Back to Details

research

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Research Skill - Preliminary Research

研究技能 - 初步研究

Trigger

触发指令

/research <topic>
/research <topic>

Workflow

工作流程

Step 1: Generate Initial Framework from Model Knowledge

步骤1：基于模型知识生成初始框架

Based on topic, use model's existing knowledge to generate:
  • Main research objects/items list in this domain
  • Suggested research field framework
Output {step1_output}, use request_user_input to confirm:
  • Need to add/remove items?
  • Does field framework meet requirements?
基于主题，利用模型已有知识生成：
  • 该领域的主要研究对象/条目列表
  • 建议的研究领域框架
输出{step1_output}，使用request_user_input确认：
  • 是否需要添加/删除条目？
  • 领域框架是否符合需求？

Step 2: Web Search Supplement

步骤2：网络搜索补充

Use request_user_input to ask for time range (e.g., last 6 months, since 2024, unlimited).
Parameter Retrieval:
  • {topic}
    : User input research topic
  • {YYYY-MM-DD}
    : Current date
  • {step1_output}
    : Complete output from Step 1
  • {time_range}
    : User specified time range
Hard Constraint: The following prompt must be strictly reproduced, only replacing variables in {xxx}, do not modify structure or wording.
Launch 1 web-search-agent (background), Prompt Template:
python
prompt = f"""## Task
Research topic: {topic}
Current date: {YYYY-MM-DD}

Based on the following initial framework, supplement latest items and recommended research fields.
使用request_user_input询问时间范围（例如：过去6个月、2024年至今、无限制）。
参数检索:
  • {topic}
    : 用户输入的研究主题
  • {YYYY-MM-DD}
    : 当前日期
  • {step1_output}
    : 步骤1的完整输出
  • {time_range}
    : 用户指定的时间范围
硬性约束: 必须严格复现以下提示词，仅替换{xxx}中的变量，不得修改结构或措辞。
启动1个web-search-agent（后台运行），Prompt Template:
python
prompt = f"""## Task
Research topic: {topic}
Current date: {YYYY-MM-DD}

Based on the following initial framework, supplement latest items and recommended research fields.

Existing Framework

Existing Framework

{step1_output}
{step1_output}

Goals

Goals

  1. Verify if existing items are missing important objects
  2. Supplement items based on missing objects
  3. Continue searching for {topic} related items within {time_range} and supplement
  4. Supplement new fields
  1. Verify if existing items are missing important objects
  2. Supplement items based on missing objects
  3. Continue searching for {topic} related items within {time_range} and supplement
  4. Supplement new fields

Output Requirements

Output Requirements

Return structured results directly (do not write files):
Return structured results directly (do not write files):

Supplementary Items

Supplementary Items

  • item_name: Brief explanation (why it should be added) ...
  • item_name: Brief explanation (why it should be added) ...

Recommended Supplementary Fields

Recommended Supplementary Fields

  • field_name: Field description (why this dimension is needed) ...
  • field_name: Field description (why this dimension is needed) ...

Sources

Sources

  • Source1
  • Source2 """

**One-shot Example** (assuming researching AI Coding History):
  • Source1
  • Source2 """

**单次示例**（假设研究主题为AI Coding History）:

Task

Task

Research topic: AI Coding History Current date: 2025-12-30
Based on the following initial framework, supplement latest items and recommended research fields.
Research topic: AI Coding History Current date: 2025-12-30
Based on the following initial framework, supplement latest items and recommended research fields.

Existing Framework

Existing Framework

Items List

Items List

  1. GitHub Copilot: Developed by Microsoft/GitHub, first mainstream AI coding assistant
  2. Cursor: AI-first IDE, based on VSCode ...
  1. GitHub Copilot: Developed by Microsoft/GitHub, first mainstream AI coding assistant
  2. Cursor: AI-first IDE, based on VSCode ...

Field Framework

Field Framework

  • Basic Info: name, release_date, company
  • Technical Features: underlying_model, context_window ...
  • Basic Info: name, release_date, company
  • Technical Features: underlying_model, context_window ...

Goals

Goals

  1. Verify if existing items are missing important objects
  2. Supplement items based on missing objects
  3. Continue searching for AI Coding History related items within since 2024 and supplement
  4. Supplement new fields
  1. Verify if existing items are missing important objects
  2. Supplement items based on missing objects
  3. Continue searching for AI Coding History related items within since 2024 and supplement
  4. Supplement new fields

Output Requirements

Output Requirements

Return structured results directly (do not write files):
Return structured results directly (do not write files):

Supplementary Items

Supplementary Items

  • item_name: Brief explanation (why it should be added) ...
  • item_name: Brief explanation (why it should be added) ...

Recommended Supplementary Fields

Recommended Supplementary Fields

  • field_name: Field description (why this dimension is needed) ...
  • field_name: Field description (why this dimension is needed) ...

Sources

Sources

  • Source1
  • Source2
undefined
  • Source1
  • Source2
undefined

Step 3: Ask User for Existing Fields

步骤3：询问用户是否已有领域定义

Use request_user_input to ask if user has existing field definition file, if so read and merge.
使用request_user_input询问用户是否已有领域定义文件，若有则读取并合并。

Step 4: Generate Outline (Separate Files)

步骤4：生成研究大纲（分文件）

Merge {step1_output}, {step2_output} and user's existing fields, generate two files:
outline.yaml (items + config):
  • topic: Research topic
  • items: Research objects list
  • execution:
    • batch_size: Number of parallel agents (confirm with request_user_input)
    • items_per_agent: Items per agent (confirm with request_user_input)
    • output_dir: Results output directory (default: ./results)
fields.yaml (field definitions):
  • Field categories and definitions
  • Each field's name, description, detail_level
  • detail_level hierarchy: brief -> moderate -> detailed
  • uncertain: Uncertain fields list (reserved field, auto-filled in deep phase)
合并{step1_output}、{step2_output}和用户提供的已有领域定义，生成两个文件：
outline.yaml (条目 + 配置):
  • topic: 研究主题
  • items: 研究对象列表
  • execution:
    • batch_size: 并行Agent数量（通过request_user_input确认）
    • items_per_agent: 每个Agent负责的条目数（通过request_user_input确认）
    • output_dir: 结果输出目录（默认：./results）
fields.yaml (领域定义):
  • 领域分类与定义
  • 每个领域的名称、描述、详细程度
  • detail_level层级：brief -> moderate -> detailed
  • uncertain: 待确认领域列表（预留字段，在深度研究阶段自动填充）

Step 5: Output and Confirm

步骤5：输出并确认

  • Create directory: 
    ./{topic_slug}/
  • Save: 
    outline.yaml
    and 
    fields.yaml
  • Show to user for confirmation
  • 创建目录：
    ./{topic_slug}/
  • 保存：
    outline.yaml
    和 
    fields.yaml
  • 展示给用户确认

Output Path

输出路径

{current_working_directory}/{topic_slug}/
  ├── outline.yaml    # items list + execution config
  └── fields.yaml     # field definitions
{current_working_directory}/{topic_slug}/
  ├── outline.yaml    # 条目列表 + 执行配置
  └── fields.yaml     # 领域定义

Follow-up Commands

后续指令

  • /research-add-items
    - Supplement items
  • /research-add-fields
    - Supplement fields
  • /research-deep
    - Start deep research
  • /research-add-items
    - 补充条目
  • /research-add-fields
    - 补充领域
  • /research-deep
    - 启动深度研究