dsh-scholar Advanced: From Search to Review Workflow

The worst part of writing a review isn't reading — it's proving you read everything: reviewers ask about your search strategy and recall rate, and you have no quantified answer. Turns out systematic literature reviews can be automated — retrieval windows, quality tiering, and recall metrics all have tools.

Deep Skill Finder community · review author

Reading English papers is slow not because of your English but because close reading is a hundred tiny motions: paragraph-by-paragraph translation, notes, formulas, method-comparison tables. One paper eats an evening; three a week. Once the skills take the small stuff, you only read the machine-prepared parallel drafts.

Deep Skill Finder community · close-reading procrastinator

Hunting potential reviewers and collaborators means digging through scholar homepages and paper acknowledgments — slow and leaky. Collaboration graphs and publication timelines are public data; there's just never been a tool that hands you the answer directly.

Deep Skill Finder community · collaborator-hunter

Lazy path · recommended

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

Whatever "Build a research workflow from literature search to finished review" 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: How do I automate a systematic literature review?

A: Hand the whole chain to tooling — strategy→execution→screening→draft: slr-automation-guide (2,862 installs) provides the SLR automation tools and process; lit-search (838 installs) runs time-windowed retrieval and returns quality-tiered DOI lists, formatted references, and quantified recall metrics — the rigor reviewers demand, backed by numbers. For the heavy analysis, research-lit (13,464 installs) is the most-installed paper-analysis and related-work summarization skill.

Q: How should I close-read English papers?

A: Two layers. Translate first: paper-translator (573 installs) renders English academic PDFs into Chinese with formulas and layout preserved — bilingual, Chinese-only, and a glossary. Then close-read: paper-cn-reader (252 installs) does paragraph-faithful translation with annotations, producing HTML+PDF reading digests with all figures and tables kept. Add literature-mining's (1,828 installs) structured notes and literature matrix to turn 'read' into 'read through.'

Q: How do I identify research gaps?

A: Two routes. Methodology-driven: literature-mining's matrix and gap-identification framework compare each paper's questions, methods, and conclusions side by side — gaps surface on their own. AI-driven: zhiyan-smart-research (233 installs) generates a structured report in one click — summary, literature review, research gaps, innovations, and suggestions — which you then verify by hand.

Q: How do I track and profile scholars?

A: Pick by need: for computer science, dblp-api (2,864 installs) searches publications, authors, and venues directly; cross-domain profiles come from bohrium-scholar-search (509 installs) by name or affiliation; for collaboration graphs and reviewer identification, ai4scholar-author-intelligence (112 installs) compares experts and maps lab networks; and openjobs-ai-talent-search (813 installs) finds talent for collaborations.

Q: Halfway through the review I find missing literature — now what?

A: Backfill with citation-chain retrieval: sn-search-academic (4,716 installs) traces citation chains, expanding from your core papers both backward (references) and forward (citations); cross-check with a topic search like psych-literature-search (519 installs). New entries go into references.bib with cite — review and library stay in sync.

Q: Does this workflow survive advisor-induced deadlines?

A: It thrives on them: retrieval and close reading are machine strengths (minutes), judgment and writing stay human. Outsource 'search thoroughly, read everything, organize' to the skill chain and keep your attention for 'which paper matters and how the argument flows' — the review's ceiling rises precisely because you finally have time to think.