YuukiAS
- 206 skills
- 0 followers
- 2 repo stars
- 6 days ago last updated
- ▌ Research Presentations · yuukias bundlePlan evidence-first research and technical presentations from papers, repo evidence, Markdown reports, Asteria or TRACE exports, code results, figures, and existing decks. Use for group meetings, supervisor discussions, seminars, conferences, journal clubs, defenses, and scientific project updates.
- ▌ Frontend Visual Systems 2 · yuukias bundleFrontend visual direction, product-interface content architecture, Product UI Copy handoff, rendered acceptance, design tokens, typography, palette, icon, layout, density, and motion brief.
- ▌ Implementation React Tailwind · yuukias bundleImplement production-ready frontend code with React, TypeScript, Tailwind CSS, and shadcn/ui. Use for components, pages, dashboards, forms, tables, navigation, themes, and responsive UI implementation.
- ▌ Render Chinese Math PDF · yuukias bundleRender and validate Chinese or mixed Chinese/English mathematical Markdown/LaTeX as PDF. Use for CJK text, Unicode math, equations, tables, Pandoc/XeLaTeX, TeX font/cache failures, citation cleanup, or readable PDF QA.
- ▌ Responsive Accessibility Review · yuukias bundleReview and fix frontend responsiveness, accessibility, usability, keyboard behavior, text fitting, contrast, and visual regressions. Use before shipping UI or when asked to improve UX quality.
- ▌ Slurm Workflows · yuukias bundlePlan, submit, monitor, diagnose, and safely iterate Slurm jobs with live Slurm discovery, optional public policy overlays, sticky resource contracts, workload modes, and guarded capacity lifecycle semantics.
- ▌ Chinese Prose · yuukias bundle中文报告、README、Markdown/PDF 成稿、技术文档、科研说明、组会材料和长文“说人话”终审。任何中文 Markdown/PDF/报告/README/面向读者的文档型中文内容都应自动触发本 skill,用于普通中文润色、中文为主、降低 AI 味/翻译腔/模板腔/宣传腔,并保护事实、数字、术语、命令、引用、实验结果和证据边界。普通聊天解释、诊断结论、进度/完成汇报和行动建议应路由到 response-clarity;产品界面标签、按钮、状态、帮助、信任/隐私披露和 locale-specific UI microcopy 应路由到 product-ui-copy。
- ▌ Webapp Testing · yuukias bundleToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
- ▌ Writing Fidelity · yuukias bundlePreserve facts, corrections, labels, structure, equations, citations, version authority, and final artifact identity during writing edits. Route Chinese natural-prose passes to chinese-prose, source-faithful structural scientific/technical rewrites to scientific-rewrite, and English scientific style passes to scientific-prose.
- ▌ Project Skill Installer · yuukias bundleUse when the user asks to install, update, or set up AI_Skills_Collection profiles for the current project. Handles project-local installation only; it does not provide domain knowledge.
- ▌ Codex Workflow Protocol · yuukias bundleUse for complex or risky Codex tasks that require source-of-truth discovery, phased planning, specialist routing, gate-driven verification, live-state supervision, integration ownership, or honest final status reporting.
- ▌ AI Skills Repository Maintainer · yuukias bundleMaintain AI_Skills_Collection itself, including production plugin refinement contracts, source-first changes, generated parity, replay/regression gates, versions, changelogs, registry, catalog, marketplace, and profiles. Use only when the user is working on this repository or explicitly asks to maintain the central skill collection.
- ▌ Frontend Reference Research · yuukias bundleReview external frontend references, screenshots, UI libraries, Figma Community examples, and design cases, then distill reusable patterns without copying third-party pages or unclear assets.
- ▌ Business Presentations · yuukias bundlePlan business, executive, product, operations, market, client, strategy, pitch, and decision decks. Use when the audience is non-technical or the deck asks for a decision, resource, proposal, or business update.
- ▌ Visual Direction · yuukias bundleChoose and execute a deliberate frontend visual direction across typography, palette, structure, texture, imagery, and composition. Use when designing or restyling frontend UI and avoiding generic AI-looking output.
