Xpersona
�

📚 智能文献综述生成器

CLAWHUB · Unverified

Literature review paper writing assistant — guides you through the full lifecycle: (1) Systematic search using PICO/Boolean/MeSH frameworks across arXiv, Sem... Skill: 📚 智能文献综述生成器 Owner: sherry-zh0u Summary: Literature review paper writing assistant — guides you through the full lifecycle: (1) Systematic search using PICO/Boolean/MeSH frameworks across arXiv, Sem... Tags: latest:1.0.0 Version history: v1.0.0 | 2026-05-20T12:18:32.946Z | user Initial release — literature review paper writing assistant. - Guides users through systematic literature search using PICO/Boolean/Me

62
Rank
84
Safety
986
Downloads

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 986 downloads reported by the source. Last updated 10/11/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Install and run

Setup complexity: low.

clawhub skill install s173r8yvwsxztdm3sr332ef001866e3d:literature-review-writing-assistant
  1. Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
  2. Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-sherry-zh0u-literature-review-writing-assistant/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

21,395 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: review-paper-writing
description: |
  Literature review paper writing assistant — guides you through the full lifecycle:
  (1) Systematic search using PICO/Boolean/MeSH frameworks across arXiv, Semantic Scholar, OpenAlex, CrossRef & PubMed;
  (2) DOI & arXiv ID validation with cross-source conflict detection;
  (3) Multi-format citation output (APA 7th, MLA 9th, IEEE, BibTeX, RIS, Markdown);
  (4) Auto-generated structured literature review with timeline, keyword extraction & source-quality tagging.
  Use when drafting a review article, survey paper, or thesis background chapter — or when given a topic to compile references for.
---

# Review Paper Writing Skill

## Overview

This skill helps you write a thorough, well-structured literature review — from topic definition and systematic search to formatted citations and a polished markdown draft. It covers:

- **Topic framing** with PICO framework
- **Search strategy** (Boolean, MeSH, wildcards, proximity)
- **Multi-source academic search** (arXiv, Semantic Scholar, OpenAlex, CrossRef, PubMed)
- **DOI / arXiv ID validation** and conflict detection
- **Citation formatting** (APA, MLA, IEEE, BibTeX, RIS, Markdown)
- **Auto-generated literature review** in Markdown

## Quick Start

### 1. Run a Search

```bash
python3 scripts/lit_search.py "large language model education" -n 20 --sources arxiv openalex
```

### 2. Validate DOIs

```bash
python3 scripts/lit_search.py "machine learning" --validate
```

### 3. Format Citations

```bash
python3 scripts/lit_search.py "BERT" -n 10 -f apa      # APA 7th
python3 scripts/lit_search.py "transformer" -n 10 -f bibtex  # BibTeX
python3 scripts lit_search.py "attention" -n 10 -f ris     # RIS
```

### 4. Filter Results

| Flag | Effect |
|------|--------|
| `--published-only` | Exclude arXiv preprints |
| `--preprint-only` | Only arXiv preprints |
| `--min-year 2020` | Earliest publication year |
| `--min-citations 50` | Minimum citation count |
| `--conflicts` | Detect cross-source metadata conflicts |

### 5. Batch Mode (from file)

Create `papers.txt` with one DOI/PMID/arXiv ID per line:
```
10.48550/arXiv.2303.08774
10.48550/arXiv.2205.11916
PMID: 34567890
```
Then:
```bash
python3 scripts/lit_search.py file://papers.txt -f bibtex
```

## Search Strategy Framework

### PICO Framework

Use PICO to structure your research question:

| Element | Meaning | Example |
|---------|---------|---------|
| **P**opulation | Target group | high school students |
| **I**ntervention | Treatment or method | motivational interviewing |
| **C**omparator | Control group | no intervention |
| **O**utcome | Measurable result | academic performance |

Convert to search terms:
```
P: student*
I: "motivational interviewing"
O: "academic achievement"
→ "motivational interviewing" AND student* AND "academic achievement"
```

### Boolean Operators

```python
# AND: all terms must appear
"cognitive behavioral therapy" AND adolescent*

# OR: any term may appear
depression OR anx

README.md

# Review Paper Writing

**Literature review paper writing assistant for systematic, multi-source academic research.**

## Features

- 🔍 **Systematic Search** — PICO framework, Boolean operators, MeSH terms, wildcards, proximity search
- 🌐 **Multi-Source Coverage** — arXiv, Semantic Scholar, OpenAlex, CrossRef, PubMed
- ✅ **DOI & ID Validation** — HEAD requests + CrossRef confirmation, conflict detection across sources
- 📄 **Citation Formatting** — APA 7th, MLA 9th, IEEE, BibTeX, RIS, Markdown
- 📊 **Auto-Generated Review** — Timeline, keyword extraction, source-quality tagging
- 🔎 **Conflict Detection** — Flags mismatches in title/year/authors for the same DOI

## Quick Start

```bash
# Search across multiple sources
python3 scripts/lit_search.py "large language model education" -n 20 --sources arxiv openalex

