LeoYeAI/agent-master-skills / skills/ai-powered-literature-review-skills
literature-reviewer-skill
Unverified根据用户提供的论文主题,进行系统性中英文文献回顾(Literature Survey)。 采用8阶段工作流,支持CNKI、Web of Science、ScienceDirect等主流数据库, 无需API配置,通过浏览器自动化获取文献信息。 输出包含GB/T 7714-2015引文、标题、摘要的Markdown文档。 当用户提到"文献回顾"、"文献综述"、"帮我找文献"、"中英文文献搜索"、"写综述"等关键词时触发。 NOTE: The 'examples/' folder contains sample outputs and is not included in skill installation.
| File | Kind | Size |
|---|---|---|
| AGENTS.md | markdown | 12.8 KB |
| README.md | markdown | 19.7 KB |
| SECURITY.md | markdown | 5.1 KB |
| SKILL.md | skill md | 22.1 KB |
| _meta.json | config | 316 B |
| agents/explore-agent.md | markdown | 4.2 KB |
| agents/orchestrator.md | markdown | 17.3 KB |
| agents/synthesize-agent.md | markdown | 12.4 KB |
| agents/verify-agent.md | markdown | 2.3 KB |
| docker-compose.yml | config | 3.3 KB |
| install.yaml | config | 2.6 KB |
| mcp.json | config | 5.6 KB |
| references/cnki-guide.md | markdown | 10.0 KB |
| references/database-access.md | markdown | 3.1 KB |
| references/gb-t-7714-2015.md | markdown | 10.8 KB |
| scripts/__init__.py | script | 519 B |
| scripts/citation_formatter.py | script | 5.3 KB |
| scripts/deduplicate_papers.py | script | 4.8 KB |
| scripts/models.py | script | 2.6 KB |
scripts/citation_formatter.py
View on GitHub#!/usr/bin/env python3
"""
引用格式化工具
支持 GB/T 7714-2015 格式
"""
from typing import Dict, List, Optional
def format_author_name(name: str, lang: str = "en") -> str:
"""
格式化作者姓名
Args:
name: 作者姓名
lang: 语言 (zh/en)
Returns:
格式化后的作者名
"""
if not name:
return ""
if lang == "zh":
# 中文:保持原样
return name.strip()
else:
# 英文:姓, 名首字母
parts = name.strip().split()
if len(parts) >= 2:
surname = parts[-1]
initials = "".join([p[0] + "." for p in parts[:-1] if p])
return f"{surname} {initials}"
return name.strip()
def format_authors(authors: List[str], lang: str = "en") -> str:
"""
格式化作者列表
Args:
authors: 作者列表
lang: 语言
Returns:
格式化后的作者字符串
"""
if not authors:
return ""
formatted = [format_author_name(a, lang) for a in authors if a]
if lang == "zh":
# 中文:用逗号分隔
return ", ".join(formatted)
else:
# 英文:最后两个用 "and" 连接
if len(formatted) == 1:
return formatted[0]
elif len(formatted) == 2:
return " and ".join(formatted)
else:
return ", ".join(formatted[:-1]) + ", and " + formatted[-1]
def format_citation_gb7714(paper: Dict, index: str = "") -> str:
"""
格式化为 GB/T 7714-2015 格式
Args:
paper: 文献字典
index: 文献编号 (如 C1, E1)
Returns:
GB/T 7714-2015 格式的引文
"""
lang = paper.get("language", "en")
authors = paper.get("authors", [])
title = paper.get("title", "")
journal = paper.get("journal", "")
year = paper.get("year", "")
volume = paper.get("volume", "")
issue = paper.get("issue", "")
pages = paper.get("pages", "")
doi = paper.get("doi", "")
# 格式化作者
author_str = format_authors(authors, lang)
# 构建卷期页字符串
vol_issue = ""
if volume:
vol_issue = volume
if issue:
vol_issue += f"({issue})"
if pages:
vol_issue += f": {pages}"
elif pages:
vol_issue = pages
# 构建引文
if lang == "zh":
# 中文期刊格式
citation = f"[{index}] {author_str}. {title}[J]. {journal}"
if year:
citation += f", {year}"
if vol_issue:
citation += f", {vol_issue}"
if doi:
citation += f". DOI:{doi}"
citation += "."
else:
# 英文期刊格式
citation = f"[{index}] {author_str}. {title}[J]. {journal}"
if year:
citation += f", {year}"
if vol_issue:
citation += f", {vol_issue}"
if doi:
citation += f". DOI:{doi}"
citation += "."
return citation
def format_citation_list(papers: List[Dict], prefix: str = "E") -> List[str]:
"""
格式化文献列表
Args:
papers: 文献列表
prefix: 编号前缀 (C/E)
Returns:
格式化后的引文列表
"""
citations = []
for i, paper in enumerate(papers, 1):
index = f"{prefix}{i}"
citation = format_citation_gb7714(paper, index)
citations.append(citation)
return citations
def generate_reference_md(papers_zh: List[Dict], papers_en: List[Dict]) -> str:
"""
生成参考文献 Markdown 文档
Args:
papers_zh: 中文文献列表
papers_en: 英文文献列表
Returns:
Markdown 格式的参考文献
"""
lines = ["# 参考文献\n"]
# 中文文献
if papers_zh:
lines.append("## 中文文献\n")
for i, paper in enumerate(papers_zh, 1):
citation = format_citation_gb7714(paper, f"C{i}")
lines.append(f"{citation}\n")
lines.append("")
# 英文文献
if papers_en:
lines.append("## 英文文献\n")
for i, paper in enumerate(papers_en, 1):
citation = format_citation_gb7714(paper, f"E{i}")
lines.append(f"{citation}\n")
lines.append("")
return "\n".join(lines)
if __name__ == "__main__":
# 测试示例
test_papers = [
{
"id": "C1",
"title": "基于深度学习的医学图像诊断研究",
"authors": ["张三", "李四", "王五"],
"journal": "计算机学报",
"year": 2023,
"volume": "46",
"issue": "5",
"pages": "1023-1035",
"doi": "10.xxxx",
"language": "zh"
},
{
"id": "E1",
"title": "Deep learning for medical image analysis",
"authors": ["Smith J", "Johnson K", "Lee M"],
"journal": "Nature Medicine",
"year": 2022,
"volume": "28",
"issue": "8",
"pages": "1500-1510",
"doi": "10.1038/s41591-022-01900-0",
"language": "en"
}
]
print("中文文献示例:")
print(format_citation_gb7714(test_papers[0], "C1"))
print()
print("英文文献示例:")
print(format_citation_gb7714(test_papers[1], "E1"))
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |