Pull Request

Description

Creates dt-method-02-deep.instructions.md, an on-demand deep reference for DT Method 2 (Design Research). The dt-coach agent loads this file via read_file when users require advanced research guidance beyond what the method-tier instruction provides.

The file contains 17 H3 subsections across 4 domains, each with prose, bullets, and a labeled coaching prompt:

• Advanced Interview Techniques — pre-interview preparation, cognitive interview techniques, silence and pause usage, reframing resistance, cultural context adaptation
• Ethnographic Observation Methods — contextual inquiry setup, shadow observation protocols, artifact analysis, environmental mapping
• Evidence Triangulation — multi-source validation, contradictory evidence handling, pattern saturation assessment, insight confidence scoring
• Manufacturing Research Patterns — shift-based research considerations, production floor observation, operator vs. supervisor perspectives, supply chain stakeholder mapping

Also adds .github/agents/design-thinking to chat.agentFilesLocations in .vscode/settings.json so the dt-coach agent appears in the VS Code agent dropdown.

Related Issue(s)

Closes #585

Type of Change

Select all that apply:

Code & Documentation:

• Bug fix (non-breaking change fixing an issue)
• New feature (non-breaking change adding functionality)
• Breaking change (fix or feature causing existing functionality to change)
• Documentation update

Infrastructure & Configuration:

• GitHub Actions workflow
• Linting configuration (markdown, PowerShell, etc.)
• Security configuration
• DevContainer configuration
• Dependency update

AI Artifacts:

• Reviewed contribution with prompt-builder agent and addressed all feedback
• Copilot instructions (.github/instructions/*.instructions.md)
• Copilot prompt (.github/prompts/*.prompt.md)
• Copilot agent (.github/agents/*.agent.md)
• Copilot skill (.github/skills/*/SKILL.md)

Other:

• Script/automation (.ps1, .sh, .py)
• Other (please describe):

Sample Prompts (for AI Artifact Contributions)

User Request:

"We're struggling to get honest answers in interviews — people keep telling us what they think we want to hear. How do we break through that?"

Execution Flow:

1. dt-coach detects the user is in Method 2 (Design Research) with an advanced interview challenge
2. Agent calls read_file on dt-method-02-deep.instructions.md to load the deep reference
3. Agent surfaces the Cognitive Interview Techniques and Reframing Resistance subsections
4. Agent responds using the coaching prompt: "What would it look like if participants felt safe enough to share what they actually think — and what's currently in the way of that?"

Output Artifacts:
No files created — the agent responds conversationally using the loaded deep reference to coach the user through the research challenge.

Success Indicators:

• Agent surfaces subsection-specific coaching prompts rather than generic research advice
• User receives technique-specific guidance (e.g., cognitive interviewing, silence usage) matched to their specific challenge
• Coaching prompts feel contextual and non-prescriptive

Testing

• Ran /prompt-analyze against dt-method-02-deep.instructions.md — 22/23 checks passed
• Reviewed and addressed all prompt-builder feedback via /prompt-build
• Verified applyTo pattern matches method-tier convention (**/.copilot-tracking/dt/**/method-02*)
• Confirmed collection manifests (design-thinking, hve-core-all) updated and plugins regenerated
• Rebased cleanly onto updated main (post upstream sync of 106 files including Methods 4–9)

Checklist

Required Checks

• Documentation is updated (if applicable)
• Files follow existing naming conventions
• Changes are backwards compatible (if applicable)
• Tests added for new functionality (if applicable)

AI Artifact Contributions

• Used /prompt-analyze to review contribution
• Addressed all feedback from prompt-builder review
• Verified contribution follows common standards and type-specific requirements

Required Automated Checks

• Markdown linting: npm run lint:md — ✅ 0 errors (181 files)
• Spell checking: npm run spell-check — ⚠️ pre-existing environment issue (Node.js v20.16.0 < v20.18 required); unrelated to this PR
• Frontmatter validation: npm run lint:frontmatter — ✅ 0 errors, 0 warnings (167 files)
• Skill structure validation: npm run validate:skills — ✅ 0 errors (2 skills)
• Link validation: npm run lint:md-links — ⚠️ pre-existing repo-wide ESM incompatibility in markdown-link-extractor; unrelated to this PR
• PowerShell analysis: npm run lint:ps — ⚠️ 3 warnings in .copilot-tracking sandbox script (generate-dalle-images.ps1), which is gitignored and unrelated to this PR

Security Considerations

• This PR does not contain any sensitive or NDA information
• Any new dependencies have been reviewed for security issues
• Security-related scripts follow the principle of least privilege

Additional Notes

The three automated check warnings are all pre-existing environment or infrastructure issues:

1. spell-check: Requires Node.js ≥ 20.18; local environment is 20.16.0 — not introduced by this PR
2. lint:md-links: markdown-link-extractor ESM compatibility error affects the entire repo — not introduced by this PR
3. lint:ps: Warnings are in .copilot-tracking/design-thinking-for-hve-capabilities/scripts/generate-dalle-images.ps1, a gitignored sandbox file — not introduced by this PR

Supersedes #677.