consulting-frameworks
Consulting Frameworks
Select the reference file matching your task. Each contains procedural guidance, application steps, quality checks, and examples.
Framework Selection Guide
| Task | Reference File | Key Frameworks |
|---|---|---|
| Decompose a problem, build an issue tree, structure hypotheses | references/structuring.md | MECE, Issue Trees, Hypothesis-Driven |
| Write executive summaries, build storylines, craft action titles | references/communication.md | Pyramid Principle, SCR, Action Titles |
| Analyze markets, competitive dynamics, or growth options | references/strategy.md | Porter's Five Forces, TAM/SAM/SOM, Value Chain, 3 Horizons, Ansoff |
| Build business cases, evaluate investments, model costs | references/financial.md | NPV/IRR, Build/Buy/Partner, Zero-Based Budgeting, Should-Cost |
| Design accountability structures, operating models, processes | references/operational.md | RACI, Operating Model Canvas, Spans & Layers, Lean/Six Sigma |
Cross-Framework Patterns
Most consulting deliverables combine multiple frameworks:
- Market sizing = TAM/SAM/SOM (strategy) + MECE segmentation (structuring) + Pyramid Principle (communication)
- Due diligence = Porter's Five Forces (strategy) + Issue Tree (structuring) + NPV/IRR (financial)
- Business case = Build/Buy/Partner (financial) + RACI (operational) + SCR (communication)
- Transformation roadmap = Operating Model (operational) + 3 Horizons (strategy) + Hypothesis-Driven (structuring)
Read the primary reference file for your task, then pull from adjacent files as needed.
More from aznatkoiny/zai-skills
real-estate-investment
>
12x402-payments
|
11reinforcement-learning
|
10cpp-reinforcement-learning
|
9deep-learning
Comprehensive guide for Deep Learning with Keras 3 (Multi-Backend: JAX, TensorFlow, PyTorch). Use when building neural networks, CNNs for computer vision, RNNs/Transformers for NLP, time series forecasting, or generative models (VAEs, GANs). Covers model building (Sequential/Functional/Subclassing APIs), custom training loops, data augmentation, transfer learning, and production best practices.
8prompt-optimizer
Optimize prompts for Claude 4.x models using Anthropic's official best practices. Use when users want to improve, refine, or create effective prompts for Claude. Triggers include requests to optimize prompts, make prompts more effective, fix underperforming prompts, create system prompts, improve instruction following, reduce verbosity, control output formatting, or enhance agentic/tool-use behaviors. Also use when users report Claude is being too verbose, not following instructions, not using tools properly, or producing generic outputs.
8