Deep Research Pro v5.0.1

# Skill: Deep Research Pro (v5.0 - 洞察引擎)

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "Deep Research Pro v5.0.1" with this command: npx skills add xueylee-dotcom/deep-research-v50

Skill: Deep Research Pro (v5.0 - 洞察引擎)

版本:5.0.1 描述:真深度研究技能 - 三阶段合成 + 失败即停止

核心原则

深度不是"写得多",而是"每一行数据都可溯源"。


🔴 v5.0.1 强制规则(新增)

规则1:提取失败必须明确报错

# 如果提取的数据不满足最低要求,输出:
{
  "error": "提取失败",
  "reason": "样本量缺失 / 主要结果缺失 / 原文引用不足30字",
  "suggestion": "跳过此来源或人工复核"
}

规则2:质量评分必须校验内容

质量评分逻辑:
- 有样本量 + 主要结果 + 原文引用 ≥ 30字 → 8.0-9.0
- 有2项 → 7.0-7.5
- 有1项或全是"见原文" → 标记为"待验证",不评分

规则3:报告必须区分"已验证"和"待验证"

## 已验证结论(基于核心论文)

### 结论1:LSTM在ICU场景预测准确率达0.87
- 来源:card-002 (PMC11110807)
- 证据:样本量1,250, 95%CI 0.82-0.91, p<0.001
- 原文引用:"The LSTM model achieved..." (Results, p.5)

## 待验证线索(基于元数据)

### 线索1:远程医疗或可节省成本
- 来源:card-001 (PubMed摘要)
- 状态:⚠️ 需人工访问原文验证

执行流程

Step 1: 检索与提取

# 使用PubMed API获取结构化数据
python3 scripts/extract-pmc.py <pmid>

# 如果返回error,跳过该来源
# 如果数据不全,标记为"待验证"

Step 2: 卡片生成(强制校验)

---
source_id: card-xxx
status: verified | pending | failed
quality_score: 8.5 | N/A
---

## 1. 核心数据提取

| 指标 | 数值 | 验证状态 |
|------|------|----------|
| 样本量 | 9,080 | ✅ 已提取 |
| 主要结果 | 未提取 | ⚠️ 待验证 |
| 原文引用 | "..."(30字+) | ✅ 已提取 |

## 2. 质量说明

- 数据完整度:2/3
- 建议:访问原文验证主要结果

Step 3: 报告生成(明确区分)

禁止:混合使用"已验证"和"待验证"数据

要求

  • 已验证结论:单独章节
  • 待验证线索:单独章节 + 警告标识

质量门禁

  1. 卡片数量:≥5个有完整数据的
  2. 溯源验证:100%通过
  3. 明确区分:已验证 vs 待验证

v5.0.1 vs v5.0 对比

维度v5.0v5.0.1
提取失败静默填充"见原文"明确报错
质量评分虚高(8.5分但空洞)必须校验内容
报告生成混合使用数据明确区分已验证/待验证

Skill版本:5.0.1 | 最后更新:2026-03-19

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Research

Deep Research Pro v2.1

Conducts stepwise in-depth research by generating detailed source cards with data, quotes, quality scores, cross-analyzing findings, and producing fully cite...

Registry SourceRecently Updated
1870Profile unavailable
Research

Deep Research Pro v2

提供完整多阶段深度研究,覆盖规划、跨源检索、质量筛选、深入分析、交叉验证及结构化报告生成。

Registry SourceRecently Updated
1940Profile unavailable
Research

Wisdom Dating. 智慧约会。Sabiduría.

Wisdom dating for AI agents — wise dating, wisdom-deep connections, and wisdom-guided matching. Date with intention, match with wisdom. Dating wisdom-first o...

Registry SourceRecently Updated
1020Profile unavailable
Research

Owl Dating. 猫头鹰约会。Búho.

Owl dating for AI agents — owl-wise dating, owl-deep connections, and owl-hours conversations. The wisest buddy dates the deepest. Dating owl-eyed on inbed.a...

Registry SourceRecently Updated
1080Profile unavailable