Literature Search logo

Literature Search

Community
ssinder
literature-search

This skill should be used when mining academic literature from PubMed, OpenAlex or Semantic Scholar — searching papers by topic or keywords, deduplicating multi-source results, filtering by relevance or citation count, enriching missing abstracts, and exporting RIS, BibTeX or GB/T 7714 citations. 用于多源学术文献检索、去重、相关性筛选、摘要富集与参考文献格式导出的场景。

Overview

Publisherssinder
Repositorybioinformatics-agent-skills
Skill nameliterature-search
Stars
75
Forks
2
Bundled files
6
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 6 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by ssinder on GitHub. Read the source before you install it.

Installation

Install the Literature Search AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/ssinder/bioinformatics-agent-skills/tree/main/skills/literature-search
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ssinder/bioinformatics-agent-skills.git /tmp/bioinformatics-agent-skills
mkdir -p .claude/skills
cp -r /tmp/bioinformatics-agent-skills/skills/literature-search .claude/skills/literature-search
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Literature Search in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Literature Search on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Literature Search is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Overview

在 PubMed、OpenAlex、Semantic Scholar 三个公开文献库上按主题或关键词检索论文,把异构结果归一化到统一 schema,按 DOI 与标题模糊匹配两级去重,再按相关性、引用数与年份做筛选,为缺摘要的文献从三个源依次补全摘要,最后导出可直接投稿使用的引用格式。

所有主题、关键词、年份范围与数据源都是命令行参数,不绑定任何具体疾病或课题,因此可用于任何研究方向的系统综述式检索。

When to Use This Skill

  • 需要围绕某个主题快速摸清 PubMed 上的文献分布(如 antimicrobial peptide、protein structure prediction)
  • 需要跨多个文献库做覆盖更全的检索并合并去重
  • 手头已有文献 CSV,但需要重新打分、筛选、清洗
  • 手头有一批文献缺摘要,需要从 OpenAlex / Semantic Scholar 补全
  • 需要把文献列表导出为 RIS / BibTeX / GB/T 7714 参考文献格式

Quick Start

bash
export PYTHONPATH="$PWD/packages"

# 1) 单源检索(PubMed)
python skills/literature-search/scripts/search_literature.py \
    --topic "antimicrobial peptide" --source pubmed \
    --date-range 2020: --max-results 50 \
    --output results/amp_pubmed.csv

# 2) 三源联合检索 + 摘要富集 + 相关性过滤
python skills/literature-search/scripts/search_literature.py \
    --topic "protein structure prediction" \
    --keywords "AlphaFold" "molecular dynamics" \
    --source pubmed openalex semantic-scholar \
    --date-range 2018:2024 --min-citations 20 --enrich-abstracts \
    --sort-by relevance --output results/prediction.csv

# 3) 离线处理已有 CSV(不联网):重新打分 + 去重 + 排除词筛选
python skills/literature-search/scripts/search_literature.py \
    --input results/raw.csv --keywords "antifungal" \
    --exclude-terms "review" "protocol" \
    --min-relevance 3 --output results/filtered.csv

# 4) 导出引用格式
python skills/literature-search/scripts/export_citations.py \
    --input results/prediction.csv --format bibtex ris gbt7714 \
    --output-dir results/citations

Workflow

  1. 检索:按 --source 逐源调用 API
    • PubMed:esearch.fcgi 拿 PMID → esummary.fcgi 批量拿元数据
    • OpenAlex:works 端点,用 filter=from_publication_date:...,to_publication_date:... 做年份过滤
    • Semantic Scholar:graph/v1/paper/search,用 year=起始-结束 做年份过滤
  2. 归一化:所有记录统一为 title/authors/year/doi/journal/abstract/citations/source/pmid/url/type/oa_status
  3. 打分:按关键词命中(标题权重 3.0、摘要权重 1.0)+ 引用数对数饱和 + 近期加成,得到 relevance
  4. 去重:DOI 精确匹配优先,其次标题归一化后的 difflib 模糊匹配(默认阈值 0.92);被去掉的记录信息合并回保留记录(补摘要、累计引用、标记多来源)
  5. 筛选:相关性与引用数阈值 + 包含/排除词 + 年份区间
  6. 摘要富集(可选):PubMed(efetch XML) → OpenAlex(倒排索引重建) → Semantic Scholar(abstract/tldr) 依次尝试
  7. 导出:统一 schema CSV(UTF-8 BOM,Excel 直开)+ 可选 JSON