# APA format
python3 scripts/lit_search.py "BERT" -n 10 -f apa

# Validate DOIs
python3 scripts/lit_search.py "machine learning" --validate

# Exclude preprints, only published work
python3 scripts/lit_search.py "attention mechanism" --published-only

# Detect cross-source conflicts
python3 scripts/lit_search.py "transformer architecture" --conflicts
```

## Supported Citation Formats

| Format | Use Case |
|--------|----------|
| `apa` | Humanities, Social Sciences |
| `mla` | Literature, Languages |
| `ieee` | Engineering, Computer Science |
| `bibtex` | LaTeX / Overleaf |
| `ris` | EndNote, Zotero |
| `markdown` | Direct document use |

## Search Strategy Guide

See `references/search_strategy.md` for:
- PICO framework for question framing
- Boolean search syntax
- MeSH term usage (PubMed)
- Wildcards and truncation
- Proximity operators
- Per-database syntax reference

## API Reference

See `references/api_reference.md` for detailed API documentation on:
- Semantic Scholar Graph API
- OpenAlex API
- CrossRef API
- PubMed E-utilities
- DOI resolution & validation logic

## Requirements

- Python 3.8+
- `requests` library

```bash
pip install requests
```

## Optional: Semantic Scholar API Key

Get a free key at https://www.semanticscholar.org/api-keys

Edit `scripts/lit_search.py`:
```python
API_KEYS = {
    "semantic_scholar": "your-api-key"
}
```

## License

MIT

_meta.json

{
  "ownerId": "kn7fwgwvg462484dm88mqp1ayh867jjf",
  "slug": "literature-review-writing-assistant",
  "version": "1.0.0",
  "publishedAt": 1779279512946
}

references/api_reference.md

# Literature Review API Reference

## 1. Semantic Scholar API

### Endpoint
```
GET https://api.semanticscholar.org/graph/v1/paper/search
```

### Parameters
| 参数 | 类型 | 说明 |
|------|------|------|
| query | string | 搜索主题 |
| limit | int | 返回数量 (默认10, 最大100) |
| offset | int | 分页偏移 |
| fields | string | 返回字段 (title,authors,year,venue,abstract,citationCount,externalIds) |

### Response (paper)
```json
{
  "paperId": "...",
  "title": "...",
  "authors": [{"name": "...", "authorId": "..."}],
  "year": 2024,
  "venue": "...",
  "abstract": "...",
  "citationCount": 100,
  "externalIds": {"DOI": "...", "PMID": "..."}
}
```

### Rate Limit
- 100 requests/5 seconds (无API key)
- 1000 requests/5 seconds (需要API key)

---

## 2. OpenAlex API

### Endpoint
```
GET https://api.openalex.org/works
```

### Parameters
| 参数 | 类型 | 说明 |
|------|------|------|
| search | string | 搜索主题 |
| per-page | int | 每页数量 (默认25, 最大200) |
| filter | string | 过滤条件 |
| sort | string | 排序方式 |

### Response (work)
```json
{
  "id": "https://openalex.org/W...",
  "title": "...",
  "authorships": [{"author": {"display_name": "..."}}],
  "publication_year": 2024,
  "primary_location": {"source": {"display_name": "..."}},
  "abstract": "...",
  "cited_by_count": 100,
  "doi": "https://doi.org/...",
  "pmid": "..."
}
```

### Rate Limit
- 100,000 requests/day (免费)

---

## 3. CrossRef API

### Endpoint
```
GET https://api.crossref.org/works
```

### Parameters
| 参数 | 类型 | 说明 |
|------|------|------|
| query | string | 搜索词 |
| rows | int | 返回数量 (默认20, 最大1000) |
| select | string | 选择字段 |

### Response
```json
{
  "message": {
    "items": [{
      "DOI": "10.xxxx/xxxxx",
      "title": ["..."],
      "author": [{"given": "...", "family": "..."}],
      "published-print": {"date-parts": [[2024]]},
      "container-title": ["..."],
      "type": "journal-article"
    }]
  }
}
```

### Rate Limit
- 50 requests/second

---

## 4. PubMed API (E-utilities)

### Endpoint
```
GET https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi
GET https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi
```

### Parameters (esearch)
| 参数 | 类型 | 说明 |
|------|------|------|
| db | string | 数据库 (pubmed) |
| term | string | 搜索词 |
| retmax | int | 返回数量 |
| retmode | string | 返回模式 (json) |

### Parameters (esummary)
| 参数 | 类型 | 说明 |
|------|------|------|
| db | string | 数据库 |
| id | string | PubMed ID |
| retmode | string | 返回模式 (json) |

### Rate Limit
- 3 requests/second
- 10 requests/second (with API key)

---

## 5. DataCite API

### Endpoint
```
GET https://api.datacite.org/dois
```

### Parameters
| 参数 | 类型 |说明|
|------|------|------|
| query | string | DOI 查询 |
| rows | int | 返回数量 |

### Response
```json
{
  "data": [{
    "id": "https://doi.org/...",
    "attributes": {
      "titles": [{"title": "..."}],
      "authors": [{"given": "...", "family": "..."}],
      "published": "2024",
      "container-title": ["..."]
    }
  }]
}
```

### Rate Limit
- 30 requests/second

---

## 6. DOI Resoluti

references/search_strategy.md

# 搜索策略指南（基于 Hempel Chapter 3）

## 1. PICO 框架

### 定义
PICO 是构建系统综述问题的框架：

| 元素 | 全称 | 说明 | 示例 |
|------|------|------|------|
| P | Population | 研究人群 | 高中生、大学生 |
| I | Intervention | 干预措施 | 动机访谈、认知行为疗法 |
| C | Comparator | 对照组 | 无干预、常规处理 |
| O | Outcome | 结局指标 | 学业成绩、心理健康 |

### 自然语言转换
```
P: 学生
I: 动机访谈
O: 学业成绩
↓
搜索词: "motivational interviewing" AND student* AND academic achievement
```

## 2. 布尔搜索

### 基本操作
```python
# AND: 同时包含两个词
"motivation interviewing" AND school

