feat: add bilingual support (zh/en) for research skills
- Rename skills/research to skills/research-en (English version) - Add skills/research-zh (Chinese version with SKILL.md structure) - Update README.md with bilingual documentation - Add web-search-agent.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
jilinchen
co-authored by
Claude Opus 4.5
Claude Opus 4.5
parent
92b47e006e
commit
10377e95e2
@@ -1,17 +1,23 @@
|
||||
# Deep Research Skill for Claude Code
|
||||
|
||||
[English](#english) | [中文](#中文)
|
||||
|
||||
---
|
||||
|
||||
## English
|
||||
|
||||
> Inspired by [RhinoInsight: Improving Deep Research through Control Mechanisms for Model Behavior and Context](https://arxiv.org/abs/2511.18743)
|
||||
|
||||
A structured research workflow skill for Claude Code, supporting two-phase research: outline generation (extensible) and deep investigation. Human-in-the-loop design ensures precise control at every stage.
|
||||
|
||||
## Use Cases
|
||||
### Use Cases
|
||||
|
||||
- **Academic Research**: Paper surveys, benchmark reviews, literature analysis
|
||||
- **Technical Research**: Technology comparison, framework evaluation, tool selection
|
||||
- **Market Research**: Competitor analysis, industry trends, product comparison
|
||||
- **Due Diligence**: Company research, investment analysis, risk assessment
|
||||
|
||||
## Commands
|
||||
### Commands
|
||||
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
@@ -21,85 +27,107 @@ A structured research workflow skill for Claude Code, supporting two-phase resea
|
||||
| `/research/deep` | Deep research each item with parallel agents |
|
||||
| `/research/report` | Generate markdown report from JSON results |
|
||||
|
||||
## Installation
|
||||
### Installation
|
||||
|
||||
Copy the `skills/` folder to your Claude Code directory:
|
||||
Choose your language version:
|
||||
|
||||
```bash
|
||||
cp -r skills/* ~/.claude/skills/
|
||||
# English version
|
||||
cp -r skills/research-en ~/.claude/skills/research
|
||||
|
||||
# Chinese version
|
||||
cp -r skills/research-zh ~/.claude/commands/research
|
||||
```
|
||||
|
||||
## Workflow
|
||||
### Workflow
|
||||
|
||||
### Phase 1: Generate Outline
|
||||
#### Phase 1: Generate Outline
|
||||
```
|
||||
/research <topic>
|
||||
```
|
||||
- Uses model knowledge + web search
|
||||
- Asks for existing field definitions
|
||||
- Creates `{topic}/` directory with separated files
|
||||
|
||||
### Phase 2: Deep Research
|
||||
#### Phase 2: Deep Research
|
||||
```
|
||||
/research/deep
|
||||
```
|
||||
- Reads outline and fields automatically from current directory
|
||||
- Launches parallel agents (5 per batch)
|
||||
- Agents read fields.yaml independently (not passed in prompt)
|
||||
- Outputs structured JSON per item
|
||||
- Supports resume from checkpoint
|
||||
|
||||
### Optional: Expand Outline
|
||||
#### Optional: Expand Outline
|
||||
```
|
||||
/research/add-items # Add more research targets
|
||||
/research/add-fields # Add more field definitions
|
||||
/research/add-items
|
||||
/research/add-fields
|
||||
```
|
||||
|
||||
## Output Format
|
||||
|
||||
### Directory Structure
|
||||
```
|
||||
{topic}/
|
||||
├── outline.yaml # items + execution config
|
||||
├── fields.yaml # field definitions
|
||||
└── results/ # deep research outputs
|
||||
```
|
||||
|
||||
### outline.yaml
|
||||
```yaml
|
||||
topic: "your topic"
|
||||
items:
|
||||
- name: "Item1"
|
||||
source: "source info"
|
||||
execution:
|
||||
batch_size: 5 # parallel agents (default: 5)
|
||||
items_per_agent: 1 # items per agent (default: 1)
|
||||
output_dir: "./results" # output directory (default: ./results)
|
||||
```
|
||||
|
||||
### fields.yaml
|
||||
```yaml
|
||||
basic_info:
|
||||
- name: "field_name"
|
||||
description: "field description"
|
||||
detail_level: "detailed|brief"
|
||||
```
|
||||
|
||||
### Research Result (JSON)
|
||||
Each item outputs a structured JSON file with all defined fields.
|
||||
|
||||
### Phase 3: Generate Report
|
||||
#### Phase 3: Generate Report
|
||||
```
|
||||
/research/report
|
||||
```
|
||||
- Generates Python script to convert JSON to markdown
|
||||
- Creates report with table of contents and anchor links
|
||||
- Skips uncertain fields automatically
|
||||
|
||||
## References
|
||||
---
|
||||
|
||||
## 中文
|
||||
|
||||
> 灵感来源：[RhinoInsight: Improving Deep Research through Control Mechanisms for Model Behavior and Context](https://arxiv.org/abs/2511.18743)
|
||||
|
||||
Claude Code 的结构化调研工作流技能，支持两阶段调研：outline生成（可扩展）和深度调查。人在回路设计确保每个阶段的精确控制。
|
||||
|
||||
### 使用场景
|
||||
|
||||
- **学术研究**：论文综述、benchmark评测、文献分析
|
||||
- **技术研究**：技术对比、框架评估、工具选型
|
||||
- **市场研究**：竞品分析、行业趋势、产品比较
|
||||
- **尽职调查**：公司研究、投资分析、风险评估
|
||||
|
||||
### 命令
|
||||
|
||||
| 命令 | 描述 |
|
||||
|------|------|
|
||||
| `/research` | 生成包含items和fields的调研outline |
|
||||
| `/research/add-items` | 向现有outline添加更多items |
|
||||
| `/research/add-fields` | 向现有outline添加更多fields |
|
||||
| `/research/deep` | 使用并行agents对每个item进行深度调研 |
|
||||
| `/research/report` | 从JSON结果生成markdown报告 |
|
||||
|
||||
### 安装
|
||||
|
||||
选择语言版本：
|
||||
|
||||
```bash
|
||||
# 英文版
|
||||
cp -r skills/research-en ~/.claude/skills/research
|
||||
|
||||
# 中文版
|
||||
cp -r skills/research-zh ~/.claude/commands/research
|
||||
```
|
||||
|
||||
### 工作流
|
||||
|
||||
#### 阶段1：生成Outline
|
||||
```
|
||||
/research <topic>
|
||||
```
|
||||
|
||||
#### 阶段2：深度调研
|
||||
```
|
||||
/research/deep
|
||||
```
|
||||
|
||||
#### 可选：扩展Outline
|
||||
```
|
||||
/research/add-items
|
||||
/research/add-fields
|
||||
```
|
||||
|
||||
#### 阶段3：生成报告
|
||||
```
|
||||
/research/report
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## References / 参考文献
|
||||
|
||||
- RhinoInsight: Improving Deep Research through Control Mechanisms for Model Behavior and Context
|
||||
|
||||
## License
|
||||
## License / 许可证
|
||||
|
||||
MIT
|
||||
|
||||
Reference in New Issue
Block a user