Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/deep-literature-search
Multi-source exhaustive literature search across academic databases
Passed 19 of 23 test cases with the skill, and 17 of 23 without it.
2 fixed17 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am writing the literature review section for my doctoral dissertation on using large language models to automatically detect software vulnerabilities in C/C++ codebases. I need a methodical search plan that leaves no major papers behind across computer science and engineering repositories. Please provide a structured strategy that breaks my topic into target concepts with alternate keywords, converts these into exact search queries tailored for tech-focused and general academic engines, outlines grey literature tracking, and provides a clear workflow for deduplicating and screening collected records.
| Checked | Without skill | With skill |
|---|---|---|
| The response defines the research question using an explicit research question framework such as SPIDER, PEO, or PICO. | Missed | Passed |
| The response includes a PRISMA 2020 flow diagram template. | Missed | Passed |
| The search strings use OR logic within concept groups and AND logic between distinct concept groups. | Passed | Passed |
The instructions your model reads when the skill loads.
A deep literature search goes beyond a quick Google Scholar query. It is a methodical, multi-source search process designed to identify all relevant publications on a topic with minimal omissions. This level of thoroughness is required for systematic reviews, meta-analyses, grant applications, and dissertation literature reviews where comprehensiveness is not optional—it is a methodological requirement.
This skill provides a structured framework for planning, executing, and documenting exhaustive literature searches across multiple academic databases. It covers query formulation using controlled vocabularies, database selection strategy, deduplication, screening workflows, and PRISMA-compliant documentation of the search process.
The framework is database-agnostic and can be applied across disciplines, from biomedical sciences (PubMed, Cochrane) to social sciences (PsycINFO, ERIC), engineering (IEEE Xplore, Compendex), and multidisciplinary databases (Web of Science, Scopus, OpenAlex).
Use the PICO/PEO/SPIDER framework appropriate to your field:
Example: "What is the effect of mindfulness-based interventions (I) on academic stress (O) in graduate students (P) compared to no intervention (C)?"
Break your research question into 2-4 key concepts. For each concept, list all synonyms, related terms, abbreviations, and controlled vocabulary terms:
| Concept | Synonyms and Related Terms |
|---|---|
| Mindfulness | mindfulness-based stress reduction, MBSR, meditation, mindful awareness |
| Academic stress | study stress, exam anxiety, academic burnout, student distress |
| Graduate students | postgraduate, doctoral students, PhD candidates, master's students |
Combine concepts using Boolean logic:
("mindfulness" OR "MBSR" OR "mindfulness-based stress reduction" OR "meditation")
AND
("academic stress" OR "study stress" OR "exam anxiety" OR "academic burnout")
test cases passed, vs 17 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.