- ▌ Motion Interaction · yuukias bundleDesign and implement frontend motion: page-load choreography, transitions, hover states, scroll effects, feedback animation, and reduced-motion behavior. Use when adding or reviewing animation and interaction polish.
- ▌ Product UX Planning · yuukias bundlePlan frontend products before implementation: purpose, audience, information architecture, navigation, user flows, states, content discipline, and feature scope. Use when starting a new app/page, redesigning UX, or reviewing whether a frontend experience is coherent.
- ▌ Design System Tokens · yuukias bundleCreate or refine frontend design systems: primitive, semantic, and component tokens; CSS variables; Tailwind theme config; typography scales; spacing; component states; brand consistency. Use when making reusable UI systems or aligning multiple screens.
- ▌ Figma Design To Code · yuukias bundlePlan Figma-to-code handoff: identify frames, tokens, assets, accessibility risks, and implementation notes that complement official Figma tooling.
- ▌ Research Reporting · yuukias bundleCreate repo-grounded research reports, milestone summaries, experiment reviews, technical notes, advisor/group-meeting reports, and result retrospectives from project evidence. Use for report semantics even when the final deliverable is a formal PDF; rendering mechanics belong to companion document skills.
- ▌ Frontend Visual Systems · yuukias bundleConvert frontend references and product intent into design tokens, visual direction, palette, typography, icon, layout, density, and motion rules for implementation by a frontend builder.
- ▌ Research Product Frontend · yuukias bundlePlan high-density research product frontends such as medical imaging viewers, phenotype explorers, model comparison dashboards, provenance tools, and experiment history interfaces.
- ▌ Project Thread Handoff · yuukias bundleUse only after explicit Skill selection to hand off the current project thread or recover a same-Project old thread; do not use for ordinary summaries, status checks, brainstorming, or general continuation.
- ▌ Machine Update Orchestrator · yuukias bundleNormal AI Skills Maintainer entry for current-machine update requests such as update presentations, update workflow-core, update AI Skills, update Bridge Kit, and sync this machine. Discovers formal release state, selects the bounded route, delegates to the owning maintainer, and verifies reload/session boundaries.
- ▌ Project Instructions Editor · yuukias bundleUse for requests to create, update, compress, sync, restructure, or reset ChatGPT Project instructions; before editing, require the complete setting or a confirmed empty setting. Exclude prose polishing, writing fidelity, scientific rewrite, AI_Skills maintenance, workflow/control, generic agent/system prompts, and global Custom Instructions.
- ▌ Bridge Kit Maintainer · yuukias bundleInternal AI Skills Maintainer capability for Bridge Kit source, version, distribution, formal release-channel maintenance, editable package refresh, runtime identity checks, and delegation to canonical ai-bridge commands.
- ▌ Product UI Copy · yuukias bundleNatural product-interface microcopy for labels, CTAs, states, help text, onboarding, settings, trust/privacy disclosures, landing-page interface copy, and locale-specific UI wording under frozen product meaning. Use for browser extension, web, desktop/WebView, mobile, and app surfaces after product semantics and UI role are known.
- ▌ Response Clarity · yuukias bundleClear ordinary user-facing explanations, conclusions, diagnostics, advice, progress updates, and task-result summaries after domain reasoning. Use for normal ChatGPT/Codex replies that should be natural in the current target language, lead with the human meaning, reduce unnecessary English/process noise, and preserve exact technical strings.
- ▌ Clinical Reports · yuukias bundleDraft clinical case reports, diagnostic summaries, trial reports, SOAP/H&P/discharge-style documentation, and de-identified medical report templates with privacy, source, and guideline checks.
- ▌ Scientific Figure QA · yuukias bundleAudit scientific figures for publication readiness, accessibility, grayscale readability, export quality, and venue visual constraints.
