Overview

Create dt-method-05-deep.instructions.md — the on-demand deep instruction file for Method 5: User Concepts. Loaded explicitly by the coach via read_file when advanced concept development is needed: sophisticated D/F/V analysis, concept portfolio management, M365 Copilot image prompt crafting techniques, and concept stress-testing against edge cases.

Target File

.github/instructions/dt-method-05-deep.instructions.md

Frontmatter

---
description: 'Deep expertise for Method 5: User Concepts — advanced D/F/V analysis, image prompt generation, and concept stress-testing'
applyTo: ''
---

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

Required Content

Advanced Three-Lens Analysis

Move beyond surface D/F/V evaluation to:

• Desirability deep-dive: Jobs-to-be-done analysis, Kano model classification (must-be, one-dimensional, attractive), emotional vs. functional value mapping
• Feasibility assessment frameworks: Technical risk scoring, capability gap analysis, build-vs-buy-vs-partner evaluation, dependency chain mapping
• Viability modeling: Unit economics sketching (even rough), total addressable impact estimation, competitive positioning, sustainability assessment
• Lens tension resolution: When D/F/V conflict (high desirability, low feasibility) — how to decide: fund more research, pivot the concept, or accept the risk

M365 Copilot Image Prompt Crafting

Advanced techniques for generating effective concept visualization prompts:

• Scene composition: Describe the environment, actors, and interactions. Include contextual details that communicate the concept's value without text overlays.
• Style directives: Specify hand-drawn/sketch/whiteboard styles to maintain lo-fi quality. Avoid photorealistic prompts that signal premature commitment.
• Perspective selection: Bird's-eye for system concepts, first-person for experience concepts, over-the-shoulder for interface concepts.
• Sequence prompts: Generate a set of 3-4 connected image prompts that tell the concept's user journey across key moments.
• Anti-patterns: Avoid prompts that generate polished marketing materials, UI mockups, or photorealistic renders — these violate lo-fi constraints.

Concept Stress-Testing

Challenge concepts with structured adversarial thinking:

• Edge case scenarios: What happens under extreme load, unusual users, failure conditions?
• Assumption mapping: List every assumption embedded in the concept and classify by risk (untested, partially tested, validated)
• Pre-mortem exercise: "Imagine this concept failed completely — what went wrong?" Work backward to identify vulnerable assumptions.
• Competitive response: "If a competitor copy this concept tomorrow, what would they do differently?"

Concept Portfolio Management

When multiple concepts are being developed:

• Portfolio balance assessment: Are concepts spread across different risk levels, user segments, and value propositions?
• Concept comparison matrix: Side-by-side D/F/V comparison with key differentiators highlighted
• Kill criteria: When to stop developing a concept — clear signals that further investment won't improve the concept
• Merge identification: Recognizing when two concepts are actually one concept with two entry points

Token Budget

Target: ~2,000-3,000 tokens (on-demand tier)

How to Build This File

This is an .instructions.md file — use the prompt-builder agent (not task-implementor) for the authoring phase. The prompt-builder includes built-in Prompt Quality Criteria validation and sandbox testing specific to AI artifacts (.instructions.md, .prompt.md, .agent.md, SKILL.md).

Workflow: /task-research → /task-plan → /prompt-build → /task-review
Between each phase, run /clear to reset context.

Phase 1: Research

Source Material:

1. design-thinking-for-hve-capabilities/guidance/05-user-concepts.md
2. .github/instructions/dt-method-05-concepts.instructions.md (already-built method-tier file)

The DT4HVE guidance file lives in the DT4HVE repository. If you don't have local access, ask the user to provide it or use read_file if the repo is cloned nearby.

Steps:

1. Read both source materials above.
2. Read .github/instructions/prompt-builder.instructions.md for authoring standards.
3. Read any existing dt-method-*-deep instruction files for structural precedent.
4. Gather content on advanced D/F/V evaluation, concept visualization techniques (especially M365 Copilot image generation), concept stress-testing frameworks, and portfolio management approaches.

Starter prompt:

/task-research

Research for IS031: dt-method-05-deep.instructions.md (on-demand deep file)

Read the DT4HVE source material at design-thinking-for-hve-capabilities/guidance/05-user-concepts.md AND the already-built method-tier file at .github/instructions/dt-method-05-concepts.instructions.md. Extract advanced/deep-dive content that goes BEYOND the basic method-tier coverage:
- Advanced D/F/V evaluation — Jobs-to-be-done, Kano model, unit economics, lens tension resolution
- Concept visualization techniques — M365 Copilot image prompt crafting, scene composition, style directives
- Concept stress-testing — edge cases, assumption mapping, pre-mortem, competitive response
- Portfolio management approaches — balance assessment, kill criteria, merge identification

Also read .github/instructions/prompt-builder.instructions.md for authoring standards and any existing dt-method-*-deep.instructions.md files for structural precedent.

