Agent skill

Search

by ZimoLiao in ZimoLiao/scholaraio

A skill your agent uses when the user wants to find academic papers, search the local library, run keyword or semantic search, search by author, explore topics, or federate across library, explore…

MITAuto-check passedResearch & Science

Install Search

skills CLI
$ npx skills add ZimoLiao/scholaraio --skill search -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ZimoLiao/scholaraio search --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ZimoLiao/scholaraio.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/search .claude/skills/search && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
search
GitHub stars
577
Token cost
~1.2k tokens
SKILL.md length
292 words
Files
1
Skills in repo
43
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user wants to find academic papers, search the local library, run keyword or semantic search, search by author, explore topics, or federate across library, explore…

  • Works in 3 steps: 解析用户输入,判断搜索模式 → 从用户输入中提取 → 执行搜索命令
  • The user wants to find academic papers
  • SKILL.md covers 执行逻辑 and 示例
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Search is an agent skill from ZimoLiao/scholaraio. Use when the user wants to find academic papers, search the local library, run keyword or semantic search, search by author, explore topics, or federate across library, explore databases, and arXiv.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science, covering Academic paper search. It works with arXiv. The repository describes itself as: Scholar All-In-One: A research infrastructure for AI agents. The licence is MIT.

When your agent uses it

  • The user wants to find academic papers
  • Search the local library
  • Semantic search
  • Search by author

Example prompts

  • “/search”

Requirements

  • Python 3

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. 解析用户输入,判断搜索模式
  2. 从用户输入中提取
  3. 执行搜索命令

What it can do on your machine

Read from SKILL.md and the folder at commit 777628b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Search loads about 1.2k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 292 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ZimoLiao/scholaraio at commit 777628b, republished under its MIT licence (© ZimoLiao). 292 words, ~1,187 tokens.

Download SKILL.mdSave it as .claude/skills/search/SKILL.md (or your agent's skills folder).
name
search
description
Use when the user wants to find academic papers, search the local library, run keyword or semantic search, search by author, explore topics, or federate across library, explore databases, and arXiv.

文献搜索

在本地论文库中搜索文献。默认使用融合检索(关键词 + 语义向量合并排序),也支持单独使用某一种模式。

执行逻辑

  1. 解析用户输入,判断搜索模式:

    • 如果用户明确要求"语义搜索"、"向量搜索"或"vsearch",使用 vsearch
    • 如果用户明确要求"关键词搜索"、"全文搜索"或"FTS",使用 search
    • 如果用户明确要找“证据片段”、“原文片段”、“行号定位”、“在哪一节/哪几行提到”,使用 search --chunk;若 chunk 索引尚未建立,先运行 index --chunks
    • 如果用户明确按作者搜索(如"找某某的论文"、"某某发表的"),使用 search-author
    • 如果用户要求按引用量排序(如"引用最高的"、"最经典的"、"top cited"),转交 /citations skill
    • 默认使用 usearch(融合检索)——同时执行 FTS5 关键词搜索和 FAISS 语义搜索,合并去重排序。两路都命中的论文排名靠前。向量索引不可用时自动降级为纯关键词。
    • 如果用户要求跨库搜索(如"也搜一下 arXiv"、"在 explore 库里也找找"、"也搜 proceedings"、"全部来源"、"联邦搜索"),使用 fsearch
  2. 从用户输入中提取:

    • 查询词:用户想搜索的内容
    • 返回数量:使用规范参数 --limit N;未指定则使用默认值
    • 年份过滤:--year 2023(单年)、--year 2020-2024(范围)、--year 2020-(起始年至今)
    • 期刊过滤:--journal "Fluid Mechanics"(模糊匹配)
    • 类型过滤:--type review(模糊匹配,常见值:review、journal-article、book-chapter)

    查询词拆分原则:不要把“作者 + 年份 + 关键词/题名词”全部拼进同一个 query。这条规则同时适用于 search、vsearch 和 usearch:

    • search 会把整串文本交给 FTS5 MATCH;作者缩写、全名、标点或年份 token 只要和索引不一致,就可能让原本可命中的论文搜不出来。
    • vsearch 通常不会因此空结果,但作者/年份/期刊等限定词会作为噪声进入 query embedding,可能拉低相关论文分数或引入相近但不精确的结果。
    • usearch 同时跑 FTS 和向量;脏 query 可能让 FTS leg 失效,只剩语义命中,结果不再获得 both 加分。
    • 年份必须优先放到 --year,不要放进 query。
    • 明确按作者找时用 search-author "<作者姓或姓名>",不要把作者混进主题 query。
    • 已知题名或主题时,query 保持为最稳定的题名/主题关键词;需要作者/年份约束时分步过滤或二次确认。
    • 如果第一次无结果,先去掉作者缩写、年份、机构、期刊等限定词,只保留题名核心词或主题词再搜。
  3. 执行搜索命令:

融合检索(默认):

bash
scholaraio usearch "<查询词>" --limit <N> [--year <Y>] [--journal <J>] [--type <T>]

关键词搜索:

bash
scholaraio search "<查询词>" --limit <N> [--year <Y>] [--journal <J>] [--type <T>]

证据片段搜索(返回 paper、section、line range、snippet):

bash
scholaraio search --chunk "<查询词>" --limit <N> [--year <Y>] [--journal <J>] [--type <T>]

语义搜索:

bash
scholaraio vsearch "<查询词>" --limit <N> [--year <Y>] [--journal <J>] [--type <T>]

作者搜索:

bash
scholaraio search-author "<作者名>" --limit <N> [--year <Y>] [--journal <J>] [--type <T>]

引用量排序:使用 /citations skill 中的 scholaraio top-cited 命令。

联邦搜索(跨库 + arXiv):

bash
# 同时搜主库和 arXiv
scholaraio fsearch "<查询词>" --scope main,arxiv --limit <N>

# 同时搜主库和 proceedings
scholaraio fsearch "<查询词>" --scope main,proceedings

# 同时搜主库和所有 explore 库
scholaraio fsearch "<查询词>" --scope main,explore:*

# 搜指定 explore 库
scholaraio fsearch "<查询词>" --scope explore:my-survey

# 仅搜 arXiv(在线查询,不需要本地数据)
scholaraio fsearch "<查询词>" --scope arxiv

# 全部来源
scholaraio fsearch "<查询词>" --scope main,proceedings,explore:*,arxiv

--scope 支持逗号分隔组合:main(主库融合搜索)、proceedings(论文集子论文)、explore:<名称> 或 explore:*(explore 库)、arxiv(在线 arXiv API)。默认 scope 为 main。arXiv 结果会标注 [已入库] 表示该论文已在本地库中。

  1. 将搜索结果整理后呈现给用户。融合检索结果中每项标注了匹配来源:

    • both:关键词和语义都命中(最相关)
    • fts:仅关键词命中
    • vec:仅语义命中
  2. 复杂查询:当 CLI 参数组合无法满足需求时(如按一作姓氏首字母筛选、多条件交叉、自定义排序等),直接写 Python 读 configured papers library 下的 */meta.json 做查询。JSON 关键字段:

title, authors, first_author, first_author_lastname, year, doi, journal,
abstract, paper_type, citation_count (dict: crossref/semantic_scholar/openalex),
ids, toc, l3_conclusion

示例

用户说:"帮我搜一下 turbulent boundary layer 相关的论文" → 执行 usearch "turbulent boundary layer"

用户说:"用语义搜索找 drag reduction 的文献,给我前5篇" → 执行 vsearch "drag reduction" --limit 5

用户说:"找 Liao Z-M 的论文" → 执行 search-author "Liao"

用户说:"我库里引用最高的论文有哪些" → 转交 /citations skill(使用 top-cited 命令)

