Back to Details

gsd-research-phase

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese
<objective> Research how to implement a phase. Spawns gsd-phase-researcher agent with phase context.
Note: This is a standalone research command. For most workflows, use 
{{COMMAND_PREFIX}}plan-phase
which integrates research automatically.
Use this command when:
  • You want to research without planning yet
  • You want to re-research after planning is complete
  • You need to investigate before deciding if a phase is feasible
Orchestrator role: Parse phase, validate against roadmap, check existing research, gather context, spawn researcher agent, present results.
Why subagent: Research burns context fast (WebSearch, Context7 queries, source verification). Fresh 200k context for investigation. Main context stays lean for user interaction. </objective>
<context> Phase number: $ARGUMENTS (required)
Normalize phase input in step 1 before any directory lookups. </context>
<process>
<objective> 研究如何实现一个阶段。基于阶段上下文启动gsd-phase-researcher agent。
注意： 这是一个独立的研究命令。对于大多数工作流，请使用
{{COMMAND_PREFIX}}plan-phase
，它会自动集成研究功能。
使用此命令的场景：
  • 你希望先进行研究，暂不做规划
  • 规划完成后，你需要重新开展研究
  • 在决定某个阶段是否可行之前，你需要先进行调研
编排器角色： 解析阶段信息，对照路线图验证，检查已有研究，收集上下文，启动研究agent，呈现结果。
为何使用子agent： 研究过程会快速消耗上下文（WebSearch、Context7查询、来源验证）。全新的200k上下文可用于调研，主上下文保持精简以用于用户交互。 </objective>
<context> 阶段编号：$ARGUMENTS（必填）
在进行任何目录查找前，第一步先标准化阶段输入。 </context>
<process>

0. Initialize Context

0. 初始化上下文

bash
INIT=$(node {{PLATFORM_ROOT}}/get-shit-done/bin/gsd-tools.cjs init phase-op "$ARGUMENTS")
Extract from init JSON: 
phase_dir
, 
phase_number
, 
phase_name
, 
phase_found
, 
commit_docs
, 
has_research
, 
state_path
, 
requirements_path
, 
context_path
, 
research_path
.
Resolve researcher model:
bash
RESEARCHER_MODEL=$(node {{PLATFORM_ROOT}}/get-shit-done/bin/gsd-tools.cjs resolve-model gsd-phase-researcher --raw)
bash
INIT=$(node {{PLATFORM_ROOT}}/get-shit-done/bin/gsd-tools.cjs init phase-op "$ARGUMENTS")
从初始化JSON中提取：
phase_dir
, 
phase_number
, 
phase_name
, 
phase_found
, 
commit_docs
, 
has_research
, 
state_path
, 
requirements_path
, 
context_path
, 
research_path
。
解析研究模型：
bash
RESEARCHER_MODEL=$(node {{PLATFORM_ROOT}}/get-shit-done/bin/gsd-tools.cjs resolve-model gsd-phase-researcher --raw)

1. Validate Phase

1. 验证阶段

bash
PHASE_INFO=$(node {{PLATFORM_ROOT}}/get-shit-done/bin/gsd-tools.cjs roadmap get-phase "${phase_number}")
If 
found
is false: Error and exit. If 
found
is true: Extract 
phase_number
, 
phase_name
, 
goal
from JSON.
bash
PHASE_INFO=$(node {{PLATFORM_ROOT}}/get-shit-done/bin/gsd-tools.cjs roadmap get-phase "${phase_number}")
如果
found
为false： 报错并退出。如果
found
为true： 从JSON中提取
phase_number
, 
phase_name
, 
goal
。

2. Check Existing Research

2. 检查已有研究

bash
ls .planning/phases/${PHASE}-*/RESEARCH.md 2>/dev/null
If exists: Offer: 1) Update research, 2) View existing, 3) Skip. Wait for response.
If doesn't exist: Continue.
bash
ls .planning/phases/${PHASE}-*/RESEARCH.md 2>/dev/null
若已存在： 提供选项：1) 更新研究，2) 查看已有研究，3) 跳过。等待用户响应。
若不存在： 继续执行。

3. Gather Phase Context

3. 收集阶段上下文

Use paths from INIT (do not inline file contents in orchestrator context):
  • requirements_path
  • context_path
  • state_path
Present summary with phase description and what files the researcher will load.
使用INIT中的路径（不要在编排器上下文中内联文件内容）：
  • requirements_path
  • context_path
  • state_path
呈现包含阶段描述以及研究agent将加载的文件的摘要。

4. Spawn gsd-phase-researcher Agent

4. 启动gsd-phase-researcher Agent

Research modes: ecosystem (default), feasibility, implementation, comparison.
markdown
<research_type>
Phase Research — investigating HOW to implement a specific phase well.
</research_type>

<key_insight>
The question is NOT "which library should I use?"

The question is: "What do I not know that I don't know?"

For this phase, discover:
- What's the established architecture pattern?
- What libraries form the standard stack?
- What problems do people commonly hit?
- What's SOTA vs what Claude's training thinks is SOTA?
- What should NOT be hand-rolled?
</key_insight>

<objective>
Research implementation approach for Phase {phase_number}: {phase_name}
Mode: ecosystem
</objective>

<files_to_read>
- {requirements_path} (Requirements)
- {context_path} (Phase context from discuss-phase, if exists)
- {state_path} (Prior project decisions and blockers)
</files_to_read>

<additional_context>
**Phase description:** {phase_description}
</additional_context>

<downstream_consumer>
Your RESEARCH.md will be loaded by `{{COMMAND_PREFIX}}plan-phase` which uses specific sections:
- `## Standard Stack` → Plans use these libraries
- `## Architecture Patterns` → Task structure follows these
- `## Don't Hand-Roll` → Tasks NEVER build custom solutions for listed problems
- `## Common Pitfalls` → Verification steps check for these
- `## Code Examples` → Task actions reference these patterns

