dsh-scholar: Academic Search Inside Your Agent

Before your proposal, you rotate five databases: arXiv with one keyword, Semantic Scholar with a rephrase, Baidu Scholar for another pass. An afternoon gone, 200 titles in a spreadsheet, quality judged by eyeball. What you want is one sentence to the agent — and it queries every source for you.

Deep Skill Finder community · proposal-season grad student

Every literature run is the same: search, screen titles, download PDFs, rename files, drop into Zotero, take notes. Three years of this repetitive motion — until you discover agent skills can take over every step: search skills for retrieval, library skills for management.

Deep Skill Finder community · PhD student

Your advisor drops a new direction: 'see what's recent in this area.' You barely know the field's vocabulary, so your search terms are guesswork — and you never learn about the half of the literature you missed. Saying 'survey the latest progress on X' to an agent that fetches preprints by topic is what you actually wanted.

Deep Skill Finder community · research newcomer

Lazy path · recommended

Install deep-skill-finder once — let your Agent find Skills for you

Whatever "Install a dsh-scholar-style academic search skill into your agent and run your first paper query" task you have, MEYO already has the matching Skills. You don't need to hunt one by one — install deep-skill-finder and your Agent will auto-search MEYO's 50,000+ Skill library on every task, recommending the best match. You just say what you want to do — matching Skills is the Agent's job.

Copy → paste into Claude Code / Codex / Cursor / WorkBuddy / CatPaw · Agent installs automatically:

Please install the deep-skill-finder skill: download the archive from https://www.meyo.life/skill-finder, extract it into your local skill directory and enable it.

Q: What is dsh-scholar?

A: dsh-scholar is the community shorthand for a class of academic-search plugins/skills: install one into your agent, say 'find me papers on X,' and it handles multi-source retrieval, result organization, and downloads. The most direct implementation is scholar-inbox-skill (124 installs) — daily fresh-paper recommendations via Scholar Inbox. For full coverage, paper-search (2,163 installs) searches, downloads, and reads across 20+ sources including arXiv, PubMed, Semantic Scholar, and CrossRef.

Q: How is this different from Google Scholar?

A: Three ways. Cross-source: one command queries arXiv, Semantic Scholar, Baidu Scholar, and more at once (scholar-search, 1,518 installs, is the unified option). Structured: results come back as clean metadata — title, authors, abstract, DOI — not webpage lists, ready for your library. Composable: retrieval chains straight into the next step — translate, summarize, draft the review — one pipeline to the end.

Q: How do I install one?

A: Copy any install command on this page and paste it into Claude Code / Codex / Cursor / WorkBuddy / CatPaw or any skill-capable agent, or one-click install from the community skill page. Then just say 'retrieve papers on topic X' to trigger it.

Q: Does it cover Chinese literature?

A: Yes. baidu-scholar-search-skill-1-1-0 (1,041 installs) retrieves both Chinese and English academic literature — journals, conferences, papers. academic-search-zh (662 installs) does Chinese-first literature locating and search strategy. For the English mainstay, arxiv-search (1,262 installs) queries arXiv metadata directly.

Q: How do search results become a library?

A: Chain the skills: retrieve with paper-search or sn-search-academic (4,716 installs, with citation-chain tracing); file with cite (2,862 installs) — find papers by title, author, or DOI and auto-append BibTeX entries to references.bib; manage with zotero-gpt-guide (2,865 installs) bringing AI assistance into Zotero. Retrieve→cite→manage: that's the full workflow.

Q: Is it free?

A: Community skills are essentially all free under their repo licenses. Retrieval calls public academic-platform APIs and runs inside your own agent — no extra charge.