Parameters

参数说明默认值
--topic自由文本检索主题(作为主检索式)无
--keywords附加关键词,AND 收窄检索 + 参与相关性打分空
--source数据源,可多选:pubmed / openalex / semantic-scholarpubmed
--date-range年份区间 START:END,如 2018:2024、2020:、:2015不限
--max-results每源每查询最大返回条数50
--input已有 CSV(提供时不联网)无
--output输出 CSV 路径<root>/results/literature_results.csv
--json-output额外输出完整 JSON无
--min-citations最低引用数0
--min-relevance最低相关性得分0
--min-abstract-length最短摘要长度0
--include-terms / --exclude-terms必含 / 必排关键词空
--title-similarity标题模糊去重阈值0.92
--enrich-abstracts开启摘要富集关闭
--sort-byrelevance / citations / yearrelevance
--email联系邮箱(OpenAlex 礼貌池、NCBI 建议提供)无
--ncbi-api-key / --s2-api-keyAPI Key(环境变量 NCBI_API_KEY / S2_API_KEY 优先)无

Outputs

文件说明
literature_results.csv主结果,UTF-8 BOM,列:title, authors, year, doi, journal, abstract, citations, source, pmid, url, type, oa_status, relevance, query
<name>.json完整记录(含解析出的字段,便于二次处理)
references.bibBibTeX 格式,@article{作者姓+年份+首词+序号} 稳定键
references.risRIS 格式,EndNote / Zotero / Mendeley 可直接导入
references.txtGB/T 7714-2015 顺序编码制 或 中文编号纯文本

Validation

  • 检索覆盖:确认三个源各自返回条数符合预期;某个源为 0 条通常是年份过滤过窄或 API Key 缺失导致限速
  • 去重有效性:去重前后条数差应接近各源之间真实重复量;source 列出现 A+B 说明该文献被多个源命中
  • 摘要完整度:摘要富集后检查 abstract 列空值率;OpenAlex 摘要来自倒排索引重建,若原库无摘要则仍然为空
  • 相关性合理性:抽查 relevance 排序前 20 条,确认主题相关;--min-relevance 阈值建议先设为 0 观察分布再收紧
  • 引用格式:导入 Zotero/EndNote 检查作者名、卷期页码是否被正确解析;GB/T 7714 输出需人工核对卷(期)与页码(部分源不提供)
  • 引用计数口径:citations 各源定义不同(PubMed 为 pmcrefcount,OpenAlex 为 cited_by_count),跨源比较时只作相对参考

References

  • references/methodology.md —— 检索策略设计、各源 API 参数、相关性评分与去重算法原理
  • references/troubleshooting.md —— 常见报错(限速、空结果、编码、重复条目)与排错步骤

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Literature Search AI skill do?

This skill should be used when mining academic literature from PubMed, OpenAlex or Semantic Scholar — searching papers by topic or keywords, deduplicating multi-source results, filtering by relevance or citation count, enriching missing abstracts, and exporting RIS, BibTeX or GB/T 7714 citations. 用于多源学术文献检索、去重、相关性筛选、摘要富集与参考文献格式导出的场景。

Why use Literature Search on TypingMind?

Because you install it once and use it with any model. Literature Search is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Literature Search in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ssinder/bioinformatics-agent-skills/tree/main/skills/literature-search. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Literature Search?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Literature Search?

As many as you like. As long as a model supports skills, you can use Literature Search with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Literature Search AI skill free?

Yes. It is published on GitHub by ssinder under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