Overview

Create dt-method-07-hifi-prototypes.instructions.md — the method-tier instruction file for Method 7: High-Fidelity Prototypes. This method opens the Implementation Space. Users transition from lo-fi experiments (Method 6) to functional prototypes with increasing technical fidelity. Method 7 is unique in the curriculum: it has 3 specialized hats (all other methods have 2) to handle the complex transition from lo-fi to hi-fi.

This is the starter issue for Phase 5 — no intra-phase dependencies.

Target File

.github/instructions/dt-method-07-hifi-prototypes.instructions.md

Frontmatter

---
description: 'Design Thinking Method 7: High-Fidelity Prototypes — technical translation, functional prototypes, and specifications'
applyTo: '**/.copilot-tracking/dt/**/method-07*'
---

Required Content

Method Purpose

Method 7 translates validated concepts into functional prototypes. The quality shift is deliberate — artifacts move from "obviously unfinished" (Methods 1-6) to "works well enough to test with real users." The coach helps users navigate this fidelity increase while maintaining appropriate scope — hi-fi doesn't mean production-ready.

Three Sub-Methods

Three Specialized Hats (Unique)

Method 7 has 3 hats — the only method with this structure. The extra hat handles the lo-fi to hi-fi transition.

Progressive Fidelity Model

Method 7 marks the quality shift from lo-fi to hi-fi:

• From Method 6: Rough prototypes that tested hypotheses
• In Method 7: Functional prototypes that demonstrate capabilities
• Toward Methods 8-9: Prototypes refined through testing and iteration

The coach explicitly acknowledges this shift: "We're crossing into higher fidelity now. The goal is 'works well enough to test,' not 'polished enough to ship.'"

Quality guardrails at this stage:

• Functional prototype should answer: "Does this concept actually work when built?"
• Technical debt is acceptable and expected — this is not production code
• Architecture decisions are documented but not over-engineered
• The prototype should be testable by someone who wasn't involved in creating it

Method 7 Artifacts

Outputs stored at .copilot-tracking/dt/{project-slug}/method-07-hifi-prototypes/:

• fidelity-map.md — Which elements are hi-fi, which remain lo-fi, and why
• prototype/ — Functional prototype artifacts (code, configurations, assets)
• architecture-notes.md — Key technical decisions, trade-offs, and rationale
• spec-draft.md — Preliminary specification for what was built

Coaching Approach

The coach in Method 7:

• Manages the fidelity transition: "I notice you're applying Method 6 roughness here — in Method 7, this component needs to actually function"
• Prevents over-engineering: "That's production-level architecture — for this prototype, a simpler approach tests the same hypothesis"
• Supports technical decision-making: "You're choosing between X and Y — let's evaluate which one lets us test our hypothesis faster"
• Bridges to testing: "This prototype is functional enough — before we polish further, let's see what real users think in Method 8"

Token Budget

Target: ~1,500-2,000 tokens (method tier — loaded when Method 7 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, run /clear to reset context.

Phase 1: Research

Gather source material for the hi-fi prototypes method instruction file.

Source Material: design-thinking-for-hve-capabilities/guidance/07-high-fidelity-prototypes.md
This 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 the source material above.
2. Read .github/instructions/prompt-builder.instructions.md for authoring standards.
3. Read any existing dt-method-* instruction files for structural precedent.
4. Gather content on lo-fi to hi-fi translation patterns, 3-hat structure rationale, progressive fidelity model, and specification drafting approaches.

Starter prompt:

/task-research

Research for IS033: dt-method-07-hifi-prototypes.instructions.md

Read the DT4HVE source material at design-thinking-for-hve-capabilities/guidance/07-high-fidelity-prototypes.md. Extract:
- Lo-fi to hi-fi translation patterns and criteria for when to increase fidelity
- 3-hat structure rationale — why this method needs three hats instead of two
- Progressive fidelity model stages and transition triggers
- Specification drafting approaches for converting prototypes to implementable specs
- Quality gates between fidelity levels

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

Output: research summary from Phase 1 above

Phase 2: Plan

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

Steps:

1. Review the research output from Phase 1.
2. Plan the instruction file structure — method purpose, three sub-methods, three specialized hats, fidelity model, artifact structure, coaching examples.
3. Define section ordering, token allocation, and applyTo targeting.

Starter prompt:

/task-plan

Plan for IS033: dt-method-07-hifi-prototypes.instructions.md

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

- Method purpose: translating lo-fi prototypes into high-fidelity implementations
- Three sub-methods: 7a Fidelity Assessment, 7b Hi-Fi Construction, 7c Specification Drafting
- Three hats: Fidelity Translator, Technical Architect, Specification Writer (document why this method has an extra hat)
- Progressive fidelity model with clear transition criteria between levels
- Artifact structure for hi-fi outputs and specifications
- Coaching examples demonstrating fidelity transitions and over-engineering prevention
- Section ordering and token budget allocation (~1,500-2,000 tokens)
- applyTo: '**/.copilot-tracking/dt/**/method-07*'

Output: plan at .copilot-tracking/plans/{date}-is033-dt-method-07-plan.md

Phase 3: Build

Author the instruction file using the prompt-builder agent.

Steps:

1. Review the plan from Phase 2.
2. Author the instruction file using /prompt-build.
3. The 3-hat structure is the defining feature — ensure each hat's role is distinct and activations are clear.

Starter prompt:

/prompt-build file=.github/instructions/dt-method-07-hifi-prototypes.instructions.md

Build IS033 using the plan at .copilot-tracking/plans/{date}-is033-dt-method-07-plan.md.

This is a method-tier instruction file for Method 7: Hi-Fi Prototypes. Key authoring notes:
- applyTo targets Method 7 artifact paths: '**/.copilot-tracking/dt/**/method-07*'
- The 3-hat structure is the defining feature — ensure each hat's role is distinct and activations are clear
- Three sub-methods with consistent table structure
- Three specialized hats with activation triggers (document why three instead of two)
- Progressive fidelity model with clear stage definitions and transition criteria
- Over-engineering prevention — coach against premature optimization
- Specification drafting guidance for converting prototypes to implementable specs
- Coaching examples demonstrate fidelity transitions

Phase 4: Review

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

Steps:

1. Review the built file against prompt-builder standards and the issue requirements.
2. Validate 3-hat structure clarity, progressive fidelity guidance, over-engineering prevention, and structural compliance.

Starter prompt:

/task-review

Review IS033: .github/instructions/dt-method-07-hifi-prototypes.instructions.md

Validate against:
- prompt-builder.instructions.md authoring standards
- 3-hat structure clarity — each hat has a distinct role and activation trigger
- Progressive fidelity guidance with clear transition criteria
- Over-engineering prevention coaching
- Token budget: ~1,500-2,000 tokens
- Frontmatter applyTo correctness
- Three sub-methods and three hats with consistent table structure

After Review

• Pass: Mark IS033 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:

• applyTo targets Method 7 artifact paths
• Three sub-methods with consistent table structure
• Three specialized hats (document why this method has an extra hat)
• Fidelity transition coaching is central

Success Criteria

• File created at .github/instructions/dt-method-07-hifi-prototypes.instructions.md
• Frontmatter applyTo targets Method 7 artifact paths
• Three sub-methods defined (translation planning, construction, specification)
• Three specialized hats with clear activation triggers (unique among methods)
• Progressive fidelity model explains the lo-fi → hi-fi quality shift
• Over-engineering prevention guidance present
• Coaching examples demonstrate fidelity management and technical decision support
• Token count within ~1,500-2,000 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