Agent skill
cardiology-content-repurposer
Transform long-form cardiology content (YouTube transcripts, newsletters, PDFs, knowledge bases) into high-quality thought leadership content across multiple formats. Use when the user wants to repurpose medical/cardiology content into: (1) Short newspaper articles (Inshorts style), (2) Atomic essays, (3) Tweets, (4) Twitter threads, or (5) Medium-style blogs. Maintains authentic interventional cardiologist voice with clinical authority, uses 4A framework, targets specific patient archetypes, and leverages PubMed for evidence-based citations when needed.
Install this agent skill to your Project
npx add-skill https://github.com/drshailesh88/integrated_content_OS/tree/main/skills/cardiology/cardiology-content-repurposer
SKILL.md
Cardiology Content Repurposer
Overview
Transform cardiology source material into engaging, evidence-based content that positions you as a thought leader while educating patients. Maintains clinical authority with conversational approachability.
When to Use This Skill
Use when the user provides:
- YouTube video transcripts about cardiology topics
- Medical newsletters or articles
- Knowledge from books/PDFs
- Any long-form medical content that needs repurposing for patient education
Core Workflow
Step 1: Analyze Source Material
Silently extract:
- Key points, themes, statistics, stories
- Clinical insights and evidence
- Multiple angles and subtopics
- Opportunities for different formats and archetypes
Step 2: Review Guidelines
Before writing, review:
references/voice-and-principles.mdfor authentic cardiologist voice, audience archetypes, and awareness levelsreferences/twitter-writing-guide.mdfor 4A framework, headline structures, and thread formattingreferences/content-formats.mdfor specific requirements of each output type
Step 3: Generate Content
Create content in this order (generate all applicable pieces from source):
-
Short Newspaper Articles (Inshorts style)
- Multiple pieces, <400 chars each
- See content-formats.md for specs
-
Atomic Essays
- Multiple pieces, 600-700 chars
- Use 4A framework for different angles
- See content-formats.md for specs
-
Tweets (Single)
- Multiple punchy tweets, 280 chars max
- Thought leadership, not random quotes
- See content-formats.md for specs
-
Twitter Threads
- Multiple threads, 4-12 tweets each
- Apply skimmability rhythms from twitter-writing-guide.md
- See content-formats.md for structure options
-
Blogs (Medium-style)
- 800-2000 words, in-depth
- Critical: If source is transcript/script without references, use PubMed to cite evidence
- See content-formats.md for citation requirements
Step 4: Apply Quality Standards
For every piece:
- Voice: Write as experienced interventional cardiologist with first-person authority
- No em-dashes: Avoid — unless absolutely necessary
- Natural language: Vary sentence structure, avoid AI patterns
- Audience fit: Only create content for archetypes where topic genuinely fits
- Awareness match: Only write for awareness levels that make sense for the topic
- No dumbing down: Audience isn't medical but isn't dumb
Step 5: PubMed Integration (for Blogs)
When source material is transcript/script without solid references:
- Identify factual claims needing backing
- Use
PubMed:search_articlesto find supporting evidence - Use
PubMed:get_article_metadatafor details - Cite naturally: [Study Name, Journal Year]
- Focus on RCTs, meta-analyses, major trials
Step 6: Present Output
List all generated content numbered by type:
SHORT NEWSPAPER ARTICLES
1. [Title]
[Body]
2. [Title]
[Body]
ATOMIC ESSAYS
1. [Title]
[Essay]
2. [Title]
[Essay]
TWEETS
1. [Tweet]
2. [Tweet]
TWITTER THREADS
Thread 1: [Theme]
• Tweet 1: [Hook]
• Tweet 2: [Content]
• Tweet 3: [Content]
• Tweet 4: [CTA]
BLOGS
Blog 1: [Title]
[Full blog with sections and citations]
Content Multiplication Strategy
Use modifiers to create variations:
- Tips, Stats, Steps, Lessons, Examples, Reasons, Mistakes, Questions, Stories, Benefits
Use 4A framework for angles:
- Actionable: "Here's how" (step-by-step)
- Analytical: "Show me numbers" (data-driven)
- Aspirational: "Make me believe" (stories)
- Anthropological: "Explain why" (psychology)
Critical Reminders
- Quality over quantity: Better to skip a format than force-fit content
- Thought leadership: Every piece should demonstrate expertise and add value
- Evidence-based: Use PubMed when making clinical claims in blogs
- Patient-centric: Translate medical jargon; speak directly to patients (you/your)
- Authentic voice: Sound like a real cardiologist, not AI
If No Source Provided
Politely ask: "Please provide the source material you'd like me to repurpose (transcript, newsletter, PDF, etc.)"
Iteration
If user requests changes, revise specifically and re-present. Only proceed on explicit 'proceed' or equivalent.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
pufferlib
This skill should be used when working with reinforcement learning tasks including high-performance RL training, custom environment development, vectorized parallel simulation, multi-agent systems, or integration with existing RL environments (Gymnasium, PettingZoo, Atari, Procgen, etc.). Use this skill for implementing PPO training, creating PufferEnv environments, optimizing RL performance, or developing policies with CNNs/LSTMs.
fluidsim
Framework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations including Navier-Stokes equations (2D/3D), shallow water equations, stratified flows, or when analyzing turbulence, vortex dynamics, or geophysical flows. Provides pseudospectral methods with FFT, HPC support, and comprehensive output analysis.
metabolomics-workbench-database
Access NIH Metabolomics Workbench via REST API (4,200+ studies). Query metabolites, RefMet nomenclature, MS/NMR data, m/z searches, study metadata, for metabolomics and biomarker discovery.
geniml
This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.
zinc-database
Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.
astropy
Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, world coordinate systems (WCS), and astronomical data analysis. Use when tasks involve coordinate transformations, unit conversions, FITS file manipulation, cosmological distance calculations, time scale conversions, or astronomical data processing.
Didn't find tool you were looking for?