YuukiAS
- 206 skills
- 0 followers
- 2 repo stars
- last week last updated
- ▌ Shap · yuukias bundleModel interpretability and explainability using SHAP (SHapley Additive exPlanations). Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.
- ▌ Vaex · yuukias bundleUse this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM.
- ▌ Ocr Kb · yuukias bundle长文档 OCR、扫描 PDF 恢复、公式/表格/图注提取、断点续跑和 DOCX/Markdown 交付工作流。用于把 PDF 页面安全转成可编辑文本并做质量核查;内部处理模式可记录为 OCR,但用户不需要说旧 pipeline 名。
- ▌ Transformers · yuukias bundleThis skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks.
- ▌ Pymoo · yuukias bundleMulti-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.
- ▌ Sympy · yuukias bundleUse this skill when working with symbolic mathematics in Python. Apply this skill when the user needs exact symbolic results rather than numerical approximations, or when working with mathematical formulas that contain variables and parameters.
- ▌ Matlab · yuukias bundleMATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. Also use when the user needs help with MATLAB syntax, functions, or wants to convert between MATLAB and Python code.
- ▌ Polars · yuukias bundleFast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1-100GB datasets, ETL pipelines, faster pandas replacement. For larger-than-RAM data use dask or vaex.
- ▌ PDF · yuukias bundleUse this skill whenever the user wants to do anything with PDF files. If the user mentions a .pdf file or asks to produce one, use this skill.
- ▌ Pyzotero · yuukias bundleInteract with Zotero reference management libraries using the pyzotero Python client. Retrieve, create, update, and delete items, collections, tags, and attachments via the Zotero Web API v3.
- ▌ Hypogenic · yuukias bundleAutomated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis).
- ▌ DOCX · yuukias bundleUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill.
- ▌ XLSX · yuukias bundleUse this skill any time a spreadsheet file is the primary input or output. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it.
- ▌ Plotly · yuukias bundleInteractive visualization library. Use when you need hover info, zoom, pan, or web-embeddable charts. Best for dashboards, exploratory analysis, and presentations. For static publication figures use matplotlib or scientific-visualization.
- ▌ Gget · yuukiasArchived quick bioinformatics lookup note. Use bioinformatics-database-retrieval for active database routing.
- ▌ Torch Geometric · yuukias bundleGraph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.
- ▌ Networkx · yuukias bundleComprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Applicable to social networks, biological networks, transportation systems, citation networks, and any domain involving pairwise relationships.
- ▌ Seaborn · yuukias bundleStatistical visualization with pandas integration. Use for quick exploration of distributions, relationships, and categorical comparisons with attractive defaults. Best for box plots, violin plots, pair plots, heatmaps. Built on matplotlib. For interactive plots use plotly; for publication styling use scientific-visualization.
- ▌ PPTX · yuukias bundleUse this skill any time a .pptx file is involved in any way — as input, output, or both. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx filename, regardless of what they plan to do with the content afterward.
- ▌
- ▌ Geopandas · yuukias bundlePython library for working with geospatial vector data including shapefiles, GeoJSON, and GeoPackage files. Supports PostGIS databases, interactive maps, and integration with matplotlib/folium/cartopy.
- ▌ Peer Review · yuukias bundleReviewer-style manuscript or grant critique and acceptance-risk assessment. Use for pre-submission self-review, paper验收, likely objections, rebuttal assessment, claim-evidence audit, methods/statistics critique, reporting standards, and concern ledgers. Route prose drafting to scientific-writing and scoring to scholar-evaluation.
- ▌ MCP Builder · yuukias bundleGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
- ▌ Depmap · yuukiasArchived provider note for DepMap lookup. Use bioinformatics-database-retrieval for active project routing.
- ▌ Pytorch Lightning · yuukias bundleDeep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.
- ▌ Stable Baselines3 · yuukias bundleProduction-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations.
- ▌ Umap Learn · yuukias bundleUMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.
- ▌ Scientific Prose · yuukias bundleEnglish scientific report writing and revision pass. Use for research reports, progress reports, figure-heavy PDFs, manuscripts, rebuttals, technical summaries, and slide text that must keep evidence, uncertainty, captions, and conclusions scientifically defensible without AI-sounding or defensive/self-undermining prose.