用户说:"2020年以后关于 drag reduction 的论文" → 执行 usearch "drag reduction" --year 2020-

用户说:"找 subgrid scale model 的原文证据片段,最好有行号" → 若未建 chunk 索引先执行 index --chunks,再执行 search --chunk "subgrid scale model"

用户说:"找 Moin 1982 numerical investigation turbulent channel flow" → 执行 usearch "numerical investigation turbulent channel flow" --year 1982;必要时再用 search-author "Moin" --year 1982 交叉确认,不要执行 search "P Moin 1982 numerical investigation turbulent channel flow"

用户说:"JFM 上发的湍流论文" → 执行 usearch "turbulence" --journal "Fluid Mechanics"

用户说:"库里引用最高的 review 文章" → 转交 /citations skill(使用 top-cited --type review 命令)

用户说:"帮我在 arXiv 上也搜一下 physics-informed neural network" → 执行 fsearch "physics-informed neural network" --scope main,arxiv

用户说:"所有来源都搜一下 drag reduction,包括 explore 库" → 执行 fsearch "drag reduction" --scope main,proceedings,explore:*,arxiv

用户说:"在我之前建的 wall-bounded-turbulence explore 库里搜 channel flow" → 执行 fsearch "channel flow" --scope explore:wall-bounded-turbulence

用户说:"连 proceedings 一起搜 granular damping" → 执行 fsearch "granular damping" --scope main,proceedings

© ZimoLiao, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/search of ZimoLiao/scholaraio.

Open the folder on GitHubat commit 777628b

Compare with similar skills

Search next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Search compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Search this skillZimoLiao/scholaraio577—~1.2kAutomated safety check: PassMIT
Read arXiv Paperkarpathy/nanochat59k1 repos~494Automated safety check: PassMIT
Literature Reviewneflibata-feng/MyArxiv-Agent12620 repos~5.9kAutomated safety check: NotesMIT
Openalex Databaseneflibata-feng/MyArxiv-Agent12612 repos~3kAutomated safety check: PassCustom licence
Citation ManagementK-Dense-AI/claude-scientific-writer2.4k2 repos~3.9kAutomated safety check: NotesMIT
Citation Managementneflibata-feng/MyArxiv-Agent12619 repos~8.1kAutomated safety check: NotesMIT

Similar skills

  • Read arXiv Paper

    karpathy/nanochat

    Fetches the TeX source of an arXiv paper from its URL, reads it and writes a markdown summary tied to the nanochat project.

    59k GitHub starsUsed in 1 repo~494 tokens
    Research & ScienceAuto-check passed
  • Literature Review

    neflibata-feng/MyArxiv-Agent

    Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.).

    126 GitHub starsUsed in 20 repos~5.9k tokens
    Research & ScienceAuto-check: notes
  • Openalex Database

    neflibata-feng/MyArxiv-Agent

    Query and analyze scholarly literature using the OpenAlex database.

    126 GitHub starsUsed in 12 repos~3k tokens
    Research & ScienceAuto-check passed
  • Citation Management

    K-Dense-AI/claude-scientific-writer

    Finds papers in OpenAlex, PubMed and Google Scholar, turns DOIs, PMIDs and arXiv IDs into clean BibTeX, and validates citations for a manuscript or thesis.

    2.4k GitHub starsUsed in 2 repos~3.9k tokens
    Research & ScienceAuto-check: notes
  • Citation Management

    neflibata-feng/MyArxiv-Agent

    Comprehensive citation management for academic research. An agent skill from neflibata-feng/MyArxiv-Agent.

    126 GitHub starsUsed in 19 repos~8.1k tokens
    Research & ScienceAuto-check: notes
  • Searches arXiv across many papers on one topic, extracts each paper's methodology and findings in parallel, and synthesizes a cited literature review.

