Research Sleuth
v1.1.0SkillLocalFreeResearch Sleuth: Deterministically extract structured fields from a research source: source_type=literature parses a re…
Deterministically extract structured fields from a research source: source_type=literature parses a reference list into bibliographic fields (authors/year/title/venue/DOI/pages); source_type=paper parses paper text into IMRaD sections, in-text citations, and figure/table references. Byte-stable; no LLM. (Action Co-pilot: generates next-best-actions (actions.json), follow-up tasks and calendar reminders on top of the analysis — what to act on today.)
Last updated 2026-10-07
Tags
How to Use
Want to run it now? Execute locally in Nexus Runner — your data stays on your machine.
Run it in Nexus RunnerRelated Skills
Paper Review
Review academic for research scenarios and output a structured, reviewable result with actionable recommendations. Prompt-class skill; results require human review.
Paper Scaffold
Generate structured academic paper outlines with section templates based on input research notes or draft content. Supports multiple citation styles and journal formats.
Lit Review Sage
Generate structured literature review from academic papers or reference lists. Supports multiple citation styles and research themes, producing publishable review sections.
Document Sleuth
Extract document for office scenarios and output a structured, reviewable result with actionable recommendations. Prompt-class skill; results require human review. (Action Co-pilot: generates next-best-actions (actions.json), follow-up tasks and calendar reminders on top of the analysis — what to act on today.)
Calendar Tracker
Extract calendar for office scenarios and output a structured, reviewable result with actionable recommendations. Prompt-class skill; results require human review. (Action Co-pilot: generates next-best-actions (actions.json), follow-up tasks and calendar reminders on top of the analysis — what to act on today.)
Research Lens
Deterministic multi-stage research-material analyzer: auto-detects analyzable facets then runs an additive pipeline (S1 IMRaD structure + readability, S2 bibliometrics from references/in-text citations with optional MCP real-citation enrichment, S3 topic concepts + co-occurrence, S4 synthesis). material_type is an optional focus hint, not a 1-of-N switch. Byte-stable offline. (Action Co-pilot: generates next-best-actions (actions.json), follow-up tasks and calendar reminders on top of the analysis — what to act on today.)