literature-search

The literature-search skill queries academic databases including Semantic Scholar, arXiv, OpenAlex, and CrossRef to retrieve research papers. It provides tools to merge results, deduplicate entries, generate BibTeX files, and download arXiv source files.

1.6K
Installs
5
Use cases
4/10
Quality

Is literature-search safe to install?

Review the source first

Review the source first: our audit of literature-search's source files found 7 shell commands, 0 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes local Python scripts and reads sensitive information from /Users/lingzhi/Code/keys.md to authenticate with the Semantic Scholar API.

How we audit skills: our security review methodology.

Who is this skill for?

Researchers and developers who need to find academic papers, verify related work, or compile bibliographies.

What can you do with it?

  • Finding academic papers based on natural language queries
  • Building bibliographies in BibTeX format
  • Retrieving recent preprints from arXiv
  • Merging and deduplicating search results from multiple academic databases
  • Downloading LaTeX source files for specific arXiv papers

How good is this skill?

Quality score: 4/10. The skill provides clear instructions and modular scripts. It relies on a hardcoded local file path for API keys, which limits portability.

What does the skill file contain?

SKILL.md
# Literature Search

Search multiple academic databases to find relevant papers.

## Input

- `$ARGUMENTS` — The search query (natural language)

## Scripts

### Semantic Scholar (primary — best for ML/AI, has BibTeX)
```bash
python ~/.claude/skills/deep-research/scripts/search_semantic_scholar.py \
  --query "QUERY" --max-results 20 --year-range 2022-2026 \
  --api-key "$(grep S2_API_Key /Users/lingzhi/Code/keys.md 2>/dev/null | cut -d: -f2 | tr -d ' ')" \
  -o results_s2.jsonl
```

Key flags: `--peer-reviewed-only`, `--top-conferences`, `--min-citations N`, `--venue NeurIPS ICML`

### arXiv ...

Frequently asked questions

Does this skill require an API key?

The Semantic Scholar search requires an API key, which the script attempts to read from /Users/lingzhi/Code/keys.md. Other services like OpenAlex do not require an API key.

What output formats does the skill support?

The skill produces JSONL files for search results and .bib files for bibliographies.

Can the skill download full papers?

The skill downloads .tex source files for arXiv papers using the download_arxiv_source.py script.

Data sourced from lingzhi227/agent-research-skills on GitHub. Install counts from skills.sh. The summary and security audit are derived from the skill's source files: every command and URL listed appears verbatim in the source.

Related skills