paper-search — 多源学术论文检索

SkillSearch

Paper search sub-skill. Aggregates academic literature searches across four free sources—OpenAlex API (default), arXiv, Semantic Scholar, and CrossRef—returning structured paper metadata (including DOI / abstract / citation count). Zero configuration by default; optionally set EZMM_OPENALEX_EMAIL /

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the paper-search — 多源学术论文检索 skill

What this skill tells your AI

The instructions your AI receives, as published by woodfishhhh/ez_math_model in skills/ez-math-model/tools/paper_search/SKILL.md and read by ahel’s review.

何时使用

  • writer 在 pipeline 04 写理论性章节("为什么用 AHP" 等)
  • modeler 在 pipeline 02 选择非教科书算法时找文献
  • 任何需要"标题 → DOI → 摘要"的场景

入口脚本

scripts/openalex_scholar.py — OpenAlex 单源(首选,零配置) scripts/aggregated_search.py — 多源聚合(OpenAlex + arXiv + S2 + CrossRef)

命令行用法

# 单源(推荐先试)
python scripts/openalex_scholar.py "AHP TOPSIS comprehensive evaluation" --top-k 5

# 多源聚合(更全但慢)
python scripts/aggregated_search.py "grey prediction GM(1,1)" --top-k 8

# 输出到文件(用于 writer 后续读取)
python scripts/aggregated_search.py "Sobol sensitivity analysis" --top-k 5 \
  --out workdir/{task_id}/refs/sensitivity.json

输出格式(JSON 数组)

[
  {
    "title": "...",
    "authors": ["...", "..."],
    "year": 2022,
    "doi": "10.1109/...",
    "venue": "Journal / Conf",
    "abstract": "...(≤ 500 字符)",
    "cited_by_count": 132,
    "url": "https://doi.org/...",
    "source": "openalex | arxiv | s2 | crossref"
  }
]

writer 取后插入 footnote 候选;每条文献全文唯一引用一次。

配置

Env Var必需用途
EZMM_OPENALEX_EMAIL提供邮箱可提升 OpenAlex 配额
EZMM_S2_API_KEYSemantic Scholar 配额翻倍

不填仍可使用所有源的免费配额。

限速与重试

  • 单源失败重试 1 次(指数退避 1s, 4s)
  • 第 2 次失败 → 标记该源不可用,跳过
  • 至少 1 个源成功就返回结果,不强求全部

失败诊断

情况处理
全部源不可达(断网)stdout 输出 [],stderr 给出诊断
单源限流跳过;其他源继续
关键词太长自动截至 200 字符

Signals

GitHub stars
41
Forks
1
Last commit
Jul 2026
Advanced
Catalog kind
skill
Gateway key
paper-search-woodfishhhh
Source
github.com/woodfishhhh/ez_math_model