strategy-orchestration-guide
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.
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 conRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.