Overview

Create dt-start-project.prompt.md — the entry prompt users invoke to begin a new Design Thinking coaching project. This prompt gathers project context, initializes coaching state, and transitions the user into Method 1: Scope Conversations with the DT coach.

Target File

.github/prompts/dt-start-project.prompt.md

Frontmatter

---
description: 'Start a new Design Thinking coaching project — gathers project context and initiates Method 1'
mode: 'agent'
tools: ['create_file', 'read_file']
---

Required Steps

Follows prompt-builder's step-based protocol (## Required Steps → ### Step N: ...):

1. Step 1: Gather Project Context — Collect project name, brief description, initial stakeholders, industry (optional), and user's DT experience level.
2. Step 2: Initialize Coaching State — Create .copilot-tracking/dt/{project-slug}/coaching-state.md with defaults.
3. Step 3: Load Industry Context — If industry is specified and a template exists, copy it to project directory. Otherwise, note that the coach will help build industry context during coaching.
4. Step 4: Transition to Method 1 — Hand off to dt-coach agent with context summary and Method 1 entry orientation.

Input Variables

Prompt Behavior

The prompt:

• Creates the project directory structure at .copilot-tracking/dt/{project-slug}/
• Initializes coaching state with defaults (Method 1, planning phase, Problem Space)
• Sets hint calibration based on user's stated experience level
• Provides a brief orientation: "You're starting Method 1: Scope Conversations. The coach will help you identify stakeholders and define the problem space."
• Ends with --- and activation text per prompt-builder standards

Authoring Standards

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

• Step-based protocol structure
• Input variables use ${input:variableName} syntax
• Ends with --- separator and activation instruction
• Tool declarations in frontmatter

How to Build This File

This is a .prompt.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 Start Project prompt file.

Source Material: The upstream project initialization patterns — session setup,
state initialization, directory structure creation, and transition to the
coaching agent — are defined in the DT4HVE repository:

design-thinking-for-hve-capabilities/.github/chatmodes/design-thinking.chatmode.md
design-thinking-for-hve-capabilities/context/ (project context and state examples)

The chatmode defines the initialization phase that the start-project prompt must
invoke, including input variables (project name, description), state file
creation, and the handoff to dt-coach. The context directory contains examples
of project structure and state initialization. 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 browse the context/ directory files listed above as context.
3. Copy the prompt below into chat and send.

/task-research topic="DT start project prompt for hve-core"

Research the Design Thinking project initialization patterns for a .prompt.md
file targeting `.github/prompts/dt-start-project.prompt.md`.

Use the attached DT4HVE Design Thinking Coach chatmode and context directory
files as primary sources. Extract and analyze:
- Project initialization steps and sequencing
- Input variables: project name, description, and any optional parameters
- State initialization: coaching-state.md creation with default values
- Directory structure creation under `.copilot-tracking/dt/`
- Transition handoff to dt-coach agent after initialization
- Error handling for existing projects or invalid inputs

Focus areas:
- What the prompt must set up before the coach agent can begin
- How input variables are captured and validated
- What the initial coaching state looks like (YAML schema defaults)
- How the directory structure maps to the project lifecycle
- How the handoff to dt-coach works after setup completes

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

Output: DT start project research

Phase 2: Plan

Plan the prompt file structure and step sequencing 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/prompts/dt-start-project.prompt.md` — a
prompt file for initializing new Design Thinking coaching projects.

Use the attached research document as the primary input.

The plan should cover:
- Frontmatter structure (`description`)
- Four steps: gather inputs, validate, create project structure, hand off to
  dt-coach
- Input variables (project name, description) with validation rules
- State initialization: coaching-state.md with YAML schema defaults
- Directory structure under `.copilot-tracking/dt/{project-name}/`
- Transition to dt-coach agent after initialization completes
- Error handling for duplicate projects or missing inputs

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

Output: .copilot-tracking/plans/{date}-dt-start-project-plan.md

Phase 3: Build

Author the prompt 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/prompts/dt-start-project.prompt.md

Build the DT Start Project prompt file following the attached implementation
plan.

Requirements:
- Four steps: gather inputs, validate, create project structure, hand off to
  dt-coach
- Input variables: project name (required), description (required)
- State initialization creates coaching-state.md with correct YAML schema
  defaults
- Directory structure: `.copilot-tracking/dt/{project-name}/` with required
  subdirectories
- Clean handoff to dt-coach agent after initialization
- Error handling for duplicate projects and missing inputs
- Prompt follows prompt-builder standards for .prompt.md files

Output: .github/prompts/dt-start-project.prompt.md

Phase 4: Review

Validate the prompt 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 prompt file from Phase 3.
3. Copy the prompt below into chat and send.

/task-review

Review the implementation of `.github/prompts/dt-start-project.prompt.md`
against the attached plan.

Validate:
- Prompt Quality Criteria from `.github/instructions/prompt-builder.instructions.md`
- Four steps defined with clear sequencing
- Input variables (project name, description) are captured and validated
- State initialization creates correct YAML schema defaults
- Directory structure follows `.copilot-tracking/dt/{project-name}/` convention
- Handoff to dt-coach agent is clean and complete
- Error handling covers duplicate projects and missing inputs
- No temporal markers, task IDs, or DT4HVE-specific references remain
- Writing style follows prompt-builder standards for .prompt.md files

Output: .copilot-tracking/reviews/{date}-dt-start-project-review.md

After Review

The reviewer reports one of three outcomes:

• Pass — The prompt 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

• Prompt file created at .github/prompts/dt-start-project.prompt.md
• Step-based protocol with 4 steps
• Input variables declared for project name and description
• Coaching state initialized with sensible defaults
• Project directory structure created at .copilot-tracking/dt/{project-slug}/
• Transition to dt-coach agent with Method 1 orientation
• Ends with --- separator and activation
• Passes task-reviewer validation against prompt-builder standards