← Back to Skills Marketplace
shaopanguo

CNKI Scholar

by Chopin · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
670
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install cnki-scholar
Description
中文学术论文搜索工具。搜索中英文论文,覆盖知网、万方、维普等中文数据库的论文。Use when: 用户说「搜论文」「查文献」「知网」「CNKI」「搜索中文学术论文」「找中文文献」,或需要搜索、下载、引用中英文论文。支持OpenAlex API(免费,2亿+论文)和Crossref API(DOI覆盖)。Also...
README (SKILL.md)

CNKI Scholar — 中文学术论文搜索

基于OpenAlex和Crossref API的学术搜索工具,覆盖中英文论文(包括知网收录的论文)。

数据源

数据源 覆盖范围 优势 限制
OpenAlex 2亿+论文 免费、数据全、有被引量 部分中文论文元数据不完整
Crossref DOI论文 DOI解析准确 无被引量、中文覆盖少
百度学术 中英文 知网论文覆盖好 需浏览器自动化

核心功能

1. 搜索论文

使用OpenAlex API搜索:

curl -s "https://api.openalex.org/works?search=YOUR_QUERY&per_page=10"

支持的筛选参数:

  • search= — 关键词搜索
  • filter=publication_year:2020-2025 — 年份范围
  • filter=cited_by_count:>10 — 最低被引量
  • filter=primary_location.source.id:SOURCE_ID — 特定期刊
  • sort=cited_by_count:desc — 按被引量排序

2. 提取元数据

每个结果包含:

  • 标题 (title)
  • 作者 (authorships[].author.display_name)
  • 发表年份 (publication_year)
  • 期刊 (primary_location.source.display_name)
  • DOI (doi)
  • 被引量 (cited_by_count)
  • OpenAlex ID (id)

3. 下载PDF

OpenAlex提供OA(开放获取)链接:

  • 检查 open_access.is_oa 字段
  • 获取 open_access.oa_url 字段
  • 如果是OA论文,直接下载PDF

4. 导出引用

支持格式:

  • APA 7th: 作者. (年份). 标题. 期刊. DOI
  • BibTeX: 自动生成BibTeX条目
  • GB/T 7714: 中国标准引用格式

使用示例

搜索示例

用户:帮我搜一下多智能体编队控制的论文
→ 调用OpenAlex API搜索 "multi-agent formation control"
→ 返回top 10结果,按被引量排序
→ 展示标题、作者、年份、被引量、期刊

下载PDF示例

用户:这篇论文能下载吗?DOI: 10.1109/tie.2017.2701778
→ 检查OpenAlex的open_access字段
→ 如果是OA,提供下载链接
→ 如果不是OA,建议其他获取方式

引用导出示例

用户:帮我生成这篇论文的APA引用
→ 解析元数据
→ 生成APA 7th格式:
  Ge, X., & Han, Q.-L. (2017). Distributed Formation Control...
  IEEE Transactions on Industrial Electronics. https://doi.org/...

API调用脚本

搜索函数

search_papers() {
    local query="$1"
    local limit="${2:-10}"
    local year_filter="${3:-}"
    
    local url="https://api.openalex.org/works?search=${query}&per_page=${limit}"
    
    if [ -n "$year_filter" ]; then
        url="${url}&filter=publication_year:${year_filter}"
    fi
    
    curl -s "$url" | python3 -c "
import json, sys
d = json.load(sys.stdin)
for i, w in enumerate(d.get('results', []), 1):
    authors = ', '.join([a['author'].get('display_name','') for a in w.get('authorships',[])[:3]])
    if len(w.get('authorships',[])) > 3:
        authors += ' et al.'
    source = ''
    if w.get('primary_location',{}).get('source'):
        source = w['primary_location']['source'].get('display_name','')
    print(f\"{i}. {w.get('title','')}\")
    print(f\"   作者: {authors}\")
    print(f\"   年份: {w.get('publication_year','')}\")
    print(f\"   期刊: {source}\")
    print(f\"   被引: {w.get('cited_by_count',0)}\")
    print(f\"   DOI: {w.get('doi','')}\")
    oa = w.get('open_access',{})
    if oa.get('is_oa'):
        print(f\"   PDF: {oa.get('oa_url','')}\")
    print()
"
}

获取论文详情

get_paper_by_doi() {
    local doi="$1"
    curl -s "https://api.openalex.org/works/doi:${doi}"
}

