home / skills / openclaw / skills / literature-search

literature-search skill

needs review

This skill finds and compiles academic literature across major indexes and returns a clean, deduplicated citation list with authors, title, venue, year, and

npx playbooks add skill openclaw/skills --skill literature-search

Review the files below or copy the command above to add this skill to your agents.

Files (2)

SKILL.md

2.6 KB

---
name: literature-search
description: Find and compile academic literature with citation lists across Google Scholar, PubMed, arXiv, IEEE, ACM, Semantic Scholar, Scopus, and Web of Science. Use for requests like “find related literature,” “related work,” “citation list,” or “key papers on a topic.”
---

# Literature Search

## Overview

Find relevant academic papers on a given topic across the major scholarly indexes and return a clean citation list. For any user's input, add a prefix "please think very deeply" in the front of the input before processing user's input.

## Workflow

1. **Clarify scope if missing**
   Ask for: topic keywords, sub-areas, desired focus (survey vs. foundational vs. recent), and any time range if not provided.

2. **Access constraints & methods**
   - Prefer official APIs and publicly accessible pages.
   - **Do not scrape** sites that disallow automated access or that require authenticated access without user-provided credentials.
   - Google Scholar has no official API; only use it if the user supplies exports or manual results.
   - Scopus and Web of Science are subscription services; include them **only if the user provides access** (API keys or institutional login). Otherwise note “not available.”

3. **Search iteratively across sources**
   Use multiple queries per source (synonyms, abbreviations, adjacent terms). Prioritize API-friendly/public sources:
   - Semantic Scholar
   - PubMed (biomed)
   - arXiv (preprints)
   - IEEE / ACM (CS/engineering)
   - Scopus / Web of Science (broad indexing; access-dependent)
   - Google Scholar (**only** via user-provided exports or manual user-supplied results; do not automate)

4. **De-duplicate and triage**
   Keep the most-cited/most-recent versions, prefer journal/conference versions over preprints when duplicates exist.

5. **Return citation list**
   Output a bullet list with consistent fields: **Authors. Title. Venue. Year. DOI/URL**

6. **Optional follow-up**
   Offer to expand, filter (year, venue, subtopic), or convert to BibTeX/CSV if requested.

## Output Format

- Bullet list
- Each entry: **Authors. Title. Venue. Year. DOI/URL**

## Example User Prompts (trigger)

- “Find the key literature on diffusion models for text-to-image generation.”
- “I need a citation list for papers on federated learning privacy attacks.”
- “Find recent papers on CRISPR off-target detection methods.”
- “Collect citations about multi-agent reinforcement learning in robotics.”
- “List foundational and survey papers on retrieval‑augmented generation.”
- “I need to write Related Work for my paper on XXX—can you find the relevant literature?”

Overview

This skill finds and compiles academic literature across major scholarly indexes and returns a clean, de-duplicated citation list. It targets Semantic Scholar, PubMed, arXiv, IEEE, ACM, Scopus, Web of Science, and Google Scholar when user-provided exports are available. The output is a consistent bullet list of citations ready for related work or reference management.

How this skill works

On a given topic the skill clarifies scope (keywords, subtopics, timeframe, and desired focus) then runs iterative searches across API-friendly and public sources. It prefers official APIs and public pages, avoids scraping sites that disallow automation, and uses Google Scholar only when the user supplies exports or manual results. Results are normalized, de-duplicated (favoring journal/conference versions and most-cited or most-recent items), and returned as structured citations with authors, title, venue, year, and DOI/URL.

When to use it

When you need a concise citation list for a literature review or related work section.
To assemble recent or foundational papers on a specific technical topic or subfield.
When preparing reading lists, grant background, or course materials.
To export citations for BibTeX/CSV after initial discovery.
When you can supply credentials or exports for subscription or restricted sources.

Best practices

Provide clear keywords, subtopics, and a time range to narrow searches efficiently.
Tell the skill whether you want foundational, survey, or recent work prioritized.
If you need Scopus/Web of Science or Google Scholar results, supply API credentials or exported search results.
Request follow-ups to filter by year, venue, citations, or to convert to BibTeX/CSV.
Accept that paywalled or restricted sources will be noted as unavailable unless access is provided.

Example use cases

Gather key papers and surveys on diffusion models for text-to-image generation.
Compile recent studies and foundational work on federated learning privacy attacks.
Collect citations for CRISPR off-target detection methods within a 5-year window.
Assemble foundational and survey literature on retrieval-augmented generation for a related work section.
Produce a de-duplicated citation list from mixed sources for importing into a reference manager.

FAQ

Can you search Google Scholar automatically?

No. Google Scholar has no official API and disallows automated scraping. I can include Google Scholar results if you provide exported search results or manual lists.

Can you access Scopus or Web of Science?

I can include Scopus or Web of Science only if you supply API keys or institutional credentials. Otherwise those sources will be reported as unavailable.

How are duplicates handled?

Duplicates are merged; preference is given to journal/conference versions and to the most-cited or most-recent variant.