Overview

Create dt-coaching-identity.instructions.md — the ambient instruction file that defines the DT coach's core identity across all methods and sessions. This is the foundational personality layer: Think/Speak/Empower philosophy, progressive hint engine, graduation awareness, and identity consistency rules. All other DT instruction files and the coach agent build on this identity.

This is the starter issue for Phase 1 — no intra-phase dependencies. New contributors can pick this up after reading the DT coaching overview (parent issue).

Target File

.github/instructions/dt-coaching-identity.instructions.md

Frontmatter

---
description: 'Design Thinking coaching identity — Think/Speak/Empower philosophy, progressive hints, and graduation awareness'
applyTo: '**/.copilot-tracking/dt/**'
---

Required Content

Think/Speak/Empower Philosophy

Three layers that shape every coaching interaction:

Progressive Hint Engine

4-level escalation system for coaching assistance:

Calibration persists across sessions via hint_calibration.level in coaching state. The coach adjusts based on pattern observation, not user self-assessment.

Graduation Awareness

At DT space boundaries (Problem → Solution, Solution → Implementation), the coach:

• Summarizes what was accomplished in the current space
• Assesses readiness signals (are minimum completion indicators present?)
• Offers graduation choices: continue forward, revisit earlier methods, or hand off to RPI
• Never forces transitions — the user decides when to move

Identity Rules

What stays constant across all methods, all sessions, all industries:

• Conversational colleague, not authoritative expert
• Curious and occasionally challenging — never judgmental
• Observes and asks — never directs or prescribes
• Celebrates iteration and messy progress over polished output
• Never generates the user's task-output artifacts (the user does the work, the coach guides)
• Personality consistency: same voice whether wearing the Stakeholder Mapper hat (Method 1) or the Prototype Evaluator hat (Method 7)

Token Budget

Target: ~2,891 tokens (ambient tier — loaded on every .copilot-tracking/dt/** path)

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 coaching identity file.

Source Material: The upstream coaching identity patterns — Think/Speak/Empower, progressive hints, graduation awareness — are defined in the DT4HVE repository's Design Thinking Coach chatmode:

design-thinking-for-hve-capabilities/.github/chatmodes/design-thinking.chatmode.md

This file defines Think/Speak/Empower, the 4-level progressive hint system, coaching identity rules, and space boundary behavior. 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 listed above as context.
3. Copy the prompt below into chat and send.

/task-research topic="DT coaching identity for hve-core"

Research the Design Thinking coaching identity pattern for an .instructions.md
file targeting `.github/instructions/dt-coaching-identity.instructions.md`.

Use the attached DT4HVE Design Thinking Coach chatmode as the primary source.
Extract and analyze:
- Think/Speak/Empower philosophy (the three coaching layers: internal reasoning,
  colleague-style observations, empowerment through choices)
- Progressive hint system (4-level escalation from broad direction to direct
  detail, including escalation triggers)
- Graduation awareness behavior at DT space boundaries
  (Problem → Solution → Implementation)
- Coaching identity consistency rules (what changes vs. what never changes across
  method specializations)
- Behavioral examples that demonstrate coaching through observation and options,
  not directives

Focus areas:
- How Think/Speak/Empower shapes coaching interactions across methods
- Hint escalation examples for each of the 4 levels, plus the trigger signals
  that advance the level
- Identity rules that persist regardless of which method hat is active
- How the coach signals method transitions without being mechanical

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

Output: DT coaching identity 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-coaching-identity.instructions.md` — an ambient-tier
instruction file for the DT coaching identity.

Use the attached research document as the primary input.

The plan should cover:
- Frontmatter structure
  (`description`, `applyTo: '**/.copilot-tracking/dt/**'`)
- Think/Speak/Empower philosophy section with behavioral examples
- Progressive hint engine table (4 levels with examples)
- Graduation awareness behavior at DT space boundaries
- Identity rules for cross-method consistency
- Token budget target: ~2,891 tokens (ambient tier)

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

Output: .copilot-tracking/plans/{date}-dt-coaching-identity-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-coaching-identity.instructions.md

Build the DT coaching identity instructions file following the attached
implementation plan.

Requirements:
- Ambient-tier instruction file loaded on all `.copilot-tracking/dt/**` paths
- Think/Speak/Empower philosophy embedded as behavioral coaching guidance, not
  explicit rules the AI reads aloud
- 4-level progressive hint engine with escalation examples
- Graduation awareness at DT space boundaries with exit choices
- Identity rules: consistent personality, never directive, never generates
  task-output artifacts
- Token budget: ~2,891 tokens
- Nativize DT4HVE content for HVE Core context — avoid source-specific
  references

Output: .github/instructions/dt-coaching-identity.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-coaching-identity.instructions.md` against the
attached plan.

Validate:
- Prompt Quality Criteria from `.github/instructions/prompt-builder.instructions.md`
- Think/Speak/Empower is embedded behaviorally (coach acts this way, doesn't
  recite rules)
- Progressive hint engine has 4 levels with concrete, actionable examples
- Graduation awareness triggers at DT space boundaries
- Token count is within ~2,891 target (ambient tier budget)
- Frontmatter has correct `applyTo: '**/.copilot-tracking/dt/**'` 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-coaching-identity-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-coaching-identity.instructions.md
• Frontmatter has applyTo: '**/.copilot-tracking/dt/**' glob
• Think/Speak/Empower philosophy embedded as behavioral guidance, not explicit rules
• 4-level progressive hint engine specified with examples
• Graduation awareness behavior at DT space boundaries
• Token count within ~2,891 target (ambient tier budget)
• Passes task-reviewer validation against prompt-builder standards