)129- Typography: Clear hierarchy, readable at mobile size130- Icons: Simple, medical-appropriate (heart, stethoscope, chart symbols)131- Data visualization: Bar charts, simple comparisons, clear numbers132- White space: Professional, not cluttered133134**Content structure:**135```136┌─────────────────────────────────────┐137│ TRIAL NAME: Bold Finding │ ← Header138├─────────────────────────────────────┤139│ [ICON] KEY RESULT │ ← Hero metric140│ XX% vs YY% (p=0.00X) │141│ NNT = Z │142├─────────────────────────────────────┤143│ ✓ CHANGE PRACTICE ⚠ WAIT ❓UNKNOWN│ ← 3-panel144│ [details] [details] [gaps]│145├─────────────────────────────────────┤146│ 🎯 BOTTOM LINE: [actionable] │ ← Takeaway147├─────────────────────────────────────┤148│ Source: [Journal] | Dr. [Name] │ ← Attribution149└─────────────────────────────────────┘150```151152**Technical implementation:**153- Create standalone HTML file with inline CSS154- Use simple SVG icons or Unicode symbols (♥, ⚕, 📊)155- Responsive design (flexbox/grid)156- No external dependencies157- Ready to screenshot or embed158159**Always deliver:**1601. Editorial text (500 words)1612. HTML infographic file1623. Brief note: "Screenshot this slide for social media posting"163164### Phase 5: Quality Assurance165166Before delivering:1671. Verify all citations link to actual PubMed articles1682. Check word count (target 500 ± 50 words)1693. Ensure character count fits 1500-1700 range1704. Confirm Eric Topol voice consistency1715. Validate that user appears as authoritative cardiologist1726. Test infographic renders properly in browser1737. Ensure infographic visual hierarchy is clear174175## Abstract-Only Workflow176177When only abstract available (common for conference presentations or embargoed trials):1781791. **Set ethical boundaries upfront**:180 - Frame as "commentary on emerging result, not practice verdict"181 - Never recommend standard-of-care change from abstract alone182 - Use "promising but provisional" tone throughout1831842. **Mine abstract systematically**:185 - Background: clinical problem (can write confidently)186 - Methods: extract headlines only (population, intervention, design, endpoint)187 - Results: direction of effect, key numbers presented188 - Explicitly note missing pieces: inclusion/exclusion details, statistical plan, safety profile1891903. **Structure shifts**:191 - Include "honesty paragraph": "As with any report available only in abstract form, important details are not yet accessible..."192 - List 3-5 specific unknowns that matter most193 - Talk implications as questions, not prescriptions194 - Close with "wait but pay attention" message1951964. **Language safety**:197 - "Based on limited information currently available"198 - "If these findings are confirmed in full report"199 - "Abstract suggests, but does not yet establish"200 - Avoid: "game changer", "paradigm shift", "definitive"201202## Alternative Paths203204**If user rejects machine's trial selection:**205- Show next-ranked trials (positions 6-10)206- Ask user for specific topic preferences207- Search by user-specified criteria208- Offer manual trial entry (user provides PMID or abstract)209210**If no recent landmark trials:**211- Search expanded timeframe (3-6 months)212- Consider meta-analyses or guidelines updates213- Look for high-impact controversies or debates214- Suggest editorial on emerging trends across multiple studies215216**Topic-specific editorial requests:**217- User can specify: coronary intervention, structural heart, heart failure, EP, imaging218- Filter trials by topic_class before scoring219- Adjust scoring weights for user's subspecialty focus220221## Integration Points222223**PubMed MCP tools to use:**224- `PubMed:search_articles` - discover recent trials225- `PubMed:get_article_metadata` - retrieve abstracts, titles, authors226- `PubMed:get_full_text_article` - retrieve full text when PMCID available227- `PubMed:convert_article_ids` - convert PMID to PMCID for full text check228- `PubMed:find_related_articles` - discover prior trials for context229230**For each editorial:**231- Minimum 3-5 PubMed citations232- At least 1 citation for the primary trial being discussed233- At least 2-3 citations for contextual prior trials234- Include DOIs in all references235236## Quality Standards237238**User portrayal:**239- Trusted interventional cardiologist with deep expertise240- Well-read, synthesizing developments to guide peers241- Authority who knows the field comprehensively242- Thoughtful skeptic, not cheerleader243244**Audience assumption:**245- Well-educated physicians (peers, juniors, seniors, referring MDs)246- Appreciate dense scientific concepts247- Value evidence-based analysis over opinion248- Want actionable insights for practice249250**Citation discipline:**251- Every substantive claim grounded in Q1 journal references252- When needing context (e.g., PARTNER 1/2 for PARTNER 3 discussion), explicitly request additional references253- If user doesn't have references, search PubMed systematically254- Focus on: NEJM, JACC family, JAMA family, Lancet, BMJ, Circulation, JAHA, EHJ, similar tier-1255256## Success Metrics257258A successful editorial delivery includes:2591. Identifies genuinely important/landmark trial2602. Provides critical evidence-based analysis2613. Positions trial in broader literature context2624. Offers specific, actionable clinical guidance2635. Maintains Eric Topol's authoritative voice2646. Cites all claims with high-quality references2657. Portrays user as knowledgeable authority2668. Fits 500-word, 1500-1700 character target2679. Engages physician audience with dense concepts26810. Balances enthusiasm with appropriate skepticism26911. **Delivers HTML infographic with clear visual hierarchy**27012. **Infographic increases dwell time and engagement**271272## Final Deliverables273274For each editorial, always provide:2751. **Editorial text** (500 words in markdown)2762. **HTML infographic file** (1200×1600px, self-contained)2773. **Usage note**: "Screenshot this infographic for social media posting (LinkedIn, Twitter, Instagram)"2784. **Reference list** with PMIDs and DOIs