arxiv2md
Convert arXiv papers to clean Markdown. Use when the user wants to read, fetch, or summarize an arXiv paper.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 3
- Forks
- 0
01 前言 Front Matter
- name
- arxiv2md
- description
- Convert arXiv papers to clean Markdown. Use when the user wants to read, fetch, or summarize an arXiv paper.
03 SKILL.md 正文
arxiv2md
Convert arXiv papers to LLM-ready Markdown. Parses arXiv's native HTML (not PDFs) for clean output with proper math, tables, and section structure.
REST API (preferred for agents)
Base URL: https://arxiv2md.org
No auth, no key, no SDK. Rate limit: 30 requests/minute per IP. Results are cached server-side for 24h.
Don't just swap the hostname. Visiting
https://arxiv2md.org/abs/2501.11120(replacingarxiv.org→arxiv2md.org) returns the HTML web app for humans, not Markdown. For programmatic use always call/api/markdownor/api/jsonbelow.
Get markdown
curl "https://arxiv2md.org/api/markdown?url=2501.11120"
Returns raw markdown as plain text.
Get JSON (with metadata)
curl "https://arxiv2md.org/api/json?url=2501.11120"
Returns { "arxiv_id", "title", "source_url", "content" }.
Parameters
All optional query params for both endpoints:
| Param | Default | Description |
|---|---|---|
url |
required | arXiv URL or ID (e.g. 2501.11120v1 or https://arxiv.org/abs/2501.11120) |
remove_refs |
true |
Remove references section |
remove_toc |
true |
Remove table of contents |
remove_citations |
true |
Remove inline citations |
frontmatter |
false |
Prepend YAML metadata (/api/markdown only) |
Examples
# Plain markdown for a paper
curl "https://arxiv2md.org/api/markdown?url=2501.11120"
# Keep references and citations intact
curl "https://arxiv2md.org/api/markdown?url=2501.11120&remove_refs=false&remove_citations=false"
# JSON with metadata
curl "https://arxiv2md.org/api/json?url=https://arxiv.org/abs/2501.11120v1"
# With frontmatter (title, authors, date as YAML header)
curl "https://arxiv2md.org/api/markdown?url=2501.11120&frontmatter=true"
CLI
pip install arxiv2markdown
# Output to file
arxiv2md 2501.11120v1 -o paper.md
# Output to stdout
arxiv2md 2501.11120v1 -o -
# Only specific sections
arxiv2md 2501.11120v1 --section-filter-mode include --sections "Abstract,Introduction" -o -
# Strip refs and TOC
arxiv2md 2501.11120v1 --remove-refs --remove-toc -o -
# With YAML frontmatter
arxiv2md 2501.11120v1 --frontmatter -o paper.md
Section filtering (--section-filter-mode + --sections) is available in the CLI and
Python library, not the REST API.
Python library
Import name is arxiv2md:
from arxiv2md import ingest_paper_sync
result = ingest_paper_sync("2501.11120v1")
print(result.content)
# Async variant
from arxiv2md import ingest_paper
result = await ingest_paper("2501.11120v1")
Optional kwargs (same for both): remove_refs, remove_toc, remove_inline_citations
(all True), section_filter_mode ("exclude"), sections (None = all),
include_frontmatter (False).
The REST API names the citation flag
remove_citations; the CLI and Python library name itremove_inline_citations. Same behavior.
Links
- Web app: https://arxiv2md.org
- Machine-readable guide: https://arxiv2md.org/llms.txt
- Source: https://github.com/timf34/arxiv2md
- PyPI: https://pypi.org/project/arxiv2markdown/
04 同仓库更多 Skills
workflow-skill-creator
Distills a completed user workflow or interaction into a reusable agent skill. Use when the user asks to turn their workflow, interaction, or multi-step process into a skill, or when they say "make this a skill", "create a skill from what we just did", "package this workflow" or similar. Do not use for creating skills from scratch without an existing workflow (use a generic skill-creator for that).
uv
Checks whether the uv Python package manager is installed and installs it if missing. Ensures uv is on PATH. Use when another skill requires uv as a prerequisite.
uniprot-database
Access protein metadata, function, taxonomy, and sequences across UniProtKB, UniParc, and UniRef. Use when searching for proteins, mapping identifiers, or retrieving functional annotations and publications. Don't use for sequence alignment, protein folding, or sequence similarity search (use specialized skills for those tasks).
unibind-database
Queries the UniBind database for experimentally validated transcription factor (TF) binding sites. Use when retrieving direct TF-DNA interaction datasets, downloading binding site coordinates (BED/FASTA) for local analysis, or listing available datasets by species, cell line, or TF name. Don't use to query specific intervals, locations, genes, motif models or expression data.
ucsc-conservation-and-tfbs
Fetch Evolutionary Conservation scores (phyloP, phastCons) and Transcription Factor Binding Sites (TFBS) from the UCSC Genome Browser. Use when analyzing whether genomic variants or regions are evolutionarily conserved, functionally important, or bounded by TF regulators across major projects (ENCODE, JASPAR, ReMap).
string-database
Query the STRING database for protein-protein interactions (PPIs), functional enrichment, and homology. Use when the user asks about interactions between specific proteins, interaction evidence, confidence scores, protein interaction partners, or pathway enrichments.