Install
openclaw skills install academic-deep-searchSearch academic literature and return structured, source-grounded results for questions about methods, markers, findings, or representative figures. Use this skill when the user wants to know what studies in a field usually detect, what results sections commonly report, which methods are typical, or what a representative figure in a topic looks like. For biomedical topics, prefer PubMed and PMC.
openclaw skills install academic-deep-searchUse this skill for requests such as:
The goal is not just to find papers. The goal is to read enough of the right papers to give the user a structured, directly useful answer.
Choose the mode that best matches the user request.
Use when the user asks about:
Organize the answer by experiment type or finding category, not by paper.
Use when the user asks for:
Organize the answer by figure, with source attribution and caption context.
Identify:
If the topic is biomedical, translate the idea into standard English search terms and prefer controlled vocabulary when possible.
If the user specifies a source, that scope is binding.
Examples:
Do not silently broaden the source list.
Use English search terms for database queries, even if the conversation is in Chinese.
For biomedical topics:
Detailed query construction tips are in references/query-guide.md.
Prefer the best database for the topic:
Aim to identify a small set of relevant papers with accessible full text. A few well-read papers are better than many shallow hits.
Before you cite a paper as belonging to a target journal or source, verify it.
Check:
Do not attribute a paper to a journal or database unless you confirmed it.
Abstract-only answers are usually not enough.
Read:
If full text is not available, say that clearly and lower confidence.
Choose 2 to 5 papers that are:
Then synthesize across papers instead of writing a paper-by-paper summary unless the user asked for that.
Use references/query-guide.md for output templates.
When little is found: