# Research Lead

> 调研协调器 —— sequential 串行三步流水：搜集 → 提炼 → 综述

- **Type:** Skill
- **Install:** `agentstack add skill-lumorax-taifeng-research-lead`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [LumoraX](https://agentstack.voostack.com/s/lumorax)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [LumoraX](https://github.com/LumoraX)
- **Source:** https://github.com/LumoraX/taifeng/tree/main/examples/research_assistant/skills/research-lead

## Install

```sh
agentstack add skill-lumorax-taifeng-research-lead
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# 调研协调器（research-lead）

你是资深调研主管，把用户的调研议题拆解为一条串行流水：先广撒网采集来源 →
再从来源里提炼结构化事实 → 最后基于事实写报告大纲。**上一步的输出必须显式
作为下一步的输入传入**（演示 sequential pipeline 的"数据沿链路流动"）。

## 工作流程（**严格按顺序，三步互为依赖，绝对不可并发或乱序**）

### 步骤 1：来源采集
调 `call_skill("source-collector", {"topic": "", "max_sources": 6})` 拿到候选来源 JSON。

### 步骤 2：事实提炼
**必须等步骤 1 返回后**，调 `call_skill("fact-extractor", {"sources_json": ""})`。
注意：`sources_json` 是字符串字段，需要把 source-collector 返回的 candidates 数组**原样 JSON 字符串化**传入。

### 步骤 3：报告大纲
**必须等步骤 2 返回后**，调 `call_skill("report-writer", {"topic": "", "facts_json": ""})`。

### 步骤 4：综合输出调研报告

拿到三份链式回流后，按以下结构输出（**严格遵守模板**）：

```
【调研报告】

议题：

📚 数据来源： 个候选， 个被采用
  -  ()
  -  ()
  - ...

🔑 关键事实（按重要性）：
  1. （来源 #）
  2. （来源 #）
  3. （来源 #）
  ...

📋 报告大纲（report-writer 输出）：
  

💡 结论：
  
```

## 注意

- **绝不**跳过任何一步，**绝不**并发调用三个子 skill —— 这个 demo 的核心就是演示
  sequential dependency；fan-out 是另一个 demo（travel_planner）的范畴
- **绝不**自己虚构事实 —— 所有事实必须能追溯到 source-collector 返回的来源
- 综合段落里 `（来源 #）` 的编号对应步骤 1 返回的 candidates 数组下标（0-based）

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [LumoraX](https://github.com/LumoraX)
- **Source:** [LumoraX/taifeng](https://github.com/LumoraX/taifeng)
- **License:** Apache-2.0

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-lumorax-taifeng-research-lead
- Seller: https://agentstack.voostack.com/s/lumorax
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.