Research

Dispatch execution subagent — select model by complexity, construct prompt with full task context

Plan execution path, produce executable plan, dispatch subagents, collect and analyze results

SOP: 评估研究 gap 的潜在影响力，识别受益方并输出影响力评分

Enumerate barriers to pursuing the chosen research direction — knowledge barriers, resource barriers, capability barriers, competition barriers. May optionally use search tools to discover obstacles the user hasn't mentioned.

Synthesize diverse ideas into coherent solution concepts. Combines fragments from multiple ideation passes into structured, actionable ideas with clear mechanism descriptions.

SOP: 综合所有中间产物，产出最终结构化假设集

Strategy: 将 working hypothesis 精确化为可测试形式

Campaign: 将 insight 和 gap 转化为结构化的可测试假设

SOP: 构建竞争假设的多维度对比矩阵

Minimal crystallization strategy for users who already have a specific research topic or problem (e.g., "I want to improve CoT faithfulness in LLMs") and need structuring into a formal North Star. Heavily simplifies or skips exploration tactics, focusing on obstacle analysis, goal decomposition, and synthesis. Use when the user's first message reveals a specific, actionable research direction.

Generate "How Might We" questions at different scope levels (narrow, medium, broad). Ensures each is actionable without being prescriptive.

Identify and classify sources of between-study heterogeneity (clinical, methodological, statistical)

Explain why different studies reach different conclusions — heterogeneity investigation protocol. Budget: 30 studies, 30 effect sizes, 50 web searches.

Estimate theoretical/practical ceiling vs current SOTA gap

Strategy: 10th Man Rule and Liberating Structures — institutionalized dissent to prevent premature consensus and expose suppressed objections.

Structured creative thinking in Six Hats Green Hat mode — pure creative output with judgment suspended.

Apply Argyris framework to identify governing variables — the unstated rules driving behavior in a research field.

Structure the user's chosen direction into a formal goal tree using KAOS-style AND/OR decomposition. Validate feasibility against ActorProfile and ObstacleReport. Use after obstacle-analysis confirms the direction is viable.

Extract shared abstract structure from two input spaces

Aggregate all accumulated context from the crystallization process into a structured ResearchBrief document. This is the final output artifact alongside the North Star — a comprehensive requirement context document for downstream research strategies.

Propose 3-8 candidate research fields based on the full ActorProfile. When user wants to explore beyond their current stack, use other ActorProfile signals (intentionality, boundary) to determine exploration space. Free exploration within the boundary.

Ritchey GMA: complete iterative morphological process

Evaluate a candidate against gate criteria and render GO/KILL/RECYCLE verdict with evidence.

Define gate criteria and pass thresholds for a specific stage in the Stage-Gate process.