- ▌ Pathml · yuukias bundleFull-featured computational pathology toolkit. Use for advanced WSI analysis including multiplexed immunofluorescence (CODEX, Vectra), nucleus segmentation, tissue graph construction, and ML model training on pathology data. Supports 160+ slide formats. For simple tile extraction from H&E slides, histolab may be simpler.
- ▌ Matplotlib · yuukias bundleLow-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientific workflows.
- ▌ Pydicom · yuukias bundlePython library for working with DICOM (Digital Imaging and Communications in Medicine) files. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.
- ▌ What If Oracle · yuukias bundleRun structured What-If scenario analysis with multi-branch possibility exploration. Also trigger when the user faces a fork-in-the-road decision, wants to stress-test an idea, or needs to think through consequences before committing.
- ▌ Timesfm Forecasting · yuukias bundleZero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model.
- ▌ Scikit Learn · yuukias bundleMachine learning in Python with scikit-learn. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.
- ▌ D2 Diagrams · yuukias bundleGenerate D2 source diagrams and rendered SVG/PNG outputs for architecture, infrastructure, method pipelines, system components, and codebase structure. Use when a text-based diagram DSL is preferable to manual drawing.
- ▌ Scientific Rewrite · yuukias bundleSource-faithful structural rewrite route for existing Chinese or Chinese-dominant scientific/technical material when users ask to reorganize it into clearer Chinese while preserving facts, numbers, formulas, citations, comparisons, conditions, limitations, paths, and exact details.
- ▌ Arxiv Database · yuukias bundleSearch and retrieve preprints from arXiv via the Atom API. Use this skill when searching for papers in physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering, or economics by keywords, authors, arXiv IDs, date ranges, or categories.
- ▌ Markitdown · yuukias bundleConvert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.
- ▌ Infographics · yuukias bundleCreate professional infographics from text, data, or research using configured research, image-generation, and quality-review providers. Produces polished, source-faithful visual explanations for reports, presentations, education, and public communication.
- ▌ Research Grants · yuukias bundleWrite competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements.
- ▌ Venue Templates · yuukias bundleThis skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
- ▌ Paper 2 Web · yuukias bundleThis skill should be used when converting academic papers into promotional and presentation formats including interactive websites (Paper2Web), presentation videos (Paper2Video), and conference posters (Paper2Poster).
- ▌ Pubmed Database · yuukias bundleDirect REST API access to PubMed. Advanced Boolean/MeSH queries, E-utilities API, batch processing, citation management. For Python workflows, prefer biopython (Bio.Entrez). Use this for direct HTTP/REST work or custom API implementations.
- ▌ Research Lookup · yuukias bundleFind current research information and recent papers quickly. Use for latest papers, targeted evidence gathering, methods/protocol checks, and source-backed facts. Route systematic or related-work synthesis to literature-review, claim-support verdicts to citation-verification, and BibTeX or library cleanup to citation-management or pyzotero.
- ▌ Canvas Design · yuukias bundleCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
- ▌ Theme Factory · yuukias bundleToolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
- ▌ Bioservices · yuukiasArchived multi-provider query note. Use bioinformatics-database-retrieval for active database routing.
- ▌ Pyhealth · yuukias bundleComprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data.
- ▌ PPTX Posters · yuukias bundleCreate research posters using HTML/CSS that can be exported to PDF or PPTX. Use this skill ONLY when the user explicitly requests PowerPoint/PPTX poster format. For standard research posters, use latex-posters instead. This skill provides modern web-based poster design with responsive layouts and easy visual integration.
- ▌ Biorxiv Database · yuukias bundleEfficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews.
- ▌ Parallel Web · yuukias bundleWeb search and content extraction through Parallel Search API when this provider is requested or when research results must be saved with reproducible source files. Follow host browsing/tool instructions when they specify another search path.
- ▌ Generate Image · yuukias bundleGenerate or edit images using configured image-generation providers. Use for photos, illustrations, artwork, visual assets, concept art, and general-purpose images; for flowcharts, circuits, pathways, and technical diagrams, use scientific-schematics instead.
