agentsclimarketplace

Citation survey skill

Skill ultimatile/citation-survey-skill

Agent skill to survey citing or referenced papers using the OpenAlex API.

Install
npx -y skills add ultimatile/citation-survey-skill

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

Survey citing or referenced papers for a given seed paper using OpenAlex API. Use when the user asks to find follow-up papers, citing papers, references, or related literature for a specific paper identified by DOI or arXiv ID. Also use when asked to check prior work, search for related publications, or build a literature survey around a specific paper.

SKILL.md

2.9 KB, as published. Nobody here has run it

Citation Survey Skill

Survey citing or referenced papers using the OpenAlex API.

All paths below are relative to this skill's base directory. Construct the full path by prepending the base directory shown at the top of this skill's context.

Usage

Find papers that cite a given work

uv run <base-dir>/scripts/citation_survey.py citing --doi <DOI>
uv run <base-dir>/scripts/citation_survey.py citing --arxiv <ARXIV_ID>

Find references of a given work

uv run <base-dir>/scripts/citation_survey.py refs --doi <DOI>

Filter results by keywords in title/abstract

uv run <base-dir>/scripts/citation_survey.py citing --doi <DOI> --filter "keyword1,keyword2"

Save results to JSON

uv run <base-dir>/scripts/citation_survey.py citing --doi <DOI> --output results.json

Show abstracts

uv run <base-dir>/scripts/citation_survey.py citing --doi <DOI> --verbose

Options

  • direction: citing (papers that cite this work) or refs (references of this work)
  • --doi: DOI of the seed paper
  • --arxiv: arXiv ID of the seed paper (alternative to --doi)
  • --filter: Comma-separated keywords to filter by title/abstract
  • --max-results: Maximum number of results (default: 2000)
  • --output: Save results to JSON file
  • --verbose: Show abstracts in output
  • --api-key: OpenAlex API key (supported, but leaks into shell history/process lists)
  • --api-key-file: Read OpenAlex API key from a file

Examples

Find papers citing Hackl et al. (2020) about Kähler geometry:

uv run <base-dir>/scripts/citation_survey.py citing --doi 10.21468/SciPostPhys.9.4.048 --filter "variational principle,kähler,neural quantum"

Find references of a paper by arXiv ID:

uv run <base-dir>/scripts/citation_survey.py refs --arxiv 2004.01015

API Key

OpenAlex API requires an API key (free account at https://openalex.org/settings/api). Prefer OPENALEX_API_KEY or --api-key-file. --api-key is still supported, but command-line secrets may be visible in shell history or process listings. The script works without a key but with stricter rate limits.

Notes

  • Uses OpenAlex API (free tier available)
  • Rate limiting: 0.15s delay between paginated requests
  • Network, timeout, and HTTP errors are reported as short user-facing messages instead of Python tracebacks
  • Abstract reconstruction from inverted index (OpenAlex format)
  • For arXiv-only papers, DOI resolution may fail; use --arxiv instead

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.