$npx skillfedfor your agent

deepxiv

DeepXiv enables layered exploration of open-access research papers, letting you search by topic or ID and read specific sections without loading entire documents. It supports trending paper discovery, web search, and integrates with Semantic Scholar metadata for citation context.

DeepXiv lets you search and progressively read academic papers section by section.

AI-generated summary based on this skill's SKILL.md

13,939 1,247 MITupdated by wanshuiyin

Decision gist · record as of 2026-07-22

DeepXiv lets you search and progressively read academic papers section by section. DeepXiv enables layered exploration of open-access research papers, letting you search by topic or ID and read specific sections without loading entire documents. It supports trending paper discovery, web search, and integrates with Semantic Scholar metadata for citation context.

manual: git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep → cp -r Auto-claude-code-research-in-sleep/skills/deepxiv ~/.claude/skills/deepxiv
skills/deepxiv/SKILL.md · version c144bc6e

Use it when

  • Yes.
  • DeepXiv's trending papers discovery lets you find popular open-access research by topic or time window—such as papers trending in the last.

Verify before relying

Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.

Same gist for agents: .md · .json

Install

wanshuiyin/Auto-claude-code-research-in-sleep/deepxiv · repository language: Python

Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

How do I search arxiv papers on machine learning with DeepXiv?

DeepXiv lets you search arxiv papers by topic—enter your query like 'machine learning' and browse results with metadata and summaries. You can filter by time window to find recent papers, then open specific papers by ID to read progressively without loading the full document at once.

Can I read a specific section of a research paper instead of the full text?

Yes. DeepXiv supports section-level access, so you can retrieve just the introduction, methods, results, or conclusion from a paper. This saves tokens and time by letting you read only the parts you need rather than loading the entire document.

What does DeepXiv's trending papers feature show?

DeepXiv's trending papers discovery lets you find popular open-access research by topic or time window—such as papers trending in the last 2 weeks or this month. Results include metadata and brief summaries so you can quickly assess relevance before diving deeper.

How does DeepXiv retrieve paper metadata and summaries?

DeepXiv pulls paper metadata and brief summaries without requiring full-text loads, often integrating with Semantic Scholar for citation context. This lightweight approach lets you look up arxiv IDs, get abstracts and section listings, and decide which papers to read in detail.

Can DeepXiv search for papers by author name?

Yes. DeepXiv supports author-based searches—you can search for papers by researchers like Karpathy. Combined with topic and time-window filters, this helps you locate specific researchers' work within the open-access literature.

What integrations does DeepXiv offer for literature search?

DeepXiv integrates with Semantic Scholar and arxiv for comprehensive literature discovery. This combination enables web search for AI papers, metadata enrichment, and citation tracking alongside arxiv's native search and trending features.

SKILL.md

Rendered from the published skill. Quoted content, verbatim.

DeepXiv Paper Search & Progressive Reading

Search topic or paper ID: $ARGUMENTS

Role & Positioning

DeepXiv is the progressive-reading literature source:

Skill Source Best for
/arxiv arXiv API Batch search, PDF download, metadata
/deepxiv DeepXiv SDK Progressive section-level reading
/semantic-scholar S2 API Published venue metadata, citation counts
/alphaxiv alphaxiv.org Instant LLM-optimized summary of one paper, with LaTeX source fallback

Use DeepXiv when you want to avoid loading full papers too early.

Constants

(truncated - see the full file via the links below)

File tree — 1 file
skills/deepxiv/SKILL.md

Let your AI agent find skills like this

Example. Real query, live index.

You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.

wish › “Search and progressively read academic papers with section-level access”

Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →

Related skills

alphaxiv
by wanshuiyin · wanshuiyin/Auto-claude-code-research-in-sleep

AlphaXiv delivers instant, machine-readable summaries of individual papers from arXiv, optimized for language models. When the overview isn't enough, it cascades to full markdown and LaTeX source inspection for deeper details. Ideal for explaining a specific paper—not for broad literature discovery.

MITupdated Jul 2026
★ 13,939repo stars
research-lit
by wanshuiyin · wanshuiyin/Auto-claude-code-research-in-sleep

research-lit discovers research papers on any topic by searching your personal library, Zotero collections, local PDFs, and academic web sources in one query. It extracts key ideas, pulls annotations, and generates summaries to accelerate literature review work. Configure which sources to prioritize or download papers directly to your collection.

MITupdated Jul 2026
★ 13,939repo stars
wiki-enrich
by wanshuiyin · wanshuiyin/Auto-claude-code-research-in-sleep

wiki-enrich completes scaffolded research papers by fetching content from multiple sources and rewriting 10 fillable TODO sections into concise prose. It preserves protected sections like Connections and Abstract (original), respects the --force flag for selective overwrites, and caps batches at 20 papers per run to manage token budgets.

MITupdated Jul 2026
★ 13,939repo stars
arxiv
by wanshuiyin · wanshuiyin/Auto-claude-code-research-in-sleep

arxiv lets you search the arXiv repository by keyword or paper ID, then download full PDFs and view complete metadata including authors, abstract, and publication date. Results display in a sortable table format, and papers can be saved to a local directory for offline access.

MITupdated Jul 2026
★ 13,939repo stars
exa-search
by wanshuiyin · wanshuiyin/Auto-claude-code-research-in-sleep

Exa Search performs broad web searches across blogs, news, research papers, and company sites with automatic content extraction. Query results return highlights, summaries, or full text alongside metadata like publication dates and authors. Use it when you need web-wide coverage beyond academic databases.

MITupdated Jul 2026
★ 13,939repo stars
research-wiki
by wanshuiyin · wanshuiyin/Auto-claude-code-research-in-sleep

Research Wiki maintains a structured, project-level knowledge base that grows smarter as you add papers, test ideas, run experiments, and capture findings. Every entry connects through typed relationships—papers extend or contradict each other, ideas get tested by experiments, claims gain proof status—so your research compounds rather than scatters. Initialize once, keep it current, query it to avoid re-deriving insights.

MITupdated Jul 2026
★ 13,939repo stars

More skills openalex (MIT) · study (MIT)

Tags
section-level-readingprogressive-accessarxiv-integrationtoken-efficientlayered-retrievalacademic-searchopen-access-papersmetadata-focusedtrending-contentlightweight-reading