Be prescriptive, not exploratory. "Use X" not "Consider X or Y."
</downstream_consumer>

<quality_gate>
Before declaring complete, verify:
- [ ] All domains investigated (not just some)
- [ ] Negative claims verified with official docs
- [ ] Multiple sources for critical claims
- [ ] Confidence levels assigned honestly
- [ ] Section names match what plan-phase expects
</quality_gate>

<output>
Write to: .planning/phases/${PHASE}-{slug}/${PHASE}-RESEARCH.md
</output>
Task(
  prompt="First, read {{PLATFORM_ROOT}}/agents/gsd-phase-researcher.md for your role and instructions.\n\n" + filled_prompt,
  subagent_type="general-purpose",
  model="{researcher_model}",
  description="Research Phase {phase}"
)
研究模式：生态系统（默认）、可行性、实现、对比。
markdown
<research_type>
阶段研究 — 调研如何出色地实现特定阶段。
</research_type>

<key_insight>
核心问题不是“我应该使用哪个库？”

而是：“有哪些我不知道自己不知道的事情？”

针对此阶段，需探索：
- 已确立的架构模式是什么？
- 构成标准技术栈的库有哪些？
- 人们通常会遇到哪些问题？
- 当前最优方案（SOTA）与Claude训练数据中的最优方案有何区别？
- 哪些内容不应手动开发？
</key_insight>

<objective>
研究第{phase_number}阶段：{phase_name}的实现方案
模式：生态系统
</objective>

<files_to_read>
- {requirements_path}（需求文档）
- {context_path}（若存在，来自discuss-phase的阶段上下文）
- {state_path}（过往项目决策与障碍）
</files_to_read>

<additional_context>
**阶段描述：** {phase_description}
</additional_context>

<downstream_consumer>
你的RESEARCH.md将被`{{COMMAND_PREFIX}}plan-phase`加载，它会使用以下特定章节：
- `## Standard Stack` → 规划将使用这些库
- `## Architecture Patterns` → 任务结构遵循这些模式
- `## Don't Hand-Roll` → 任务绝不会为列出的问题构建自定义解决方案
- `## Common Pitfalls` → 验证步骤会检查这些问题
- `## Code Examples` → 任务操作会参考这些模式

请给出明确的指令，而非探索性内容。使用“使用X”而非“考虑X或Y”。
</downstream_consumer>

<quality_gate>
在宣布完成前，请验证：
- [ ] 所有领域均已调研（而非仅部分）
- [ ] 负面声明已通过官方文档验证
- [ ] 关键声明有多个来源支撑
- [ ] 如实标注置信度
- [ ] 章节名称与plan-phase预期一致
</quality_gate>

<output>
写入至：.planning/phases/${PHASE}-{slug}/${PHASE}-RESEARCH.md
</output>
Task(
  prompt="First, read {{PLATFORM_ROOT}}/agents/gsd-phase-researcher.md for your role and instructions.\n\n" + filled_prompt,
  subagent_type="general-purpose",
  model="{researcher_model}",
  description="Research Phase {phase}"
)

5. Handle Agent Return

5. 处理Agent返回结果

## RESEARCH COMPLETE
: Display summary, offer: Plan phase, Dig deeper, Review full, Done.
## CHECKPOINT REACHED
: Present to user, get response, spawn continuation.
## RESEARCH INCONCLUSIVE
: Show what was attempted, offer: Add context, Try different mode, Manual.
## RESEARCH COMPLETE
： 显示摘要，提供选项：规划阶段、深入调研、查看完整内容、完成。
## CHECKPOINT REACHED
： 呈现给用户，获取响应，启动续期agent。
## RESEARCH INCONCLUSIVE
： 展示已尝试的内容，提供选项：添加上下文、尝试不同模式、手动处理。

6. Spawn Continuation Agent

6. 启动续期Agent

markdown
<objective>
Continue research for Phase {phase_number}: {phase_name}
</objective>

<prior_state>
<files_to_read>
- .planning/phases/${PHASE}-{slug}/${PHASE}-RESEARCH.md (Existing research)
</files_to_read>
</prior_state>

<checkpoint_response>
**Type:** {checkpoint_type}
**Response:** {user_response}
</checkpoint_response>
Task(
  prompt="First, read {{PLATFORM_ROOT}}/agents/gsd-phase-researcher.md for your role and instructions.\n\n" + continuation_prompt,
  subagent_type="general-purpose",
  model="{researcher_model}",
  description="Continue research Phase {phase}"
)
</process>
<success_criteria>
  • Phase validated against roadmap
  • Existing research checked
  • gsd-phase-researcher spawned with context
  • Checkpoints handled correctly
  • User knows next steps </success_criteria>
markdown
<objective>
继续研究第{phase_number}阶段：{phase_name}
</objective>

<prior_state>
<files_to_read>
- .planning/phases/${PHASE}-{slug}/${PHASE}-RESEARCH.md（已有研究）
</files_to_read>
</prior_state>

<checkpoint_response>
**类型：** {checkpoint_type}
**响应：** {user_response}
</checkpoint_response>
Task(
  prompt="First, read {{PLATFORM_ROOT}}/agents/gsd-phase-researcher.md for your role and instructions.\n\n" + continuation_prompt,
  subagent_type="general-purpose",
  model="{researcher_model}",
  description="Continue research Phase {phase}"
)
</process>
<success_criteria>
  • 阶段已对照路线图验证
  • 已检查已有研究
  • 已加载上下文并启动gsd-phase-researcher
  • 检查点已正确处理
  • 用户了解后续步骤 </success_criteria>