draw
Generate diagrams and vector graphics. Supports Mermaid (flowcharts, sequence diagrams, ER diagrams, Gantt charts, mind maps) via mermaid-py, and custom vector graphics (shapes, text, gradients, layers) via cli-anything-inkscape. Outputs PNG/SVG/PDF to workspace/. Use when the user wants to visualize workflows, architecture, data relationships, research timelines, concept maps, or create polished figures for papers.
napkin
Read, create, search, and manage notes in Obsidian vaults using the napkin CLI. Works directly on markdown files and canvas files — no Obsidian app required. Use when the user asks to interact with their Obsidian vault, manage notes, search vault content, work with tasks, tags, properties, daily notes, templates, bases, bookmarks, aliases, or canvas files from the command line.
audit
Audit paper data quality in the knowledge base. Checks for missing fields, filename issues, DOI duplicates, title mismatches, and more. Supports LLM-based deep diagnosis for title mismatches and automated repair. Use when the user wants to check data quality, find problems, or fix metadata issues.
topics
Explore topic distribution in the paper library using BERTopic clustering. Build/rebuild topic models, view topic overview, list papers in a topic, merge similar topics, and generate HTML visualizations. Use when the user asks about research themes, topic distribution, or wants to discover cross-domain connections.
workspace
Manage workspace paper subsets — create workspaces, add/remove papers, search within a workspace, and export BibTeX. Workspaces are thin layers that reference papers in the main library by UUID. Use when the user wants to organize papers into groups for writing, review, or focused analysis.
review-response
Draft point-by-point responses to peer review comments. Locates supporting evidence from workspace papers and the original manuscript. Use when the user receives reviewer feedback and needs to write a rebuttal or revision response letter.
explore
Explore literature by fetching papers from OpenAlex with multi-dimensional filters (ISSN, concept, author, institution, keyword, etc.), building local embeddings, running BERTopic clustering, and multi-mode search (semantic/keyword/unified). Data is isolated in data/explore/<name>/. Use when the user wants to survey a journal, explore a research field, analyze an author's output, or do landscape analysis.
citation-check
Verify citations in AI-generated or human-written text against the local knowledge base. Catches hallucinated references, wrong metadata, and missing papers. Use when the user wants to check if citations are real and accurate.
scientific-runtime
Use when serving scientific CLI tasks through ScholarAIO, especially when the agent should prefer scholaraio toolref, handle partial coverage safely, and avoid turning user work into documentation maintenance.
search
Search academic papers in the local ScholarAIO knowledge base. Supports unified search (keyword + semantic fusion), keyword-only (FTS5), semantic-only (FAISS), author search, and federated search across main library, explore databases, and arXiv. Use when the user wants to find papers, look up literature, search by author, explore research topics, or search across multiple sources. For citation rankings and citation count updates, see the /citations skill.
literature-review
Write a literature review based on papers in a workspace. Covers topic organization, narrative structure, gap identification, and BibTeX export. Use when the user wants to draft a literature review, survey a research area, or summarize the state of the art.
paper-writing
Assist with writing sections of a research paper (Introduction, Related Work, Method, Results, Discussion, Conclusion). Leverages workspace papers for citations and evidence. Use when the user wants help drafting or revising specific paper sections.
research-gap
Identify research gaps and open questions from the literature in a workspace. Combines topic clustering, citation analysis, and cross-paper comparison. Use when the user wants to find unexplored areas, formulate research questions, or assess where the field is heading.
bioinformatics
Use when working on bioinformatics toolchains such as alignment, variant calling, phylogenetics, or protein-structure analysis, especially when the agent must route across BLAST, minimap2, samtools, bcftools, MAFFT, IQ-TREE, or ESMFold.