双引擎论文搜索

by XiaoMaColtAI

双引擎论文搜索 is an AI Engineering skill for Claude Code, published by XiaoMaColtAI in math-modeling-skill.

819 stars51 forkson XiaoMaColtAI/math-modeling-skillAdded 2026/08/23+8% in starsRepository updated 2026/08/22

View source on GitHub Download repo ZIP

claude-codeclaude-skillscodexcodex-skillcumcmdeepseek-harnessmath-modelingmcm-icmskillsvibe-coding

Install in seconds

Install 双引擎论文搜索

Copy 双引擎论文搜索 into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/XiaoMaColtAI/math-modeling-skill/tree/main/tools/paper_search ~/.claude/skills/paper_search

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/XiaoMaColtAI/math-modeling-skill.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: tools/paper_search/SKILL.md in XiaoMaColtAI/math-modeling-skill
Installs to: ~/.claude/skills/paper_search
Collection: One of 10 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What 双引擎论文搜索 does

双引擎论文搜索并行使用 OpenAlex 和 AnySearch 搜索论文，交叉匹配并输出可追溯的元数据。用于需要核验作者、题名、年份和来源的文献检索。

双引擎论文搜索 is cataloged under AI Engineering on DirSkills. 双引擎论文搜索 comes from a repository tagged claude-code, claude-skills, codex, codex-skill and cumcm.

Documentation

README

Excerpt

双引擎论文搜索

数据源

OpenAlex：结构化学术元数据。
AnySearch Academic：学术垂直搜索，支持当前 MCP Markdown 响应解析。

默认并行调用两个引擎。DOI 相同的记录直接交叉验证；无 DOI 时仅在标题高度相似且年份相容时合并。同一引擎中标题规范化后相同的预印本与正式出版记录也会折叠，并优先保留引用信息和元数据更完整的记录。交叉匹配结果、OpenAlex 独有结果和 AnySearch 独有结果分开输出。

融合时按查询词覆盖率过滤和重排，相关性优先于引用量，避免高被引但主题无关的论文挤占结果。包含多个专业术语时，候选文献至少命中两个有效查询词；这一阈值兼顾缺少摘要的元数据，不能代替人工核验。物理、材料和光学主题应组合使用材料名、机理名与模型名，例如 Sellmeier 4H-SiC Fabry-Perot；结果过少时逐步放宽查询，不直接接受无关结果。

使用

python scripts/hybrid_scholar.py --query "robust optimization vehicle routing" --limit 10 --json

如 AnySearch 需要鉴权：

$env:ANYSEARCH_API_KEY = "<密钥>"
python scripts/hybrid_scholar.py --query "analytic hierarchy process" --limit 8

诊断单个引擎时可用 --openalex-only 或 --anysearch-only；正式文献检索默认不得只运行一个引擎。

核验规则

This is the opening of the README. Read the full README on GitHub.

Frequently asked about 双引擎论文搜索

What else does XiaoMaColtAI publish alongside 双引擎论文搜索?
双引擎论文搜索 is one of 10 skills that DirSkills catalogs from XiaoMaColtAI/math-modeling-skill, the repository it ships in. Its siblings there include DOCX Tools, Excel Tools and LaTeX工具. Each one is a separate skill with its own page in this directory, installs the same way 双引擎论文搜索 does, and is maintained by XiaoMaColtAI in that same repository. The rest of the collection is listed on the XiaoMaColtAI/math-modeling-skill page.
How does 双引擎论文搜索 compare to other AI Engineering skills?
双引擎论文搜索 ranks #1568 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of 双引擎论文搜索 against them. Open each page to compare what they document and how they install.