- ▌ Literature Review · yuukias bundleSynthesize scholarly literature and create single-paper evidence cards. Use for systematic/scoping/narrative reviews, related work, paper精读, paper cards, claim-evidence extraction, method maps, thematic synthesis, and research-gap analysis. Route quick lookup, DOI/claim checks, BibTeX, and Zotero to citation skills.
- ▌ Dhdna Profiler · yuukiasExtract cognitive patterns and thinking fingerprints from any text. Also trigger when the user provides text and wants deeper insight into the author's reasoning patterns, decision-making style, or cognitive signature.
- ▌ Ena Database · yuukiasArchived provider note for ENA sequence lookup. Use bioinformatics-database-retrieval for active project routing.
- ▌ Geo Database · yuukiasArchived provider note for GEO dataset lookup. Use bioinformatics-database-retrieval for active project routing.
- ▌ Cardiac Mri · yuukias bundleUse for cardiac MRI / CMR domain knowledge, cine SAX/LAX, ED/ES timing, LV/RV function, myocardial strain, tagged MRI, feature tracking, and cardiac phenotype validation independent of any single project.
- ▌ Neurokit2 · yuukias bundleComprehensive biosignal processing toolkit for analyzing physiological data including ECG, EEG, EDA, RSP, PPG, EMG, and EOG signals.
- ▌ Latex Posters · yuukias bundleCreate professional research posters in LaTeX using beamerposter, tikzposter, or baposter. Support for conference presentations, academic posters, and scientific communication. Includes layout design, color schemes, multi-column formats, figure integration, and poster-specific best practices for visual communication.
- ▌ Bgpt Paper Search · yuukias bundleSearch scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. Returns 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions.
- ▌ Openalex Database · yuukias bundleQuery and analyze scholarly literature using the OpenAlex database. Use for literature searches, research output analysis, citation analysis, and academic database queries.
- ▌ Open Notebook · yuukias bundleSelf-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis. Supports 16+ AI providers including OpenAI, Anthropic, Google, Ollama, Groq, and Mistral with complete data privacy through self-hosting.
- ▌ Drawio Diagrams · yuukias bundleCreate, edit, validate, and export editable draw.io diagrams for architecture, methods, flowcharts, ER diagrams, and paper method figures. Use when the deliverable should remain editable as .drawio XML or embedded editable SVG/PDF.
- ▌ Content Generation · yuukiasArchived legacy academic content-generation pipeline note. Do not route new writing tasks here; use paper-workflow-orchestrator, scientific-writing, peer-review, writing-fidelity, and chinese-prose for current manuscript drafting and review.
- ▌ Scholar Evaluation · yuukias bundleQuantitatively evaluate scholarly work with a fixed rubric or ScholarEval-style dimensions. Use for rubric assessment, benchmarked quality scoring, numbered ratings, and dimension-by-dimension evaluation. Route ordinary reviewer-style critique to peer-review and prose revision to scientific-writing.
- ▌
- ▌ Gene Database · yuukiasArchived provider note for gene lookup. Use bioinformatics-database-retrieval for active project routing.
- ▌ Gtex Database · yuukiasArchived provider note for GTEx expression lookup. Use bioinformatics-database-retrieval for active project routing.
- ▌ Gwas Database · yuukiasArchived provider note for GWAS Catalog lookup. Use bioinformatics-database-retrieval for active project routing and GWAS summary-stat database selection.
- ▌ Kegg Database · yuukiasArchived provider note for KEGG pathway lookup. Use bioinformatics-database-retrieval for active project routing.
- ▌ Brand Creative Assets · yuukias bundleCreate and review brand-related frontend assets: brand identity, visual guidelines, banners, hero visuals, slides, social images, icons, and marketing creative. Use for branded campaigns and visual asset systems.
- ▌
- ▌ Citation Management · yuukias bundleManage bibliography, BibTeX, citation metadata, and reference-library hygiene. Use for DOI/PMID/arXiv-to-BibTeX conversion, metadata extraction, duplicate repair, and style formatting. Route claim support to citation-verification, literature synthesis to literature-review, paper lookup to research-lookup, and Zotero operations to pyzotero.
- ▌ Experiment Execution · yuukias bundlePlan, run, monitor, interpret, and reproduce computational or scientific experiments, including run setup, metric tracking, statistical interpretation, failure triage, and reproducibility checks.