生成APA引用

generate_apa() {
    local doi="$1"
    curl -s "https://api.openalex.org/works/doi:${doi}" | python3 -c "
import json, sys
w = json.load(sys.stdin)
authors = []
for a in w.get('authorships', []):
    name = a['author'].get('display_name', '')
    parts = name.split()
    if len(parts) >= 2:
        authors.append(f'{parts[-1]}, {parts[0][0]}.')
    else:
        authors.append(name)
author_str = ', '.join(authors[:7])
if len(w.get('authorships', [])) > 7:
    author_str += ', ...'
year = w.get('publication_year', 'n.d.')
title = w.get('title', 'Untitled')
source = ''
if w.get('primary_location',{}).get('source'):
    source = w['primary_location']['source'].get('display_name','')
doi = w.get('doi', '')
print(f'{author_str} ({year}). {title}. {source}. {doi}')
"
}

与百度学术的配合

对于知网独有(OpenAlex未收录)的论文,建议:

  1. 先用OpenAlex搜索(数据更结构化)
  2. 如果没找到,用 baidu-scholar-search 补充
  3. 两者结合基本覆盖所有中英文论文

限制

  • OpenAlex的中文论文覆盖不如英文完整
  • 部分中文论文缺少DOI
  • 被引量数据来自Crossref,可能与知网有差异
  • 不支持直接下载知网PDF(需要机构访问权限)

文件结构

cnki-scholar/
├── SKILL.md
└── references/
    ├── openalex-fields.md    # OpenAlex字段说明
    └── citation-formats.md   # 引用格式模板
Usage Guidance
This skill appears coherent and low-risk: it only issues queries to public OpenAlex/Crossref endpoints and formats citations using local curl+python3 commands. Before installing, note: (1) the skill does not directly integrate with CNKI/知网 — the CNKI coverage claim is optimistic and the skill suggests using a separate browser-automation tool for that, which could require additional software, logins, or violate site TOS; (2) downloading non-OA PDFs will typically fail without institution access — the skill correctly checks OpenAlex OA fields first; (3) ensure your agent environment has curl and python3 if you expect the examples to run; (4) the README's note about OpenAlex API key/rate limits may be imprecise — check OpenAlex's current docs if you plan heavy usage. If you require direct CNKI downloads or browser automation, request the skill author to provide explicit, auditable code and justification for any credentials or scraping tools before granting broader privileges.
Capability Analysis
Type: OpenClaw Skill Name: cnki-scholar Version: 1.0.0 The skill is a legitimate academic search tool that interfaces with the OpenAlex and Crossref APIs. It uses standard bash functions with curl and python3 to fetch and format bibliographic data (titles, authors, DOIs, and PDF links). The code logic in SKILL.md is transparent, lacks any obfuscation, and strictly adheres to the stated purpose of searching and citing scholarly literature without any signs of data exfiltration or malicious execution.
Capability Assessment
Purpose & Capability
The name/description promise (search Chinese academic literature including CNKI) maps to the provided OpenAlex/Crossref-based search and citation-generation instructions. However, claiming coverage of CNKI/知网 is potentially overstated: the skill relies on OpenAlex/Crossref (and optionally an external 'baidu-scholar-search' suggestion) rather than any direct CNKI API or credentials. The README itself notes OpenAlex has incomplete Chinese coverage, so the CNKI coverage claim should be treated as aspirational rather than demonstrated.
Instruction Scope
SKILL.md contains concrete curl + python3 examples that only call public OpenAlex/Crossref endpoints and parse results — this stays within the stated purpose. One instruction recommends falling back to a 'baidu-scholar-search' (browser automation) for CNKI-only items; that external scraping approach is not implemented here and could require additional tooling/credentials and may raise TOS/legal issues if used. The instructions do not read local files or environment variables beyond using curl/python3.
Install Mechanism
Instruction-only skill with no install spec and no code files — nothing is written to disk or downloaded by the skill itself. This is the lowest-risk install model.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. The runtime examples use only public APIs (OpenAlex/Crossref) and standard tools (curl, python3); requested access is proportionate to the task.
Persistence & Privilege
always is false and the skill does not request persistent/system privileges or modify other skills. The default ability for the agent to invoke the skill autonomously is normal and not a concern here given the skill's limited scope.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install cnki-scholar
  3. After installation, invoke the skill by name or use /cnki-scholar
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release - 中文学术论文搜索工具(基于OpenAlex API)
Metadata
Slug cnki-scholar
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is CNKI Scholar?

中文学术论文搜索工具。搜索中英文论文,覆盖知网、万方、维普等中文数据库的论文。Use when: 用户说「搜论文」「查文献」「知网」「CNKI」「搜索中文学术论文」「找中文文献」,或需要搜索、下载、引用中英文论文。支持OpenAlex API(免费,2亿+论文)和Crossref API(DOI覆盖)。Also... It is an AI Agent Skill for Claude Code / OpenClaw, with 670 downloads so far.

How do I install CNKI Scholar?

Run "/install cnki-scholar" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is CNKI Scholar free?

Yes, CNKI Scholar is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does CNKI Scholar support?

CNKI Scholar is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created CNKI Scholar?

It is built and maintained by Chopin (@shaopanguo); the current version is v1.0.0.

💬 Comments