# OR: 包含任一词
depression OR anxiety OR mental health

# NOT: 排除词
animal NOT pet
```

### 优先级
```python
# 使用括号分组
("cognitive behavioral therapy" OR CBT) AND adolescent*
```

## 3. 通配符和截词

```python
# * 截词（任意后缀）
student* → student, students, student's

# ? 单字符替代
wom?n → woman, women
```

## 4. 邻近搜索

```python
# adjective 在名词前
behavior N/2 change

# 同一句中
"stress" ADJ3 "coping"
```

## 5. 索引词（MeSH）

### PubMed MeSH
```python
# 主要 MeSH
"Motor Activity"[Mesh]

# 限定词
"Depression"[Mesh] AND "Therapy"[Mesh:Subheading]
```

### 字段搜索
```python
# 标题中搜索
ti:intervention

# 摘要中搜索
ab:random*

# 关键词
kw:machine learning
```

## 6. 过滤器

### 研究类型
```python
# 随机对照试验
randomized controlled trial[pt]

# 综述
review[pt] AND systematic[sbbb]

# 元分析
meta-analysis[pt]
```

### 日期范围
```python
# 最近5年
"2019/01/01"[PDAT] : "2024/12/31"[PDAT]

# 特定年份
2024[dp]
```

### 物种
```python
# 只 Human
humans[mesh]

# 只 animals
animals[mesh]
```

## 7. 数据库特定语法

### PubMed
```python
# 简单搜索
"motivational interviewing"[Title/Abstract]

# MeSH 术语
"Motor Activity"[Mesh] AND "Adolescent"[Mesh]

# 组合
("Anxiety"[Mesh] OR "Anxiety Disorders"[Mesh]) 
AND ("Cognitive Therapy"[Mesh] OR "Behavior Therapy"[Mesh])
AND 2020:2024[dp]
```

### PsycINFO (OVID)
```python
# 关键词加字段
motivation interview*.tw

# MeSH
exp Motivational Interviewing/

# 组合
(exp Motivation/ OR exp Motivation Techniques/)
AND (exp Intervention/ OR exp Treatment/)
AND adolescent*.mp
```

### Web of Science
```python
# 主题搜索
TS=("motivational interviewing" AND school*)

# 复合查询
TS=(cognitive AND ("behavior therapy" OR CBT))
PY=2020-2024
```

## 8. 搜索策略开发流程

### 步骤
1. **确定核心概念** → 从 PICO 提取关键词
2. **列出同义词** → synonym, hyphenated, alternate spelling
3. **构建搜索块** → 每个概念单独的搜索
4. **组合** → 用 AND 连接搜索块
5. **测试** → 调整搜索词数量（目标：100-500 篇）
6. **记录** → 保存最终搜索策略

### 示例：动机访谈
```
核心概念1: motivation* interview*
  - "motivational interviewing"
  - "motivational interview"
  - MI

核心概念2: school*
  - school
  - schools
  - school*

核心概念3: adolescent*
  - adolescent
  - adolescents
  - teen
  - teenager
  - youth

搜索策略:
("motivational interviewing" OR "motivational interview" OR MI) 
AND (school OR schools) 
AND (adolescent OR teen OR teenager OR youth)
```

## 9. 搜索优化

### 结果太少？
- 移除 AND 连接的一个概念
- 改为 OR 连接同义词
- 放宽日期限制
- 移除 NOT 排除词

### 结果太多？
- 添加更多 AND 概念
- 缩小日期范围
- 添加强制性过滤器（human, English）
- 使用更具体的术语

## 10. 搜索策略记录模板

```markdown
## 搜索策略记录

### 日期
2024-XX-XX

### 数据库
PubMed, PsycINFO, Web of Science

### 搜索策略
| 数据库 | 搜索策略 | 结果数 |
|---------|----------|--------|
| PubMed | (1) AND (2) | XX |
| PsycI

Sponsored

Ads related to 📚 智能文献综述生成器 and adjacent AI workflows.