メニュー
Parallel search across PubMed, Perplexity, and your knowledge base. Searches all sources simultaneously and synthesizes findings with citations. Faster evidence gathering for clinical questions.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Transforms research and knowledge base material into information-dense infographic copy—clear, scannable, authoritative, and reference-worthy. Use when converting clinical algorithms, decision trees, comparison data (drug vs drug, treatment options), trial results, myth vs truth content, patient preparation guides, checklists, or sequential process workflows into structured copy ready for single-image infographic formats. Supports multiple infographic types including hero stats, dense multi-section layouts, side-by-side comparisons, myth-busters, step-by-step processes, and patient checklists. Outputs structured copy with compressed noun-heavy phrasing, specific numbers, trial citations, and JSON-formatted handoff data for downstream infographic generation.
Manages all other skills by detecting capability gaps, proposing new skills, and keeping the system registry in sync. Use when the user encounters something the system cannot do, wants to log a capability gap, review the skill backlog, propose or build a new skill, analyze recurring unmet needs, or run sync pipelines to update context files (CLAUDE.md, GEMINI.md, AGENTS.md) after skill changes.
Template-driven medical infographics using the AntV Infographic framework. Use when creating structured infographics from clinical data, trial results, or patient education content using pre-built templates for hero stats, comparison layouts, process flows, myth-busters, and checklists. Outputs publication-ready HTML/PNG infographics with JACC/NEJM-grade design tokens.
Declarative, grammar-based charting using AntV G2 for complex medical visualizations. Use when creating forest plots, Kaplan-Meier curves, funnel plots, waterfall charts, or any statistical/clinical chart that requires grammar-of-graphics composition with medical-journal-grade styling and accessibility-validated color palettes.
Publication-grade design tokens and utilities for Nature/JACC/NEJM quality graphics. Use when generating charts, infographics, animations, or any visual content that requires medical-journal-grade color palettes, typography, accessibility-validated contrast ratios, and consistent branding. Provides Python token APIs, colorblind-safe palettes, G2 chart templates, AntV infographic templates, Vizzu animation presets, and Manim integration for animated medical explainers.
Content OS orchestrator - the master skill that produces ALL content types from one seed idea (forward mode) or splits long-form content into short-form pieces (backward mode). Invokes research, writing, quality review, and visual generation skills in a coordinated pipeline. Long-form content goes through full quality gates; short-form gets quick accuracy pass.
| name | parallel-literature-search |
| description | Parallel search across PubMed, Perplexity, and your knowledge base. Searches all sources simultaneously and synthesizes findings with citations. Faster evidence gathering for clinical questions. |
All sources at once. This skill searches PubMed, web, and your RAG knowledge base in parallel, then synthesizes the findings into a single coherent summary with citations.
| Source | What It Searches | Output |
|---|---|---|
| PubMed | Academic literature, trials, reviews | PMIDs, abstracts, citations |
| Perplexity | Web, recent news, guidelines | Summaries with sources |
| RAG (AstraDB) | Your curated knowledge base | Guideline excerpts, textbook refs |
| Approach | Sources | Time | Depth |
|---|---|---|---|
| Sequential search | One at a time | 5+ min | Deeper but slow |
| Parallel search | All at once | 30-60 sec | Fast overview |
| Manual search | You do it | 20+ min | Variable |
Use this skill when you say:
"Parallel search: SGLT2 inhibitors in HFpEF"
"Find all evidence on GLP-1 and cardiovascular outcomes"
"What does literature say about statin discontinuation?"
# Basic search
python scripts/parallel_search.py --query "SGLT2 inhibitors heart failure"
# Specify sources
python scripts/parallel_search.py --query "GLP-1 cardiovascular" --sources pubmed,perplexity
# Save output
python scripts/parallel_search.py --query "CAC scoring" --output ~/research/
# Literature Search: SGLT2 Inhibitors in HFpEF
**Query:** SGLT2 inhibitors heart failure preserved ejection fraction
**Searched:** 2025-01-01 09:30:45
**Sources:** PubMed, Perplexity, RAG
---
## SYNTHESIS
SGLT2 inhibitors have demonstrated significant benefit in HFpEF based on
EMPEROR-Preserved and DELIVER trials. Key findings:
1. **EMPEROR-Preserved (PMID: 34449189)**: Empagliflozin reduced composite
endpoint of CV death/HHF by 21% (HR 0.79, 95% CI 0.69-0.90)
2. **DELIVER (PMID: 36027570)**: Dapagliflozin showed 18% reduction in
worsening HF/CV death (HR 0.82, 95% CI 0.73-0.92)
