research-lookup
Compile current scholarly evidence for a scientific manuscript or research brief. Use when the user explicitly asks to gather literature, references, background evidence, competing findings, or a manuscript research packet. Uses Parallel Search by default, Parallel Extract for source verification, Parallel Research for explicitly deep/exhaustive work, optional explicit Parallel Chat, and optional Perplexity only when requested or allowed as a failure fallback.
Author
Category
Content CreationInstall
Hot:19
Download and extract to your skills directory
Copy command and send to AI Agent for auto-install:
Download and install this skill https://openskills.cc/api/download?slug=k-dense-ai-skills-research-lookup&locale=en&source=copy
Research Lookup - Academic Literature Search and Research Evidence Collection
Skill Overview
Research Lookup is an academic literature search skill designed for preparing scientific manuscripts. It can automatically collect and verify 60 high-quality references, generating a manuscript-ready research package.
Use Cases
1. Scientific Paper Writing
When you are writing a scientific paper, research report, or academic review, Research Lookup can help you quickly gather relevant literature, validate research methods, and find evidence that supports or refutes your arguments.
2. Systematic Evidence Compilation
When you need to collect comprehensive academic evidence for a specific research question—including peer-reviewed studies, systematic reviews, meta-analyses, methodological validation, and evidence with limitations—this skill can provide a structured evidence matrix.
3. Research Background Survey
When you need to understand the current state of research in a field, methodological precedents, mechanism explanations, or research gaps, Research Lookup can provide a validated literature foundation and consensus findings.
Core Features
1. Multi-Channel Academic Literature Search
Based on the multi-round search strategy of Parallel Search, it automatically covers major academic databases such as PubMed/PMC, Europe PMC, Crossref, OpenAlex, Semantic Scholar, and arXiv/bioRxiv/medRxiv, as well as authoritative journals and institutional sources. By default, it generates 60 verified unique references.
2. Literature Evidence Verification and Extraction
Using Parallel Extract for deep validation of search results, it extracts structured information such as authors, year, journal, DOI, PMID, study design, sample size, methods, interventions, outcomes, quantitative findings, limitations, and conclusions, generating an auditable evidence matrix.
3. Manuscript Research Package Generation
Automatically generates a complete paper research package, including both machine-readable and human-readable data packages, citation-ready references, an evidence matrix, statement-to-source mapping, integrated analysis, chapter briefs, and a coverage report—directly usable in the Introduction, Methods rationale, and Discussion sections.
FAQ
What kinds of research needs is research-lookup suitable for?
Research Lookup is specifically designed for scientific manuscripts that require a large number of high-quality academic references. It is best suited when you need to systematically collect literature evidence, validate research methods, find supporting or refuting evidence, and understand the state of research. It is not suited for simple factual question lookups or situations that require access to unpublished materials.
Can this skill guarantee finding 60 references?
The goal of the skill is 60 verified and unique references, not any arbitrary set of 60 links. It de-duplicates using DOI, PMID, standardized URLs, and standardized titles, excludes retracted literature, clearly flags preprints, and prioritizes sources that are directly relevant and use an appropriate study design. If the search results are insufficient, it will report the gaps accurately rather than lowering quality to fill the number.
What literature sources does Research Lookup support?
By default, it uses the multi-channel academic strategy of Parallel Search, prioritizing coverage of PubMed/PMC, Europe PMC, Crossref, OpenAlex, Semantic Scholar, preprint servers (arXiv/bioRxiv/medRxiv), major journals, and authoritative institutional sources. Domain filtering is not treated as exhaustive, and additional unrestricted supplemental searches are performed to reduce blind spots. For clearly deep research needs, Parallel Research is supported; for scenarios requiring an OpenAI-compatible interface, Parallel Chat is supported.