Weaver
by stephenwinters81
Map-Reduce system for comprehensive reports and literature reviews. Breaks topic into chapters, researches each in parallel, then weaves into unified document. Use for deep research, reports, and synthesis.
Skill Details
Repository Files
2 files in this skill directory
name: weaver description: Map-Reduce system for comprehensive reports and literature reviews. Breaks topic into chapters, researches each in parallel, then weaves into unified document. Use for deep research, reports, and synthesis.
The Weaver: Deep Research Synthesis Protocol
When to Activate
Use this skill when the user requests:
- Comprehensive literature reviews
- Long-form reports or documents
- Deep research on complex topics
- Multi-chapter synthesis
- User explicitly mentions "weaver", "report", or "literature review"
Architecture
Map-Reduce with Editorial Synthesis
Phase 1: The Loom (Map)
- Planner agent breaks topic into Table of Contents
- Typically 5-10 chapters/sections
- Each chapter has clear scope and questions
Phase 2: Spinning (Execute)
- Spawn N parallel Worker agents (one per chapter)
- Each worker researches their chapter deeply
- Workers operate independently (no cross-talk)
Phase 3: Weaving (Reduce)
- Editor agent ingests all chapter reports
- Identifies gaps, contradictions, redundancies
- Stitches into coherent Master Document
- Adds transitions, executive summary, conclusions
Invocation
python3 ~/.claude/skills/weaver/weaver.py "Your research topic"
Options
python3 ~/.claude/skills/weaver/weaver.py "Your topic" --chapters 8 --output report.md
Example Usage
User: "Write a comprehensive report on Australia's critical minerals opportunity"
python3 ~/.claude/skills/weaver/weaver.py "Australia's critical minerals opportunity: resources, processing, markets, and policy"
Output Structure
1. Executive Summary
2. [Chapter 1 - from Worker 1]
3. [Chapter 2 - from Worker 2]
...
N. Conclusions and Recommendations
N+1. Sources and Further Reading
Why This Works
- Parallel Depth: Each chapter gets dedicated deep research
- No Context Limits: Workers don't share context, avoiding truncation
- Editorial Coherence: Final pass ensures unified voice and flow
- Comprehensive Coverage: Structured approach ensures no gaps
Requirements
- Claude Code CLI installed and authenticated (
claudecommand available) - Python package:
rich(for formatted output)
Related Skills
Dbt Transformation Patterns
Master dbt (data build tool) for analytics engineering with model organization, testing, documentation, and incremental strategies. Use when building data transformations, creating data models, or implementing analytics engineering best practices.
Clinical Decision Support
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug develo
Scientific Schematics
Create publication-quality scientific diagrams using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.
Mermaid Diagrams
Comprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams (domain modeling, object-oriented design), sequence diagrams (application flows, API interactions, code execution), flowcharts (processes, algorithms, user journeys), entity relationship diagrams (database schemas), C4 architecture diagrams (system context, containers, components), state diagrams, git graphs, pie charts,
Diagram Generation
Mermaid diagram generation for architecture visualization, data flow diagrams, and component relationships. Use for documentation, PR descriptions, and architectural analysis.
Scientific Schematics
Create publication-quality scientific diagrams using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.
Clinical Decision Support
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug develo
Materialize Docs
Materialize documentation for SQL syntax, data ingestion, concepts, and best practices. Use when users ask about Materialize queries, sources, sinks, views, or clusters.
Dbt Transformation Patterns
Master dbt (data build tool) for analytics engineering with model organization, testing, documentation, and incremental strategies. Use when building data transformations, creating data models, or implementing analytics engineering best practices.
Mermaidjs V11
Create diagrams and visualizations using Mermaid.js v11 syntax. Use when generating flowcharts, sequence diagrams, class diagrams, state diagrams, ER diagrams, Gantt charts, user journeys, timelines, architecture diagrams, or any of 24+ diagram types. Supports JavaScript API integration, CLI rendering to SVG/PNG/PDF, theming, configuration, and accessibility features. Essential for documentation, technical diagrams, project planning, system architecture, and visual communication.