These skills help an agent with academic research workflows. Most come from a Nature-style skills collection, which covers reading, writing and reviewing papers.
19 skills
Create publication-style Matplotlib charts with an AI agent, using scientific plotting conventions, reference scripts and print or vector export guidance.
Frame social-science research questions, literature maps, evidence routes and defensible claims, then review novelty and feasibility.
Prepare Data and Code Availability statements, repository plans, dataset citations and FAIR metadata checks.
Develop or audit research proposals and plans through evidence, argument and section contracts before drafting.
Review scientific documents for claims, methods, evidence, citations and presentation.
Run Codex-oriented research, literature review, manuscript revision, study screening and experiment-planning workflows.
Prepare point-by-point reviewer responses, revision cover letters, marked manuscripts and consistent revision packages.
Turn scientific papers or reading notes into Chinese PPTX research presentations with source figures and speaker notes.
Retrieve academic full text through open-access, publisher API and authorized institutional or browser access.
Draft manuscript sections and initial-submission materials from supplied evidence, or restructure a scientific argument.
Audit statistical reporting across methods, results and figure legends, including replication, uncertainty and multiple comparisons.
Search literature across sources, manage references, verify citations and audit citation impact with explicit evidence.
Choose research skills for question framing, literature search, paper analysis, citation checks and study screening, with clear scope and traceable evidence.
Use reader and paper-card skills to digest literature, proposal skills to plan studies, and figure skills for publication graphics.