Overview

Create dt-method-01-scope.instructions.md — the method-tier instruction file for Method 1: Scope Conversations. This method is the entry point to the Problem Space where users define project boundaries, identify stakeholders, and articulate the problem space they want to explore.

Target File

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

Frontmatter

---
description: 'Design Thinking Method 1: Scope Conversations — stakeholder identification, problem framing, and project boundaries'
applyTo: '**/.copilot-tracking/dt/**/method-01*'
---

Required Content

Method Purpose

Method 1 establishes the boundaries of the design challenge. Before diving into research, teams need clarity on:

• Who are the stakeholders affected by this problem?
• What boundaries should we set (and which should we leave open)?
• What do we already know vs. what do we assume?

Three Sub-Methods

Two Specialized Hats

Method 1 Artifacts

Outputs stored at .copilot-tracking/dt/{project-slug}/method-01-scope/:

• stakeholder-map.md — Stakeholder groups, relationships, influence levels
• scope-boundaries.md — What's in scope, out of scope, and open questions
• assumptions-log.md — Known facts vs. assumptions to validate

Lo-Fi Quality Enforcement

Method 1 artifacts are explicitly rough:

• Stakeholder maps are bullet lists or simple tables, not polished diagrams
• Scope boundaries are conversational, not formal requirements documents
• Assumptions are captured as-is, not analyzed or prioritized yet

Coaching Approach

The coach in Method 1:

• Asks expansive questions ("Who else might care about this?")
• Challenges unstated assumptions ("You mentioned the engineering team — what about the people who use what engineering builds?")
• Resists narrowing too early ("Let's keep that boundary open for now and see what research reveals")

Token Budget

Target: ~1,500-2,000 tokens (method tier — loaded when Method 1 artifacts are open)

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, use /clear to reset context, then attach the output artifact from the previous phase as input for the next.

Phase 1: Research

Gather source material for the Method 1 (Scope Conversations) instruction file.

Source Material: The upstream Method 1 definitions — sub-methods, hat
behaviors, scope framing patterns, and stakeholder mapping techniques — are
defined in the DT4HVE repository:

design-thinking-for-hve-capabilities/.github/chatmodes/design-thinking.chatmode.md
design-thinking-for-hve-capabilities/guidance/01-scope-conversations.md

The chatmode defines Method 1's role in the 9-method sequence and its two
specialized hats (Stakeholder Mapper, Scope Framer). The guidance file contains
the detailed sub-method definitions and coaching examples. If you don't have the
DT4HVE repository cloned, ask a maintainer for access.

Steps:

1. Type /clear to start a fresh conversation.
2. Attach the DT4HVE chatmode file and 01-scope-conversations.md listed above as context.
3. Copy the prompt below into chat and send.

/task-research topic="DT Method 1 scope conversations for hve-core"

Research the Design Thinking Method 1 (Scope Conversations) patterns for an
.instructions.md file targeting
`.github/instructions/dt-method-01-scope.instructions.md`.

Use the attached DT4HVE Design Thinking Coach chatmode and Method 1 guidance
file as primary sources. Extract and analyze:
- Three sub-methods for Method 1 (planning, execution, documentation)
- Two specialized hats: Stakeholder Mapper and Scope Framer — activation
  triggers, behaviors, and example coaching prompts
- Scope framing patterns and stakeholder mapping techniques
- Lo-fi enforcement rules (artifacts stay rough, no polishing)
- Coaching approach: expansive questions, challenges assumptions, resists
  narrowing too early

Focus areas:
- How the coach embeds coaching behavior, not procedural steps
- What makes each hat distinct in voice and purpose
- How lo-fi enforcement keeps artifacts rough during scoping
- How coaching examples can be nativized for HVE Core context

The research output will feed `/task-plan` and then `/prompt-build` to author
the instructions file.

Output: DT method 01 scope research

Phase 2: Plan

Plan the file structure and content organization using the research output.

Steps:

1. Type /clear to reset the conversation.
2. Attach the research document from Phase 1 (from the research phase above).
3. Copy the prompt below into chat and send.

