Overview

Create dt-method-04-deep.instructions.md — the on-demand deep instruction file for Method 4: Brainstorming. Loaded explicitly by the coach via read_file when a user needs advanced ideation facilitation: handling group dynamics in AI-assisted brainstorming, overcoming creative blocks, advanced convergence frameworks, and cross-pollination from analogous industries.

Target File

.github/instructions/dt-method-04-deep.instructions.md

Frontmatter

---
description: 'Deep expertise for Method 4: Brainstorming — advanced facilitation, convergence frameworks, and cross-pollination strategies'
applyTo: ''
---

Note: applyTo is empty — this file is loaded on-demand by the coach agent, not auto-loaded by glob.

Required Content

Advanced Facilitation Techniques

Move beyond basic brainstorming to:

• Brainwriting variants: Silent idea generation before group discussion — reduces anchoring bias
• Round-robin forced connections: Each participant builds on the previous idea in unexpected ways
• Attribute listing: Decompose the problem into attributes and brainstorm per attribute
• Morphological analysis: Create a matrix of problem dimensions × possible solutions and systematically explore combinations
• Provocation techniques (Po): Deliberately absurd statements to escape conventional thinking patterns

Creative Block Recovery

When ideation stalls, the coach can deploy:

• Assumption reversal: List every assumption about the problem, then reverse each one and brainstorm from the reversed state
• Random input: Introduce unrelated concepts as creative catalysts (random word, random image prompt, random industry)
• Constraint manipulation: Add extreme constraints ("What if it had to be free?") or remove constraints ("What if we had unlimited budget?")
• Perspective shifting: Brainstorm as different personas — the end user, the competitor, a child, a skeptic

Advanced Convergence Frameworks

Beyond simple voting or clustering:

• Impact/effort matrix: Plot ideas on 2×2 (high impact/low effort = quick wins, high impact/high effort = strategic bets)
• Dot voting with constraints: Each participant gets limited votes forcing prioritization — coach adapts for single-user contexts
• Concept clustering with gap analysis: After clustering, identify gaps in the solution landscape — "What problem areas have no ideas yet?"
• Weighted D/F/V scoring: Assign relative weights to desirability, feasibility, viability based on project priorities — preview of Method 5's deeper evaluation

Cross-Pollination from Analogous Industries

Sourced from DT4HVE's cross-industry evidence:

• Manufacturing → Software: Production line optimization patterns applied to development workflows
• Healthcare → Manufacturing: Patient-centered design applied to operator experience
• Energy → Healthcare: Grid resilience patterns applied to healthcare system reliability
• Coach prompts: "How does [analogous industry] solve a similar problem? What can we borrow?"

Token Budget

Target: ~2,000-3,000 tokens (on-demand 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, run /clear to reset context.

Phase 1: Research

Source Material:

1. design-thinking-for-hve-capabilities/guidance/04-brainstorming.md
2. .github/instructions/dt-method-04-brainstorming.instructions.md (already-built method-tier file)

The DT4HVE guidance 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 both source materials above.
2. Read .github/instructions/prompt-builder.instructions.md for authoring standards.
3. Read any existing dt-method-*-deep instruction files for structural precedent.
4. Gather content on advanced facilitation techniques, creative block recovery strategies, convergence frameworks beyond basic voting, and cross-industry ideation patterns.

Starter prompt:

/task-research

Research for IS030: dt-method-04-deep.instructions.md (on-demand deep file)

Read the DT4HVE source material at design-thinking-for-hve-capabilities/guidance/04-brainstorming.md AND the already-built method-tier file at .github/instructions/dt-method-04-brainstorming.instructions.md. Extract advanced/deep-dive content that goes BEYOND the basic method-tier coverage:
- Advanced facilitation techniques (brainwriting variants, morphological analysis, provocation techniques)
- Creative block recovery strategies — assumption reversal, random input, constraint manipulation, perspective shifting
- Convergence frameworks beyond simple voting — impact/effort matrix, weighted D/F/V scoring, gap analysis
- Cross-industry ideation patterns from DT4HVE's analogous industry evidence

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

Output: research summary from Phase 1 above

Phase 2: Plan

Steps:

1. Review the research output from Phase 1.
2. Plan the deep instruction file structure — advanced ideation patterns, creative block interventions, cross-industry techniques, on-demand loading structure.
3. Define section ordering, token allocation, and confirm empty applyTo.

Starter prompt:

/task-plan

Plan for IS030: dt-method-04-deep.instructions.md (on-demand deep file)

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

- Advanced facilitation techniques beyond basic brainstorming (brainwriting, attribute listing, morphological analysis, provocation)
- Creative block recovery strategies for when ideation stalls
- Advanced convergence frameworks beyond simple voting (impact/effort, weighted D/F/V, gap analysis)
- Cross-pollination patterns from analogous industries
- On-demand loading structure — empty applyTo, loaded via read_file by the coach
- Content must clearly go beyond what the method-tier file already covers
- Section ordering and token budget allocation (~2,000-3,000 tokens)

Output: plan at .copilot-tracking/plans/{date}-is030-dt-method-04-deep-plan.md

Phase 3: Build

Steps:

1. Review the plan from Phase 2.
2. Author the instruction file using /prompt-build.
3. Content should enable the coach to guide advanced ideation when basic method-tier techniques aren't sufficient.

Starter prompt:

/prompt-build file=.github/instructions/dt-method-04-deep.instructions.md

Build IS030 using the plan at .copilot-tracking/plans/{date}-is030-dt-method-04-deep-plan.md.

This is an on-demand deep instruction file for Method 4: Brainstorming. Key authoring notes:
- applyTo is EMPTY — this file is loaded on-demand by the coach, not auto-loaded by glob
- Content provides advanced/deep-dive material beyond the basic method-tier file
- Advanced facilitation techniques (brainwriting, morphological analysis, provocation)
- Creative block recovery — assumption reversal, random input, constraint manipulation, perspective shifting
- Convergence frameworks beyond voting — impact/effort matrix, weighted D/F/V scoring, concept clustering with gap analysis
- Cross-pollination from analogous industries with coach prompts
- Writing style: guidance over commands — deep reference material, not procedural steps
- Token budget: ~2,000-3,000 tokens

Phase 4: Review

Steps:

1. Review the built file against prompt-builder standards and the issue requirements.
2. Validate advanced content depth beyond method-tier, creative block recovery quality, cross-industry pattern applicability, and prompt-builder compliance.

Starter prompt:

/task-review

Review IS030: .github/instructions/dt-method-04-deep.instructions.md

Validate against:
- prompt-builder.instructions.md authoring standards
- Advanced content depth — must go beyond what the method-tier file already covers
- Creative block recovery quality — practical strategies the coach can deploy when ideation stalls
- Cross-industry pattern applicability — patterns should be actionable, not theoretical
- Empty applyTo in frontmatter (on-demand loading)
- Writing style: guidance over commands
- Token budget: ~2,000-3,000 tokens
- Structural consistency with other deep-tier instruction files

After Review

• Pass: Mark IS030 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:

• Empty applyTo: since this is on-demand content
• Writing style: guidance over commands
• Content is deep reference material, not procedural steps

Success Criteria

• File created at .github/instructions/dt-method-04-deep.instructions.md
• Frontmatter has empty applyTo: (on-demand loading)
• Advanced facilitation techniques beyond basic brainstorming
• Creative block recovery strategies for when ideation stalls
• Convergence frameworks beyond simple voting
• Cross-pollination patterns from analogous industries
• Token count within ~2,000-3,000 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