3. Current guidelines (ACC/AHA 2022) recommend SGLT2i as Class 2a for HFpEF.
---
## PUBMED RESULTS (5 most relevant)
| # | Title | PMID | Year | Type |
|---|-------|------|------|------|
| 1 | Empagliflozin in HFpEF | 34449189 | 2021 | RCT |
| 2 | Dapagliflozin in HFpEF | 36027570 | 2022 | RCT |
| 3 | Meta-analysis SGLT2i HF | 37654321 | 2023 | MA |
| 4 | Real-world SGLT2i outcomes | 38765432 | 2024 | Obs |
| 5 | SGLT2i mechanism review | 39876543 | 2024 | Rev |
---
## WEB RESULTS (Perplexity)
- **ACC 2024 Update**: New data on SGLT2i in cardiorenal syndrome
- **ESC Guidelines 2023**: Updated recommendations for SGLT2i
- **Clinical Practice**: Real-world prescribing patterns
---
## RAG RESULTS (Your Knowledge Base)
- **Braunwald Ch. 27**: Heart failure classification and treatment
- **ACC/AHA HF Guidelines**: Class recommendations for SGLT2i
- **ESC HF Guidelines**: European perspective on SGLT2i use
---
## EVIDENCE QUALITY
| Source | Strength | Notes |
|--------|----------|-------|
| EMPEROR-Preserved | High | Large RCT, well-conducted |
| DELIVER | High | Large RCT, confirmatory |
| Meta-analyses | High | Consistent findings |
| Real-world | Moderate | Observational limitations |
---
## KEY CITATIONS
1. Anker SD, et al. N Engl J Med. 2021;385:1451-1461. (PMID: 34449189)
2. Solomon SD, et al. N Engl J Med. 2022;387:1089-1098. (PMID: 36027570)
3. Vaduganathan M, et al. Lancet. 2022;400:757-767. (Meta-analysis)
---
## GAPS & CONSIDERATIONS
- Limited data in specific HFpEF phenotypes
- Long-term safety data still accumulating
- Indian-specific data limited (consider local studies)
User Query
│
├──────────────────┬──────────────────┐
│ │ │
▼ ▼ ▼
[PubMed Agent] [Perplexity Agent] [RAG Agent]
│ │ │
▼ ▼ ▼
PMIDs & Web sources Guideline
Abstracts & summaries excerpts
│ │ │
└──────────────────┴──────────────────┘
│
▼
[Synthesis Agent]
│
▼
Unified Report with
Citations & Evidence
quick-topic-researcher - Quick overviewdeep-researcher - Comprehensive reviewyoutube-script-master - Evidence for scriptscardiology-editorial - Literature for editorials# Core
anthropic>=0.18.0
python-dotenv>=1.0.0
rich>=13.0.0
# Already have these via your setup
# PubMed MCP - configured in .mcp.json
# Perplexity - via OpenRouter or MCP
| Key | Purpose | Status |
|---|---|---|
| ANTHROPIC_API_KEY | Synthesis | Already have |
| NCBI_API_KEY | PubMed (via MCP) | Already have |
| PERPLEXITY_API_KEY | Web search | Already have |
When user asks for literature/evidence:
Extract:
# PubMed (via MCP)
pubmed_search_articles(queryTerm="SGLT2 inhibitors heart failure", maxResults=10)
# Perplexity (via MCP or API)
perplexity_ask(messages=[{"role": "user", "content": "Latest evidence on SGLT2 inhibitors in heart failure 2024"}])
# RAG (if available)
# Query AstraDB for relevant guidelines
Combine findings from all sources into:
Structured report with:
The skill recognizes PICO format:
| Component | Example | How It's Used |
|---|---|---|
| Patient | "elderly patients with HFpEF" | Filters PubMed |
| Intervention | "SGLT2 inhibitors" | Primary search term |
| Comparison | "vs placebo" | Narrows to RCTs |
| Outcome | "mortality" | Focuses results |
# Basic clinical question
"SGLT2 inhibitors in heart failure"
# PICO format
"In elderly patients with HFpEF, do SGLT2 inhibitors reduce mortality compared to placebo?"
# Specific trial
"What are the key findings from EMPEROR-Preserved?"
# Guideline-focused
"Current ACC/AHA recommendations for SGLT2i in heart failure"
# Comparative
"SGLT2i vs GLP-1 for cardiovascular outcomes in diabetes"
This skill gives you evidence from multiple sources in under a minute - perfect for content preparation and quick clinical questions.