    84k GitHub starsUsed in 2 repos~4.3k tokens
    Research & ScienceAuto-check passed

More from ZimoLiao/scholaraio

All 43 skills in this repo
  • Document

    ZimoLiao/scholaraio

    A skill your agent uses when the user wants to create or inspect DOCX, PPTX, or XLSX files, generate a downloadable Office deliverable, or verify its structure and layout warnings with scholaraio…

    577 GitHub stars~674 tokensUpdated 15 days ago
    Auto-check passed
  • Academic Writing

    ZimoLiao/scholaraio

    A skill your agent uses when the user needs help choosing or organizing an academic-writing workflow by deliverable, stage, or format, including review articles, guided reading, paper sections, PPT…

    577 GitHub stars~827 tokensUpdated 15 days ago
    Auto-check passed
  • Arxiv

    ZimoLiao/scholaraio

    A skill your agent uses when the user wants to browse arXiv preprints, search arXiv directly, fetch a PDF by arXiv ID or URL, or send a preprint into the ScholarAIO ingest pipeline.

    577 GitHub stars~799 tokensUpdated 15 days ago
    Auto-check passed
  • Bioinformatics

    ZimoLiao/scholaraio

    A skill your agent uses when working on bioinformatics workflows such as alignment, variant calling, phylogenetics, or protein-structure analysis, especially across BLAST, minimap2, samtools…

    577 GitHub stars~1.4k tokensUpdated 15 days ago
    Auto-check passed
  • Citation Check

    ZimoLiao/scholaraio

    A skill your agent uses when the user wants to verify citations in AI-generated or human-written text against the local knowledge base and catch hallucinated, wrong, or missing references.

    577 GitHub stars~454 tokensUpdated 15 days ago
    Auto-check passed
  • Draw

    ZimoLiao/scholaraio

    A skill your agent uses when the user wants diagrams, flowcharts, architecture visuals, data relationships, timelines, concept maps, Mermaid, Graphviz, drawio, or polished paper figures generated…

    577 GitHub stars~1.3k tokensUpdated 15 days ago
    Auto-check: notes

Works with

Questions about Search

What does Search do?

A skill your agent uses when the user wants to find academic papers, search the local library, run keyword or semantic search, search by author, explore topics, or federate across library, explore…. Search is an agent skill from ZimoLiao/scholaraio. Use when the user wants to find academic papers, search the local library, run keyword or semantic search, search by author, explore topics, or federate across library, explore databases, and arXiv.

When should I use Search?

Search fits situations like: the user wants to find academic papers; search the local library; semantic search; search by author.

How do I install Search in Claude Code?

Run `npx skills add ZimoLiao/scholaraio --skill search -a claude-code`. Or copy the skill folder (.claude/skills/search in ZimoLiao/scholaraio) into .claude/skills/search in your project. Claude Code loads it when a task matches its description.

How do I install Search in Codex?

Run `npx skills add ZimoLiao/scholaraio --skill search -a codex`. Or copy the skill folder (.claude/skills/search in ZimoLiao/scholaraio) into .agents/skills/search in your project. Codex loads it when a task matches its description.

Can I use Search in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ZimoLiao/scholaraio --skill search -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/search, .gemini/skills/search, .github/skills/search and .opencode/skills/search in your project.

What does Search need to run?

SKILL.md names no scripts, command-line tools or credentials: Search is instructions for the agent only. Our summary lists: Python 3.

Does Search access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Search safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Search use?

Search is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Search use?

About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Search?

Skills that share tags, products or a category with Search: Read arXiv Paper (karpathy/nanochat, 59k stars), Literature Review (neflibata-feng/MyArxiv-Agent, 126 stars), Openalex Database (neflibata-feng/MyArxiv-Agent, 126 stars) and Citation Management (K-Dense-AI/claude-scientific-writer, 2.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Search?

ZimoLiao (a GitHub user) maintains it in ZimoLiao/scholaraio, which has 577 GitHub stars. The repository holds 43 skills in this directory. The repository was last updated on September 25, 2026.

Source: ZimoLiao/scholaraio on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.