Overview

Create dt-quality-constraints.instructions.md — the ambient instruction file that defines per-method quality constraints, enforcing lo-fi output in early methods and allowing progressive fidelity as the user moves through later Design Thinking methods.

AI assistants default to production-quality output. In Design Thinking, early-stage artifacts must deliberately signal "still being shaped" to encourage iteration and prevent premature commitment.

Target File

.github/instructions/dt-quality-constraints.instructions.md

Frontmatter

---
description: 'Design Thinking quality constraints — lo-fi enforcement and progressive fidelity rules per method'
applyTo: '**/.copilot-tracking/dt/**'
---

Required Content

Problem Statement

AI assistants default to production-quality output. In Design Thinking, early-stage artifacts must signal "still being shaped" to:

• Encourage iteration rather than premature commitment
• Keep focus on thinking quality rather than presentation quality
• Prevent stakeholders from treating drafts as final deliverables

Per-Method Fidelity Rules

Quality Gate Behavior

The coach applies quality constraints by:

• Refusing to polish artifacts beyond their method's fidelity level
• Suggesting rougher alternatives when output is too refined ("This stakeholder map is very detailed — in Method 1 we keep these rough so they invite feedback. Want to simplify?")
• Celebrating messiness in early methods as a signal of healthy iteration
• Acknowledging the shift when transitioning to higher-fidelity methods

Integration with Coaching Identity

Quality constraints augment the Think/Speak/Empower model:

• Think: Assess whether current artifact fidelity matches method expectations
• Speak: Observe when output quality doesn't match the method's stage
• Empower: Offer options for adjusting fidelity level

Token Budget

Target: ~800-1,000 tokens (ambient 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, 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 quality constraints file.

Source Material: The upstream quality constraint patterns and lo-fi enforcement
rules are defined in the DT4HVE repository's Design Thinking Coach chatmode:

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

This file contains lo-fi enforcement rules, per-method quality patterns, and
the approach to preventing over-polished output in early DT methods. 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 quality constraints for hve-core"

Research the Design Thinking quality constraint patterns for an .instructions.md
file targeting `.github/instructions/dt-quality-constraints.instructions.md`.

Use the attached DT4HVE Design Thinking Coach chatmode as the primary source.
Extract and analyze:
- Lo-fi enforcement rules (how the coach prevents production-quality output in
  early methods)
- Per-method fidelity levels across all 9 methods (Problem, Solution,
  Implementation spaces)
- Quality gate behavior (how the coach observes and responds to over-polished
  artifacts)
- The "Too Nice Prototype" tension and its resolution (Discussion #485 pattern)
- Integration with Think/Speak/Empower coaching identity for quality feedback

Focus areas:
- How fidelity progresses from lo-fi (Methods 1-4, 6) through medium
  (Methods 5, 7-8) to high (Method 9)
- Behavioral examples of the coach suggesting rougher alternatives
- How quality constraints celebrate messiness as a signal of healthy iteration
- The shift in coaching tone when transitioning to higher-fidelity methods

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

Output: DT quality constraints 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-quality-constraints.instructions.md` — an ambient-tier
instruction file for DT quality constraints and lo-fi enforcement.

Use the attached research document as the primary input.

The plan should cover:
- Frontmatter structure
  (`description`, `applyTo: '**/.copilot-tracking/dt/**'`)
- Problem statement section (why AI defaults to over-polished output)
- Per-method fidelity rules table covering all 9 methods
- Quality gate behavior embedded as coaching guidance
- Integration with Think/Speak/Empower coaching identity
- "Too Nice Prototype" tension resolution
- Token budget target: ~800-1,000 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-quality-constraints-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-quality-constraints.instructions.md

Build the DT quality constraints instructions file following the attached
implementation plan.

Requirements:
- Ambient-tier instruction file loaded on all `.copilot-tracking/dt/**` paths
- Per-method fidelity rules covering all 9 methods in a single table
- Quality gate behavior embedded as coaching guidance, not rigid rules the AI
  recites
- Coach suggests rougher alternatives when output exceeds method fidelity level
- Integration with Think/Speak/Empower model for quality feedback
- Addresses the "Too Nice Prototype" tension from community feedback
- Token budget: ~800-1,000 tokens
- Nativize DT4HVE content for HVE Core context — avoid source-specific
  references

Output: .github/instructions/dt-quality-constraints.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-quality-constraints.instructions.md` against the
attached plan.

Validate:
- Prompt Quality Criteria from `.github/instructions/prompt-builder.instructions.md`
- Per-method fidelity rules cover all 9 methods
- Quality gate behavior is embedded as coaching guidance, not rigid rules
- "Too Nice Prototype" tension from community feedback is addressed
- Lo-fi enforcement is behavioral (coach observes and suggests, not blocks)
- Token count is within ~800-1,000 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-quality-constraints-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-quality-constraints.instructions.md
• Frontmatter has applyTo: '**/.copilot-tracking/dt/**' glob
• Per-method fidelity rules cover all 9 methods
• Quality gate behavior embedded as coaching guidance, not rigid rules
• Addresses "Too Nice Prototype" tension from community feedback
• Token count within ~800-1,000 target
• Passes task-reviewer validation against prompt-builder standards