/task-plan

Plan the implementation of
`.github/instructions/dt-method-01-scope.instructions.md` — a method-tier
instruction file for DT Method 1 (Scope Conversations).

Use the attached research document as the primary input.

The plan should cover:
- Frontmatter structure
  (`description`, `applyTo: '**/.copilot-tracking/dt/**/method-01*'`)
- Method purpose and overview
- Sub-method table (planning, execution, documentation)
- Two specialized hats (Stakeholder Mapper, Scope Framer) with activation
  triggers and example coaching prompts
- Artifact structure for scope conversation outputs
- Lo-fi enforcement rules
- Coaching approach: expansive questions, challenges assumptions, resists
  narrowing
- Token budget target: ~1,500-2,000 tokens (method tier)

The implementation phase will use `/prompt-build` (not task-implementor) since
this is an AI artifact file.

Output: .copilot-tracking/plans/{date}-dt-method-01-scope-plan.md

Phase 3: Build

Author the instruction file using the prompt-builder agent. Prompt-builder handles authoring standards (frontmatter, writing style, progressive disclosure) automatically through its built-in Prompt Quality Criteria validation.

Steps:

1. Type /clear to reset the conversation.
2. Attach the plan document from Phase 2 (find it in .copilot-tracking/plans/).
3. Copy the prompt below into chat and send.

/prompt-build file=.github/instructions/dt-method-01-scope.instructions.md

Build the DT Method 1 (Scope Conversations) instructions file following the
attached implementation plan.

Requirements:
- Method-tier instruction file loaded on `.copilot-tracking/dt/**/method-01*`
  paths
- Three sub-methods defined (planning, execution, documentation)
- Two specialized hats (Stakeholder Mapper, Scope Framer) with clear activation
  triggers
- Lo-fi enforcement: artifacts stay rough, no polishing during scoping
- Coaching approach embeds behavior (expansive questions, challenges assumptions,
  resists narrowing) — not procedural steps
- Artifact structure for scope conversation outputs
- Token budget: ~1,500-2,000 tokens
- Nativize DT4HVE content for HVE Core context — avoid source-specific
  references

Output: .github/instructions/dt-method-01-scope.instructions.md

Phase 4: Review

Validate the instruction file against the plan and prompt-builder standards.

Steps:

1. Type /clear to reset the conversation.
2. Attach the plan document from Phase 2 and the new instruction file from Phase 3.
3. Copy the prompt below into chat and send.

/task-review

Review the implementation of
`.github/instructions/dt-method-01-scope.instructions.md` against the
attached plan.

Validate:
- Prompt Quality Criteria from `.github/instructions/prompt-builder.instructions.md`
- Three sub-methods defined (planning, execution, documentation)
- Two specialized hats with distinct activation triggers and coaching voices
- Lo-fi enforcement prevents polishing during scoping
- Coaching approach: expansive questions, challenges assumptions, resists
  narrowing
- Token count is within ~1,500-2,000 target (method tier budget)
- Frontmatter has correct `applyTo: '**/.copilot-tracking/dt/**/method-01*'`
  glob
- No temporal markers, task IDs, or DT4HVE-specific references remain
- Writing style follows prompt-builder standards: guidance over commands,
  `*` bullets, `**bold**` for key concepts

Output: .copilot-tracking/reviews/{date}-dt-method-01-scope-review.md

After Review

The reviewer reports one of three outcomes:

• Pass — The instruction file meets all criteria. Open a PR with the new file.
• Iterate — The reviewer identified specific issues. Return to Phase 3: /clear, attach the review document, then re-run /prompt-build with the fixes noted.
• Escalate — Fundamental gaps need more research. Return to Phase 1 to investigate the identified areas.

Success Criteria

• File created at .github/instructions/dt-method-01-scope.instructions.md
• Frontmatter applyTo targets Method 1 artifact paths
• Three sub-methods defined (planning, execution, documentation)
• Two specialized hats with clear activation triggers
• Artifact output paths specified
• Lo-fi quality constraints enforced
• Coaching examples demonstrate conversational guidance, not directives
• Token count within ~1,500-2,000 target
• Passes task-reviewer validation against prompt-builder standards