- ▌ Plantuml Diagrams · yuukias bundleCreate PlantUML source and rendered diagrams for sequence, activity, class, component, deployment, state, and C4-style architecture diagrams. Use when UML semantics are more important than freeform drawing.
- ▌ Gnomad Database · yuukiasArchived provider note for gnomAD variant lookup. Use bioinformatics-database-retrieval for active project routing.
- ▌ Jaspar Database · yuukiasArchived provider note for JASPAR motif lookup. Use bioinformatics-database-retrieval for active project routing.
- ▌ String Database · yuukiasArchived provider note for STRING network lookup. Use bioinformatics-database-retrieval for active project routing.
- ▌ Consciousness Council · yuukias bundleRun a multi-perspective Mind Council deliberation on any question, decision, or creative challenge. Also trigger when the user faces a dilemma, trade-off, or complex choice with no obvious answer.
- ▌ Hypothesis Generation · yuukias bundleStructured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them.
- ▌ Citation Verification · yuukias bundleVerify academic citations, references, BibTeX entries, DOI/PMID metadata, citation claims, and figure/table evidence before manuscript submission, review response, or report delivery. Use when citation existence or claim support matters more than citation formatting alone.
- ▌ Latex Paper Authoring · yuukias bundleAuthor, organize, repair, and prepare LaTeX research papers for arXiv, Overleaf, conference templates, or journal submission. Use when manuscript structure, LaTeX source hygiene, compilation, figures, bibliography, or template cleanup is central.
- ▌ Cellxgene Census · yuukiasArchived provider note for CELLxGENE Census lookup. Use bioinformatics-database-retrieval for active project routing unless doing single-cell analysis.
- ▌ Ensembl Database · yuukiasArchived provider note for Ensembl lookup. Use bioinformatics-database-retrieval for active project routing.
- ▌ Monarch Database · yuukiasArchived provider note for Monarch phenotype lookup. Use bioinformatics-database-retrieval for active project routing.
- ▌ Uniprot Database · yuukiasArchived provider note for UniProt protein lookup. Use bioinformatics-database-retrieval for active project routing.
- ▌ Perplexity Search · yuukias bundlePerform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter.
- ▌ Excalidraw Diagrams · yuukias bundleCreate or revise Excalidraw-style sketch diagrams for early architecture, workflow, method, and concept ideation. Use when the user wants informal hand-drawn exploration rather than publication-final figures.
- ▌ Bioinformatics Workflows · yuukias bundleCommon bioinformatics workflows across databases, single-cell analysis, genomics I/O, and omics analysis.
- ▌ Skill Library Analysis · yuukias bundleAnalyze, deduplicate, cluster, and select skills from a large skill library or cloned upstream sources. Use when maintaining AI_Skills_Collection, comparing external skill repos, or deciding whether to merge, add, archive, or ignore skills.
- ▌ Imagegen · yuukias bundleGenerate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts.
- ▌ Pysam · yuukias bundleGenomic file toolkit. Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, extract regions, calculate coverage, for NGS data processing pipelines.
- ▌ Interpro Database · yuukiasArchived provider note for InterPro domain lookup. Use bioinformatics-database-retrieval for active project routing.
- ▌ Lamindb · yuukias bundleThis skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR.
- ▌ Reactome Database · yuukiasArchived provider note for Reactome pathway lookup. Use bioinformatics-database-retrieval for active project routing.
- ▌ Medical Imaging Workflows · yuukias bundleMedical imaging workflows for CMR, DICOM/NIfTI, classical features, deep learning, and pathology imaging.
- ▌ Bayesian Ppl Diagnostics · yuukias bundleExecutable guidance for Bayesian workflows using Stan/CmdStanPy, brms, PyMC, and ArviZ, with legacy JAGS/OpenBUGS paths and Rcpp acceleration patterns.
- ▌ Alphafold Database · yuukiasArchived provider note for AlphaFold DB lookup. Use bioinformatics-database-retrieval for active project routing.
- ▌ Scanpy · yuukias bundleStandard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use anndata.
- ▌ Scvelo · yuukias bundleRNA velocity analysis with scVelo. Estimate cell state transitions from unspliced/spliced mRNA dynamics, infer trajectory directions, compute latent time, and identify driver genes in single-cell RNA-seq data. Complements Scanpy/scVI-tools for trajectory inference.