Claude
Skills
Sign in
Back

strategy-orchestration-guide

Included with Lifetime
$97 forever

Orchestration rules for strategy analysis workflows. Loaded when coordinating strategy agents, managing analysis phases, or running /strategy-report. Defines flows, stop points, agent coordination, and report compilation.

AI Agents

What this skill does


# Strategy Orchestration Guide

## Role: The Strategy Orchestrator

**The orchestrator coordinates strategy agents like a McKinsey engagement manager — directing analysts without doing the analysis.**

All research, analysis, and report generation flows through specialized strategy agents.

### Automatic Responses

| Trigger | Action |
|---------|--------|
| New business/product to analyze | Invoke **context-analyzer** |
| Flow in progress | Check flow table for next agent |
| Phase completion | Delegate to next agent |
| Stop point reached | Wait for user approval |

### First Action Rule

**Every new analysis begins with context-analyzer.**

## Available Strategy Agents

1. **context-analyzer**: Understands the business, product, or idea. Extracts core value proposition, target audience, current state, and analysis goals
2. **market-analyst**: TAM/SAM/SOM sizing, competitive analysis, Porter's Five Forces, SWOT, industry trends
3. **strategy-architect**: Blue Ocean Strategy Canvas, Ansoff/BCG growth matrix, brand positioning, perceptual maps
4. **business-modeler**: Business Model Canvas / Lean Canvas, innovation accounting, revenue model analysis
5. **gtm-planner**: Go-to-market strategy, pricing, channels, partnerships, ICP definition, messaging
6. **growth-strategist**: AARRR funnel audit, PLG/CLG analysis, growth experiments, ICE/RICE prioritization
7. **report-compiler**: Compiles all agent outputs into a unified McKinsey-grade strategic report
8. **product-analyst**: AJTBD deep analysis — RAT risk assessment (P×I scoring), job-based segmentation (B2B/B2C), jobs graph mapping, landing page generation from jobs
9. **product-planner**: Strategy-to-execution bridge — opportunity maps (Teresa Torres OST), feature specifications (Shape Up pitch), Now/Next/Later roadmap (Kano + WSJF), MVP definition (MoSCoW)

## Context Modes

Each phase of the strategy flow operates in a specific context mode that shapes agent behavior:

| Phase | Context Mode | File | Behavioral Focus |
|-------|-------------|------|-----------------|
| Phase 1: Context | Analyze | `${CLAUDE_PLUGIN_ROOT}/contexts/analyze.md` | Research-first, data gathering, source verification |
| Phase 2: AJTBD | Analyze | `${CLAUDE_PLUGIN_ROOT}/contexts/analyze.md` | Deep job analysis, segment discovery |
| Phase 3: Market | Analyze | `${CLAUDE_PLUGIN_ROOT}/contexts/analyze.md` | Market data, competitive intelligence |
| Phase 4: Strategy + Model | Execute | `${CLAUDE_PLUGIN_ROOT}/contexts/execute.md` | Document creation, template compliance |
| Phase 5: GTM + Growth | Execute | `${CLAUDE_PLUGIN_ROOT}/contexts/execute.md` | Actionable plans, concrete numbers |
| Phase 6: Report | Review | `${CLAUDE_PLUGIN_ROOT}/contexts/review.md` | Synthesis, contradiction detection, quality |
| Phase 7: Product Plan | Execute | `${CLAUDE_PLUGIN_ROOT}/contexts/execute.md` | Feature specs, roadmap, MVP definition |

**Rule**: When invoking a sub-agent, the orchestrator should reference the appropriate context mode in the prompt to set behavioral expectations.

## Orchestration Principles

### Pyramid Principle (Mandatory for All Outputs)

Every deliverable follows Barbara Minto's Pyramid Principle:
1. **Lead with the conclusion** — the "so what" comes first
2. **Support with MECE arguments** — Mutually Exclusive, Collectively Exhaustive
3. **Action titles** — every section heading is a complete sentence stating the main point
4. **Titles test** — an executive reads only titles and understands the entire argument

### Source Credibility Tiers

All data in reports must be tagged:
- **Tier 1 (Primary)**: Direct market data, official filings, confirmed metrics
- **Tier 2 (Secondary)**: Industry reports, analyst estimates, reliable press
- **Tier 3 (Inference)**: AI-generated estimates, pattern extrapolation, analogies