Output: research summary from Phase 1 above

Phase 2: Plan

Steps:

1. Review the research output from Phase 1.
2. Plan the deep instruction file structure — advanced D/F/V sections, image prompt techniques, stress-testing framework, portfolio management, on-demand loading structure.
3. Define section ordering, token allocation, and confirm empty applyTo.

Starter prompt:

/task-plan

Plan for IS031: dt-method-05-deep.instructions.md (on-demand deep file)

Using the Phase 1 research output, plan the deep instruction file:

- Advanced D/F/V analysis beyond surface evaluation (Jobs-to-be-done, Kano, unit economics, lens tension)
- M365 Copilot image prompt crafting techniques for concept visualization
- Concept stress-testing framework — structured adversarial thinking
- Concept portfolio management for multi-concept scenarios
- On-demand loading structure — empty applyTo, loaded via read_file by the coach
- Content must clearly go beyond what the method-tier file already covers
- Section ordering and token budget allocation (~2,000-3,000 tokens)

Output: plan at .copilot-tracking/plans/{date}-is031-dt-method-05-deep-plan.md

Phase 3: Build

Steps:

1. Review the plan from Phase 2.
2. Author the instruction file using /prompt-build.
3. M365 Copilot image prompt crafting is a distinctive feature of this deep file — ensure practical, actionable guidance.

Starter prompt:

/prompt-build file=.github/instructions/dt-method-05-deep.instructions.md

Build IS031 using the plan at .copilot-tracking/plans/{date}-is031-dt-method-05-deep-plan.md.

This is an on-demand deep instruction file for Method 5: User Concepts. Key authoring notes:
- applyTo is EMPTY — this file is loaded on-demand by the coach, not auto-loaded by glob
- Content provides advanced/deep-dive material beyond the basic method-tier file
- Advanced D/F/V analysis with Jobs-to-be-done, Kano model, and lens tension resolution
- M365 Copilot image prompt crafting — scene composition, style directives, sequence prompts, anti-patterns
- Concept stress-testing — edge cases, assumption mapping, pre-mortem, competitive response
- Portfolio management — balance assessment, comparison matrix, kill criteria, merge identification
- Writing style: guidance over commands — deep reference material, not procedural steps
- Token budget: ~2,000-3,000 tokens

Phase 4: Review

Steps:

1. Review the built file against prompt-builder standards and the issue requirements.
2. Validate D/F/V depth, image prompt quality, stress-testing rigor, portfolio management utility, and prompt-builder compliance.

Starter prompt:

/task-review

Review IS031: .github/instructions/dt-method-05-deep.instructions.md

Validate against:
- prompt-builder.instructions.md authoring standards
- D/F/V depth — advanced evaluation frameworks, not just surface D/F/V
- Image prompt quality — practical M365 Copilot prompt crafting guidance with anti-patterns
- Stress-testing rigor — structured adversarial thinking approaches
- Portfolio management utility — practical tools for multi-concept scenarios
- Empty applyTo in frontmatter (on-demand loading)
- Writing style: guidance over commands
- Token budget: ~2,000-3,000 tokens
- Structural consistency with other deep-tier instruction files

After Review

• Pass: Mark IS031 complete.
• Iterate: Address review findings, rebuild, re-review.
• Escalate: If blocked by missing DT4HVE source material or architectural questions, raise to the user.

Authoring Standards

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

• Empty applyTo: since this is on-demand content
• Writing style: guidance over commands
• M365 Copilot image prompt crafting is a distinctive feature of this deep file

Success Criteria

• File created at .github/instructions/dt-method-05-deep.instructions.md
• Frontmatter has empty applyTo: (on-demand loading)
• Advanced D/F/V analysis with sophisticated evaluation frameworks
• M365 Copilot image prompt crafting with practical examples and anti-patterns
• Concept stress-testing with structured adversarial approaches
• Concept portfolio management for multi-concept scenarios
• Token count within ~2,000-3,000 target
• Passes task-reviewer validation against prompt-builder standards
• Each prompt, instructions, or agent file registered in collections/design-thinking.collection.yml with path and kind fields
• Each prompt, instructions, or agent file registered in collections/hve-core-all.collection.yml with path and kind fields
• npm run plugin:generate succeeds after collection manifest updates