research-flow
Workflow for deep project research with grounded references, parallel exploration, etc.
来源信息
- 仓库
- griddynamics/rosetta
- 最近来源活动
- 2026年8月19日 22:06
- 检测到的 SKILL.md 语言
- 英语
- 星标
- 360
- Forks
- 80
安装方式
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
检查来源文件
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
正在显示 SKILL.md
SKILL.md
来源说明 · 只读预览- 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">
1. All Rosetta prep steps MUST be FULLY completed
2. USE SKILL `load-project-context`, `orchestration`, `hitl`
3. MUST ALWAYS use todo tasks ledger, ASAP. Phases are sequential. Independent tasks can run in parallel.
4. Orchestrator trusts the system and skills; coordinates sequence, artifacts, state, and approvals only.
5. Workflow state MUST be saved to `agents/TEMP/<FEATURE>/research-flow-state.md` file.
6. If `/goal` is set repeat phases 3-4 until goal is met.
</prerequisites>
<context_load phase="1" subagent="researcher" role="Context gatherer for research scope" subagent_required_model="inherit">
1. Read all lines from CONTEXT.md, ARCHITECTURE.md, and IMPLEMENTATION.md.
2. Input: user research request. Output: loaded project context.
3. Update `research-flow-state.md`.
</context_load>
<prompt_craft phase="2" subagent="researcher" role="Research prompt architect" subagent_required_model="inherit">
1. Create an optimized research prompt for the user request.
2. Save as `research-prompt.md` in FEATURE PLAN folder. Output ONLY the optimized prompt.
3. Input: user request + project context. Output: `research-prompt.md`.
4. Required skills: `reasoning`
5. Update `research-flow-state.md`.
6. HITL approval of research prompt before execution.
</prompt_craft>
<execute_research phase="3" subagent="researcher" role="Deep research executor" subagent_required_model="inherit">
1. Execute the approved research prompt as a separate subagent.
2. Input: approved `research-prompt.md`. Output: `docs/<feature>-research.md`.
3. Required skills: `research`
4. Update `research-flow-state.md`.
</execute_research>
<finalize phase="4" subagent="researcher" role="Research finalizer" subagent_required_model="inherit">
1. Finalize `docs/<feature>-research.md`.
2. Input: completed research document. Output: finalized research document.
3. Update `research-flow-state.md` and mark complete.
</finalize>
</workflow_phases>
</research_flow>
在 GitHub 查看