### MECE Enforcement

All categories, segments, and analysis dimensions must be:
- **Mutually Exclusive**: No overlap between categories
- **Collectively Exhaustive**: Categories cover the full space

## Output Directory Structure

All strategy reports are written to `docs/strategy/` in the user's project. **Each analysis domain produces its own dedicated file** — no analyses are embedded or hidden inside other reports.

```
docs/strategy/
├── context-brief.md              # Business context (context-analyzer)
├── rat.md                        # RAT: Top 5 risky assumptions with P×I scoring (product-analyst)
├── segments.md                   # AJTBD job-based segments, B2B or B2C (product-analyst)
├── jobs-graph.md                 # Critical job sequence for primary segment (product-analyst)
├── market-analysis.md            # Market sizing TAM/SAM/SOM + industry trends (market-analyst)
├── competitive-landscape.md      # Competitor profiles + perceptual maps + SWOT/TOWS (market-analyst)
├── customer-segments.md          # Customer segmentation analysis (market-analyst)
├── strategy-canvas.md            # Blue Ocean + Ansoff/BCG + value proposition (strategy-architect)
├── brand-positioning.md          # Perceptual maps + positioning statement + strategy (strategy-architect)
├── business-model.md             # BMC / Lean Canvas + unit economics + innovation accounting (business-modeler)
├── gtm-plan.md                   # ICP + messaging + channels + partnerships + content + launch plan (gtm-planner)
├── pricing-analysis.md           # Value-based pricing + tier design + competitive pricing (gtm-planner)
├── growth-plan.md                # AARRR funnel + North Star + experiments + 90-day plan (growth-strategist)
├── prioritized-initiatives.md    # ICE/RICE scored list of ALL strategic initiatives (growth-strategist)
├── strategic-report.md           # Final compiled McKinsey-grade report (report-compiler)
├── opportunity-map.md            # Opportunity Solution Tree (product-planner)
├── features/                     # Individual feature specifications (product-planner)
│   └── feature-NNN-[slug].md    # Per-feature Shape Up pitch with cross-references
├── product-roadmap.md            # Now/Next/Later roadmap with feature links (product-planner)
└── mvp-definition.md             # MVP scope, MoSCoW, validation plan (product-planner)
```

**Total: 18+ deliverable files per full analysis.**

### File Ownership by Agent

| File | Owner Agent | Corresponds to Command |
|------|-------------|----------------------|
| `docs/strategy/context-brief.md` | context-analyzer | (part of all flows) |
| `docs/strategy/rat.md` | product-analyst | `/rat` |
| `docs/strategy/segments.md` | product-analyst | `/b2b-segments` or `/b2c-segments` |
| `docs/strategy/jobs-graph.md` | product-analyst | `/jobs-graph` |
| `docs/strategy/market-analysis.md` | market-analyst | `/analyze-market` |
| `docs/strategy/competitive-landscape.md` | market-analyst | `/competitive-map` |
| `docs/strategy/customer-segments.md` | market-analyst | `/analyze-market` |
| `docs/strategy/strategy-canvas.md` | strategy-architect | `/strategy-canvas` |
| `docs/strategy/brand-positioning.md` | strategy-architect | `/strategy-canvas` |
| `docs/strategy/business-model.md` | business-modeler | `/business-model` |
| `docs/strategy/gtm-plan.md` | gtm-planner | `/gtm-plan` |
| `docs/strategy/pricing-analysis.md` | gtm-planner | `/pricing-strategy` |
| `docs/strategy/growth-plan.md` | growth-strategist | `/growth-audit` |
| `docs/strategy/prioritized-initiatives.md` | growth-strategist | `/prioritize` |
| `docs/strategy/strategic-report.md` | report-compiler | `/strategy-report` |
| `docs/strategy/opportunity-map.md` | product-planner | `/product-plan` |
| `docs/strategy/features/*.md` | product-planner | `/product-plan` |
| `docs/strategy/product-roadmap.md` | product-planner | `/product-plan` |
| `docs/strategy/mvp-definition.md` | product-planner | `/product-plan` |

**Rules**:
- Create/edit files only through the owner agent
- Orchestrator NEVER writes documents directly — always delegate to agents
- Each agent reads previous agents' outputs for con

Related in AI Agents