Workflows Brainstorm

Evaluate whether brainstorming is needed based on the research question.

Clear requirements indicators:

• Specific estimator or method already chosen
• Referenced existing implementation to follow
• Described exact identification strategy
• Constrained, well-defined methodological scope

If requirements are already clear: Skip brainstorming and note: "Requirements are detailed enough to proceed directly to planning. Run /workflows:plan to continue." Then stop.

If requirements need exploration: Proceed to Phase 1.

Phase 1: Understand the Problem

1.1 Codebase and Literature Research

Run a targeted scan to understand existing patterns and related methods:

• Task methods-explorer("Understand existing methodological patterns and approaches related to: <research_question>")

Focus on: existing estimation code, identification strategies used in this project, methodology documented in papers or notes.

1.2 Problem Decomposition

Analyze the research question systematically without user interaction:

1. Core question: What is the fundamental methodological decision being made?
2. Constraints: What data limitations, computational budgets, or identification requirements constrain the choice?
3. Prior art: What has this project already done that's similar? What methods are established in the literature?
4. Success criteria: What would a good solution look like? (e.g., consistent estimation, reasonable computational cost, testable identification)

Document findings from the research agent and decomposition. If the question is ambiguous, pick the most natural interpretation given the project context and note the assumption.

Phase 2: Compare Approaches

Propose 2-3 concrete methodological approaches based on research and analysis.

For each approach, provide:

Recommendation: Select the simplest approach that satisfies the identification requirements. Apply parsimony — prefer well-understood methods with established software implementations over novel approaches unless the research question specifically demands novelty.

Document why the recommended approach was chosen and what conditions would favor the alternatives.

Phase 3: Capture the Analysis

Entry condition: Phase 2 comparison table is complete with all criteria filled for all approaches. Exit condition: Document written to docs/brainstorms/ with all required YAML frontmatter fields.

Artifact Storage

Write the brainstorm output to docs/brainstorms/<topic>-requirements.md with YAML frontmatter:

---