| name | research-flow |
| description | Workflow for deep project research with grounded references, parallel exploration, etc. |
<research_flow>
<description_and_purpose>
Orchestrates deep research via meta-prompting: craft an optimized research prompt, then execute it in a dedicated subagent.
</description_and_purpose>
<workflow_phases>
<prerequisites phase="0", applies="ALL">
-
All Rosetta prep steps MUST be FULLY completed
-
USE SKILL load-project-context, orchestration, hitl
-
MUST ALWAYS use todo tasks ledger, ASAP. Phases are sequential. Independent tasks can run in parallel.
-
Orchestrator trusts the system and skills; coordinates sequence, artifacts, state, and approvals only.
-
Workflow state MUST be saved to agents/TEMP/<FEATURE>/research-flow-state.md file.
-
If /goal is set repeat phases 3-4 until goal is met.
<context_load phase="1" subagent="researcher" role="Context gatherer for research scope" subagent_required_model="inherit">
- Read all lines from CONTEXT.md, ARCHITECTURE.md, and IMPLEMENTATION.md.
- Input: user research request. Output: loaded project context.
- Update
research-flow-state.md.
</context_load>
<prompt_craft phase="2" subagent="researcher" role="Research prompt architect" subagent_required_model="inherit">
- Create an optimized research prompt for the user request.
- Save as
research-prompt.md in FEATURE PLAN folder. Output ONLY the optimized prompt.
- Input: user request + project context. Output:
research-prompt.md.
- Required skills:
reasoning
- Update
research-flow-state.md.
- HITL approval of research prompt before execution.
</prompt_craft>
<execute_research phase="3" subagent="researcher" role="Deep research executor" subagent_required_model="inherit">
- Execute the approved research prompt as a separate subagent.
- Input: approved
research-prompt.md. Output: docs/<feature>-research.md.
- Required skills:
research
- Update
research-flow-state.md.
</execute_research>
- Finalize
docs/<feature>-research.md.
- Input: completed research document. Output: finalized research document.
- Update
research-flow-state.md and mark complete.
</workflow_phases>
</research_flow>