Zwicky Strategic Analyst
by cmsodi
|
Skill Details
Repository Files
3 files in this skill directory
name: zwicky-strategic-analyst description: | Generate strategic reports using Advanced Morphological Analysis (Zwicky Box), 4Dimensions© ontology, TRIZ problem-solving, and Minto Pyramid communication.
Use when:
- Creating strategic analysis on complex topics (space, defense, policy, technology)
- Generating scenario analysis for decision-making
- Building executive reports with morphological methodology
- Analyzing trade-offs and contradictions using TRIZ principles
- User mentions "Zwicky", "morphological analysis", "4Dimensions", "strategic scenarios"
Output: Professional reports in Markdown, Word (.docx), PowerPoint (.pptx), or Excel (.xlsx)
Zwicky Strategic Analyst
Generate executive-ready strategic reports using Advanced Morphological Analysis.
Overview
This skill transforms complex strategic topics into structured analysis using:
- 4Dimensions© Ontology: Material, Formal, Efficient, Final causes across 4 levels
- Zwicky Box: Morphological analysis for scenario generation
- TRIZ: Inventive problem-solving for contradiction resolution
- Minto Pyramid: Clear communication structure
Workflow
Execute the full pipeline in a single pass. Do not ask for "OK" between steps.
Step 1: Generate 4×4 Strategic Matrix
Create a 16-cell matrix mapping the topic through:
Columns (Levels):
- Foundational: Universal substrates, basic principles
- Subsystem: Components, specifications
- System: Integrated platforms, processes
- Supersystem: Networks, governance, coordination
Rows (Dimensions):
- Material: Physical assets, hardware, technologies
- Formal: Frameworks, software, standards, laws
- Efficient: ONLY human agents/organizations
- Final: Purposes, missions, objectives
Output: Markdown table with 5+ bullet points per cell.
Step 2: Select Strategic Features
From the matrix, identify 3 Features (variables) with strategic optionality:
- Each Feature has exactly 3 Variants (mutually exclusive options)
- Features must be independent of each other
- Check: Constants (fixed) vs Variables (genuine choices)
Output format per Feature:
- Feature Name
- Source Cell (e.g., Material/System)
- Strategic Question
- Justification
- Three Variants listed
Step 3: Generate Scenarios YAML
Transform features into YAML configuration:
topic: "{topic}"
dimensions:
Feature1:
- {name: "Variant_A", weight: 9}
- {name: "Variant_B", weight: 6}
- {name: "Variant_C", weight: 3}
Feature2:
- {name: "Variant_X", weight: 8}
- {name: "Variant_Y", weight: 5}
- {name: "Variant_Z", weight: 2}
Feature3:
- {name: "Option_1", weight: 7}
- {name: "Option_2", weight: 4}
- {name: "Option_3", weight: 1}
constraints:
- ["Variant_A", "Variant_X"] # Physically/logically incompatible
Weight assignment: 1-10 based on alignment with stated objective. Higher = better fit.
Step 4: Run Zwicky Engine
Execute scripts/zwicky_engine.py with the YAML to generate:
- All valid combinations (excluding constrained pairs)
- Scenarios ranked by total score
- Top 3 scenarios for detailed analysis
Step 5: TRIZ Brainstorming (Top 3 Scenarios)
For EACH of the top 3 scenarios:
- Scenario Visualization: Describe how the combination works in practice
- 4Dimensions Check: Map back to System/Supersystem levels
- TRIZ Analysis:
- Identify the contradiction (e.g., "High X but low Y")
- Select a TRIZ principle to resolve it:
- #1 Segmentation
- #2 Taking out
- #10 Action in advance
- #15 Dynamics
- #25 Self-service
- (or any of the 40 principles)
- Apply the solution concretely
Step 6: Strategic Merging
Compare the 3 scenarios:
- Overlap Matrix: Shared dimensions per pair (X/3), difference type (incremental/radical)
- Compatibility Verdict: COMPATIBLE / ALTERNATIVE / PARTIAL
- Structure Selection:
- Structure A (Alternatives): For mutually exclusive options
- Structure B (Integrated): For compatible components
- Minto Premises:
- Situation: Current undeniable state
- Complication: Why action is needed now
- Solution: Core recommendation
Step 7: Create 3×3×3 Outline
Structure following Minto Pyramid:
Introduction (S-C-Q-A)
├── Section 1: Primary Component/Argument
│ ├── 1.1 [Specific content]
│ ├── 1.2 [Specific content]
│ └── 1.3 [Specific content]
├── Section 2: Secondary Component/Argument
│ ├── 2.1 [Specific content]
│ ├── 2.2 [Specific content]
│ └── 2.3 [Specific content]
└── Section 3: Evolution/Impact/Forward-Looking
├── 3.1 [Specific content]
├── 3.2 [Specific content]
└── 3.3 [Specific content]
Step 8: Write Final Report
Expand outline into full prose:
- Executive Summary at top
- Reference 4Dimensions in each section
- Concrete Roadmap (Who/What/When)
- Minimum 2000 words
- Authoritative, concise, insightful tone
Output Format Selection
Based on user request, generate appropriate output:
Markdown (default): Full report in chat Word (.docx): Use docx skill for professional formatting PowerPoint (.pptx): Use pptx skill for 10-slide executive deck Excel (.xlsx): Use xlsx skill for interactive matrix
Ontological Rules (STRICT)
- Material Cause: Hardware, resources, technologies. Test benches are Material/Formal composites.
- Formal Cause: Software, algorithms, standards, laws, designs. Software is ALWAYS Formal.
- Efficient Cause: ONLY humans/organizations. AI/robots are NEVER Efficient causes.
- Final Cause: Purposes, missions, strategic goals.
References
For detailed guidance on specific aspects:
references/4dimensions_ontology.md: Full ontology documentationreferences/triz_principles.md: All 40 TRIZ principles with examplesreferences/minto_templates.md: Minto Pyramid templates
Example Invocation
User: "Create a strategic report on European Space Launch Autonomy for EU policy makers. Focus on 5-year horizon with budget constraints."
Claude: [Executes full pipeline, generates report with specific recommendations]
Related Skills
Attack Tree Construction
Build comprehensive attack trees to visualize threat paths. Use when mapping attack scenarios, identifying defense gaps, or communicating security risks to stakeholders.
Grafana Dashboards
Create and manage production Grafana dashboards for real-time visualization of system and application metrics. Use when building monitoring dashboards, visualizing metrics, or creating operational observability interfaces.
Matplotlib
Foundational plotting library. Create line plots, scatter, bar, histograms, heatmaps, 3D, subplots, export PNG/PDF/SVG, for scientific visualization and publication figures.
Scientific Visualization
Create publication figures with matplotlib/seaborn/plotly. Multi-panel layouts, error bars, significance markers, colorblind-safe, export PDF/EPS/TIFF, for journal-ready scientific plots.
Seaborn
Statistical visualization. Scatter, box, violin, heatmaps, pair plots, regression, correlation matrices, KDE, faceted plots, for exploratory analysis and publication figures.
Shap
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model
Pydeseq2
Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis.
Query Writing
For writing and executing SQL queries - from simple single-table queries to complex multi-table JOINs and aggregations
Pydeseq2
Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis.
Scientific Visualization
Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib/seaborn/plotly with publication styles. For quick exploration use seaborn or plotly directly.
