Overview

Create dt-method-01-deep.instructions.md, the on-demand deep instruction file for Method 1: Scope Conversations. Loaded explicitly by the coach via read_file when a user needs advanced techniques beyond what the method-tier instruction provides: complex stakeholder mapping, power dynamics analysis, organizational politics navigation, and multi-department scope negotiation.

This is the starter issue for Phase 3, no intra-phase dependencies.

Target File

.github/instructions/dt-method-01-deep.instructions.md

Frontmatter

---
description: 'Deep expertise for Method 1: Scope Conversations — advanced stakeholder analysis, power dynamics, and scope negotiation'
applyTo: ''
---

Note: applyTo is empty, this file is loaded on-demand by the coach agent, not auto-loaded by glob.

Required Content

Advanced Stakeholder Mapping

Move beyond basic stakeholder identification to:

• Multi-layer stakeholder maps: Direct stakeholders → indirect stakeholders → ecosystem actors → regulatory bodies
• Influence/interest matrices: Position stakeholders by influence level and interest level to identify key players, keep-satisfied, keep-informed, and monitoring groups
• Relationship network analysis: Map connections between stakeholders, who influences whom, where are alliances, where are tensions
• Missing voice detection: Systematic prompts to identify stakeholders not yet represented ("Who is affected but not at the table?")

Power Dynamics Navigation

Coaching guidance for sensitive organizational contexts:

• Identifying formal authority vs. informal influence
• Recognizing when scope is being constrained by political pressure rather than genuine boundaries
• Helping users navigate conflicting stakeholder priorities without the coach taking sides
• Detecting when a "scope conversation" is really a "permission conversation"

Multi-Department Scope Negotiation

Techniques for complex organizational scoping:

• Cross-functional boundary identification (where does your problem end and another team's begin?)
• Shared dependency mapping (which systems, teams, or processes are touched by multiple stakeholders?)
• Scope escalation patterns (when to expand scope based on discovered interconnections)
• Scope anchoring (techniques to prevent scope creep while keeping exploration open)

Manufacturing-Specific Scope Patterns

Sourced from DT4HVE's 130+ manufacturing references:

• Production line stakeholder hierarchies (operators → supervisors → engineers → management → safety)
• Regulatory constraint scoping (compliance bodies as stakeholders with veto power)
• Shift-based scope considerations (problems that manifest differently across shifts)
• Supply chain scope boundaries (where internal scope meets supplier/customer scope)

Token Budget

Target: ~2,000-3,000 tokens (on-demand tier, loaded when coach needs advanced Method 1 techniques)

Source Material

Attach these files as context for the task-researcher phase:

• DT4HVE Method guidance: design-thinking-for-hve-capabilities/guidance/01-scope-conversations.md, canonical Method 1 with manufacturing floor example (L57)
• Coaching hats: design-thinking-for-hve-capabilities/.github/chatmodes/hats/, method-specific coaching hat files
• Cumulative research: Design Thinking cumulative research, Parts 1-2 (methodology foundations and cross-industry evidence) and Part 7 (cross-industry strategy and manufacturing reference patterns)

RPI Pipeline Workflow

1. task-researcher: Gather DT4HVE advanced Method 1 content, extended stakeholder mapping, power dynamics patterns, manufacturing scope examples. Cross-reference cumulative research Parts 1-2 (DT foundations) and Part 7 (cross-industry strategy).
2. task-planner: Plan the file, advanced stakeholder mapping techniques, power dynamics coaching guidance, multi-department scope patterns, industry-specific examples.
3. task-implementor: Author following prompt-builder standards. Nativize DT4HVE advanced techniques for HVE Core context. Content should enable the coach to provide expert-level guidance when loaded.
4. task-reviewer: Validate technique depth, coaching tone (guidance not directive), industry example quality, prompt-builder compliance.

Authoring Standards

Follow .github/instructions/prompt-builder.instructions.md:

• Empty applyTo: since this is on-demand content
• Writing style: guidance over commands
• Content is deep reference material, not procedural steps

Starter Prompts

Research: /task-research — "Gather advanced Method 1: Scope Conversations content from DT4HVE — extended stakeholder mapping, power dynamics patterns, manufacturing scope examples. Attach guidance/01-scope-conversations.md and cumulative research Parts 1-2, 7 as context."

Plan: /task-plan — "Plan dt-method-01-deep.instructions.md — advanced stakeholder mapping, power dynamics coaching, multi-department scope patterns, manufacturing-specific examples."

Implement: /task-implement — "Author dt-method-01-deep.instructions.md following prompt-builder standards with empty applyTo, guidance-over-commands tone, 2000-3000 token budget."

Review: /task-review — "Validate dt-method-01-deep.instructions.md against prompt-builder standards, coaching tone, and manufacturing reference quality."

Prompt-Builder Compliance Checklist

Per .github/instructions/prompt-builder.instructions.md:

• description: frontmatter present and descriptive
• applyTo: '' (empty, on-demand loading)
• Writing style uses guidance over commands (no "You must/will/shall")
• Token count within budget tier
• No ALL CAPS emphasis
• Content structured for coaching context

Success Criteria

• File created at .github/instructions/dt-method-01-deep.instructions.md
• Frontmatter has empty applyTo: (on-demand loading)
• Advanced stakeholder mapping with multi-layer, influence/interest, and relationship network techniques
• Power dynamics navigation guidance appropriate for coaching context
• Multi-department scope negotiation patterns
• Manufacturing-specific scope patterns sourced from DT4HVE
• Token count within ~2,000-3,000 target
• Passes task-reviewer validation against prompt-builder standards
• Artifact registered in collections/design-thinking.collection.yml with path and kind fields
• Artifact registered in collections/hve-core-all.collection.yml with path and kind fields
• npm run plugin:generate run after updating collection manifests