agentsclimarketplace

Paper search

Skill lucaswychan/quant-paper-agent/.agents/skills/paper-search

A Claude Code plugin that turns a quantitative-finance arxiv paper into a production-ready event-driven strategy

Install
npx -y skills add lucaswychan/quant-paper-agent --skill paper-search

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Search arXiv quantitative-finance categories, resolve exact paper versions, and download reproducible PDF source bundles. Use for q-fin paper discovery, date/category/keyword searches, arXiv IDs or URLs, reading queues, and batch downloads that must preserve source provenance for later extraction or replication.

SKILL.md

2.1 KB, as published. Nobody here has run it

Paper search

Create an exact, auditable source bundle. Do not extract or summarize the PDF in this stage.

Workflow

  1. Resolve the workspace root. All examples assume commands run from that root.
  2. Search with scripts/search_arxiv.py. Review the returned records before downloading broad searches.
  3. Download selected records with scripts/download_paper.py.
  4. Confirm that every paper directory contains a valid PDF, metadata, and a checksum manifest.
python3 scripts/search_arxiv.py --query "cross-sectional momentum" \
  --category q-fin.PM --since 2024-10-01 --max 10

python3 scripts/download_paper.py 2403.12345v2 --root papers

Search results include arxiv_id, versioned_id, version, published, updated, categories, authors, abstract, and exact PDF URL. Date searches paginate until the requested range is covered; they must not filter only a small latest-results window.

Artifact contract

papers/<versioned-id>/
├── paper.pdf
├── meta.json
└── source_manifest.json

source_manifest.json records the exact versioned ID, URL, SHA-256, byte count, download time, and HTTP content type. An unversioned request resolves to the latest arXiv version and records that version explicitly.

Rules

  • Use HTTPS.
  • Preserve exact arXiv versions; never silently collapse v2 into the unversioned ID.
  • Validate IDs and dates before requesting them.
  • Download atomically and reject non-PDF responses.
  • Reuse a cached PDF only when its checksum agrees with its manifest.
  • Respect arXiv throttling and identify the client through the configured user agent.
  • Surface empty searches and network errors; never invent papers or widen scope silently.
  • Do not parse PDFs here. paper-extract owns content inspection.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.