Published skills
drawio-skill
Generates draw.io diagrams from natural language, using 6 presets and a 2-round self-check loop. Exports to PNG/SVG/PDF/JPG.
drawio-skill
Generate diagrams, flowcharts, architecture diagrams, ER, UML, network topology, ML/DL model figures, and mind maps. Ideal for explaining complex systems, data flows, or relationships that benefit from visual representation.
asta-skill
Domain expertise for Ai2 Asta MCP tools (Semantic Scholar corpus). Intent-to-tool routing, safe defaults, workflow patterns, and pitfall warnings for academic paper search, citation traversal, and author discovery.
paper-fetch
Use this skill to obtain, download, or fetch a paper's PDF, given identifiers like a DOI, arXiv ID, title, or citation. It triggers on requests to download papers, find PDFs, or get open-access versions, including bulk requests.
excalidraw
Use when user requests diagrams, flowcharts, architecture charts, or visualizations. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that benefit from visual representation. Generates .excalidraw files and exports to PNG/SVG via Kroki API or locally using excalidraw-brute-export-cli.
creating-mermaid-diagrams
Generates Mermaid diagrams (.mmd) and exports them to PNG/SVG/PDF. Use this skill for visualizing various diagrams like flowcharts, sequence, class, ER, or state machine diagrams, especially when explaining complex systems, API flows, or database schemas.
semanticscholar-skill
Use when searching academic papers, looking up citations, finding authors, or getting paper recommendations using the Semantic Scholar API. Triggers on queries about research papers, academic search, citation analysis, or literature discovery.
tldraw-skill
Use when user requests diagrams, flowcharts, architecture charts, or visualizations. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that benefit from visual representation. Generates .tldr JSON files and exports to PNG/SVG locally using @kitschpatrol/tldraw-cli.
yt2bb
Use when the user wants to repurpose a YouTube video for Bilibili, add bilingual (English-Chinese) subtitles to a video, or create hardcoded subtitle versions for Chinese platforms.
scholar-deep-research
Use when the user asks for a literature review, academic deep dive, research report, state-of-the-art survey, topic scoping, comparative analysis of methods/papers, grant background, or any request that needs multi-source scholarly evidence with citations. Also trigger proactively when a user question clearly requires academic grounding (e.g. "what's known about X", "compare approach A vs B in the
bbc-skill
Fetches Bilibili video comments for UP主 self-analysis, producing JSONL and summary.json for further Claude Code analysis (sentiment, keywords, audience trends). Use this read-only tool when asked to collect, download, export, or analyze comments from a Bilibili video (BV ID / URL / UID).
agent-native-design
Use when designing, reviewing, or refactoring a CLI that must serve AI agents alongside humans, or when converting an API or SDK into an agent-usable CLI interface.
imagen-qwen
Use when generating images with Alibaba Cloud Bailian API, especially for Chinese text rendering or photorealistic images.
journal-abbrev
Use when looking up journal or magazine name abbreviations, converting between full names and ISO 4/MEDLINE abbreviations, processing BibTeX files for journal name standardization, or answering questions about 期刊缩写/杂志缩写. Triggers on "journal abbreviation", "abbreviate journal", "journal name", "期刊缩写", "杂志缩写", "ISO 4", "LTWA", "BibTeX journal". PROACTIVELY USE when user mentions citation formatting
scientific-thinking
Use when interpreting research findings, evaluating scientific evidence, analyzing mechanisms, comparing competing hypotheses, designing experiments, or constructing scientific arguments.
zenodo-skill
Use for Zenodo-related tasks like depositing or publishing research artifacts, minting DOIs, uploading files, creating new versions, or searching records. It covers the full Zenodo REST API workflow, including creating depositions, uploading files, setting metadata, and publishing.
thesis-reviewer
Use when the user wants to review, evaluate, or provide feedback on a master's or doctoral thesis. It supports all disciplines with discipline-specific review modules.
seurat-skill
This comprehensive Seurat v5 (R) guide covers single-cell RNA-seq and multimodal analysis. It details installation, standard workflows, clustering, integration, differential expression, visualization, spatial transcriptomics, CITE-seq, ATAC-seq, WNN, and cell cycle regression.
grant-thinking-general
Use to evaluate grant ideas, diagnose proposal logic, frame fundable projects, strengthen reviewer-aware arguments, or prepare any section of a research proposal.
plantuml-skill
Use when user requests diagrams, flowcharts, sequence diagrams, class diagrams, component diagrams, ER diagrams, architecture charts, or visualizations. Also use proactively when explaining systems with 3+ components, APIs, data flows, or class hierarchies. Generates .puml files and exports to PNG/SVG via Kroki API (no local install required).
grant-thinking-cn-biology
Use when evaluating biology grant ideas in the Chinese funding context (NSFC, MOST, etc.) — diagnosing project legitimacy, mechanism-centered scientific questions, reviewer-aware logic, innovation discipline, feasibility, and scope control across funding levels (youth, general, key).
figshare-skill
Interact with Figshare via its v2 REST API to search public data, download files, manage personal content (articles, collections, projects), or upload files, including large multi-part uploads. This skill triggers on mentions of "figshare", Figshare DOIs, figshare.com URLs, or phrases like "upload".
target-prioritization
Prioritize drug targets from a ranked gene list (e.g., scRNA-seq DE output) by orchestrating parallel API queries against UniProt, OpenTargets (with integrated DepMap CRISPR essentiality + gnomAD constraint), PubMed, the Human Protein Atlas (HPA), and ChEMBL tool compounds, then re-ranking by a composite score combining protein localization, druggability, disease genetics, tissue specificity (safe
ccc-skill
Domain expertise for cell-cell communication (CCC) analysis, including intent-to-tool routing, workflow patterns, code templates, and pitfall warnings. Covers LIANA+, CellPhoneDB, CellChat, NicheNet, COMMOT, Squidpy, MEBOCOST, DIALOGUE, and 10+ other tools for scRNA-seq and spatial transcriptomics data.
Category alert