首页/医疗与健康/medical-imaging-review
M

medical-imaging-review

by @luwillv
4.2(20)

医学影像 AI 综述写作工具。提供结构化 7 阶段工作流,覆盖冠脉 CT、肺部影像、脑部 MRI、心脏影像、病理切片、视网膜等多个领域,支持 Zotero 文献管理集成,含质量检查清单。

medical-imagingliterature-reviewacademicairesearchGitHub
安装方式
npx skills add https://github.com/luwill/research-skills --skill medical-imaging-review
compare_arrows

Before / After 效果对比

1 组
使用前

手动整理数百篇论文,写作结构混乱,容易遗漏重要文献和领域

使用后

7 阶段结构化工作流自动引导,覆盖 6 大影像领域模板,Zotero 集成管理文献,质量清单确保完整性

SKILL.md

Medical Imaging AI Literature Review Skill

Write comprehensive literature reviews following a systematic 7-phase workflow.

Quick Start

  1. Initialize project with three core files:

    • CLAUDE.md - Writing guidelines and terminology
    • IMPLEMENTATION_PLAN.md - Staged execution plan
    • manuscript_draft.md - Main manuscript
  2. Follow the 7-phase workflow (see references/WORKFLOW.md)

  3. Use domain-specific templates (see references/DOMAINS.md)


Core Principles

Writing Style

  • Hedging language: "may", "suggests", "appears to", "has shown promising results"
  • Avoid absolutes: Never say "X is the best method"
  • Citation support: Every claim needs reference
  • Limitations: Each method section needs a Limitations paragraph

Required Elements

  • Key Points box (3-5 bullets) after title
  • Comparison table for each major section
  • Performance metrics: Dice (0.XXX), HD95 (X.XX mm)
  • Figure placeholders with detailed captions
  • References: 80-120 typical, organized by topic

Paragraph Structure

Topic sentence (main claim)
  → Supporting evidence (citations + data)
  → Analysis (critical evaluation)
  → Transition to next paragraph

Literature Sources

Use multi-source strategy for comprehensive coverage:

SourceBest ForTools
ArXivLatest DL methods, preprintssearch_papers, read_paper
PubMedClinical validation, peer-reviewedpubmed_search_articles
ZoteroExisting library, organized refszotero_search_items

For MCP configuration details, see references/MCP_SETUP.md.


Standard Review Structure

# [Title]: State of the Art and Future Directions

## Key Points
- [3-5 bullets summarizing main findings]

## Abstract

## 1. Introduction
### 1.1 Clinical Background
### 1.2 Technical Challenges
### 1.3 Scope and Contributions

## 2. Datasets and Evaluation Metrics
### 2.1 Public Datasets (Table 1)
### 2.2 Evaluation Metrics

## 3. Deep Learning Methods
### 3.1 [Category 1]
### 3.2 [Category 2]
(Table 2: Method Comparison)

## 4. Downstream Applications

## 5. Commercial Products & Clinical Translation (Table 3)

## 6. Discussion
### 6.1 Current Limitations
### 6.2 Future Directions

## 7. Conclusion

## References

Method Description Template

### 3.X [Method Category]

[1-2 paragraph introduction with motivation]

**[Method Name]:** [Author] et al. [ref] proposed [method], which [innovation]:
- [Key component 1]
- [Key component 2]
Achieves Dice of X.XX on [dataset].

**Limitations:** Despite advantages, [category] methods face:
(1) [limit 1]; (2) [limit 2].

Citation Patterns

# Data citation
"...achieved Dice of 0.89 [23]"

# Method citation
"Gu et al. [45] proposed..."

# Multi-citation
"Several studies demonstrated... [12, 15, 23]"

# Comparative
"While [12] focused on..., [15] addressed..."

Reference Files

FilePurpose
references/WORKFLOW.mdDetailed 7-phase workflow
references/TEMPLATES.mdCLAUDE.md and IMPLEMENTATION_PLAN.md templates
references/DOMAINS.mdDomain-specific method categories
references/MCP_SETUP.mdMCP server configuration
references/QUALITY_CHECKLIST.mdPre-submission quality checklist

用户评价 (0)

发表评价

效果
易用性
文档
兼容性

暂无评价

统计数据

安装量689
评分4.2 / 5.0
版本
更新日期2026年10月23日
对比案例1 组

用户评分

4.2(20)
5
50%
4
50%
3
0%
2
0%
1
0%

为此 Skill 评分

0.0

兼容平台

🔧Claude Code

时间线

创建2026年4月6日
最后更新2026年10月23日
🎁 Agent 知识卡片
调研问卷