- ▌ Academic Paper Writer Pro · yuukias bundle学术论文排版、OCR恢复、DOCX/Markdown整理和模板化交付工作流。用于扫描 PDF、DOC/DOCX、Markdown 到 Word/PDF 的结构修复、断点恢复、参考文献整理和最终文件验收;内容写作、审稿和事实保真应路由到 research-writing 与 writing-fidelity。
- ▌ Openai Docs · yuukias bundleUse for openai docs workflows when the task directly names this tool or domain. Prefer narrower project skills or umbrella retrieval skills when the task is only a lookup.
- ▌ Esm · yuukias bundleComprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations).
- ▌ Gtars · yuukias bundleHigh-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.
- ▌ Opentargets Database · yuukiasArchived provider note for OpenTargets lookup. Use bioinformatics-database-retrieval for active project routing.
- ▌ Scientific Schematics · yuukias bundleCreate publication-quality scientific diagrams and schematics using configured image-generation and review providers. Use when papers, grants, presentations, posters, or educational materials need source-faithful visual illustrations, prompt planning, quality review, and iterative refinement.
- ▌ Nature Manuscript Workflow · yuukias bundlePlan, draft, revise, and audit broad-journal or high-impact manuscripts, including claim framing, figure logic, data availability, submission readiness, and reviewer response. Use for story-driven journal strategy, broad-audience manuscript framing, figure-to-claim alignment, and Nature-family targets when explicit.
- ▌ Research Paper Workflow · yuukias bundleFormal manuscript planning, drafting, revision, reviewer-style critique, rubric scoring, rebuttal, supplement, venue, and LaTeX coordination; route literature discovery and citation checks to literature-and-citations.
- ▌ Tiledbvcf · yuukias bundleEfficient storage and retrieval of genomic variant data using TileDB. Scalable VCF/BCF ingestion, incremental sample addition, compressed storage, parallel queries, and export capabilities for population genomics.
- ▌ Flowio · yuukias bundleParse FCS (Flow Cytometry Standard) files v2.0-3.1. Extract events as NumPy arrays, read metadata/channels, convert to CSV/DataFrame, for flow cytometry data preprocessing.
- ▌ Geniml · yuukias bundleThis skill should be used when working with genomic interval data (BED files) for machine learning tasks. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.
- ▌ Exploratory Data Analysis · yuukias bundlePerform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics.
- ▌ Markdown Mermaid Writing · yuukias bundleMarkdown and Mermaid diagram writing for reports, architecture notes, methods, workflows, and scientific documentation when structure or relationships need a diagram. Use for flowcharts, pipelines, dependency maps, timelines, and evidence maps; ordinary prose reports do not require diagrams.
- ▌
- ▌ Skill Creator · yuukias bundleGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
- ▌ Scvi Tools · yuukias bundleDeep generative models for single-cell omics. Use when you need probabilistic batch correction (scVI), transfer learning, differential expression with uncertainty, or multi-modal integration (TOTALVI, MultiVI). Best for advanced modeling, batch effects, multimodal data. For standard analysis pipelines use scanpy.
- ▌ Scientific Critical Thinking · yuukias bundleEvaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review writing use peer-review.
- ▌ Get Available Resources · yuukias bundleThis skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space).
- ▌ Literature And Citations · yuukias bundleCurrent paper lookup, literature synthesis, single-paper evidence cards, citation support checks, BibTeX and reference metadata hygiene, and Zotero-oriented workflows.
- ▌ Statistical Visualization · yuukias bundleStatistical result visualization with Matplotlib and Plotly. For publication-ready figure palettes, venue figure QA, and manuscript figure styling, use the scientific-visualization plugin.
- ▌ Research Product Frontend 2 · yuukias bundleHigh-density research product frontend planning for imaging, phenotype, model comparison, provenance, and experiment interfaces.
- ▌ Plugin Creator · yuukias bundleCreate and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, and baseline placeholders you can edit before publishing or testing.
- ▌ Zarr Python · yuukias bundleChunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.
- ▌ Arboreto · yuukias bundleInfer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.
- ▌ Pydeseq2 · yuukias bundleDifferential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis.
- ▌ Scientific Visualization · yuukias bundleMeta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell).
- ▌ Data Analysis Python · yuukias bundlePython data analysis workflows with EDA, Polars, scikit-learn, and symbolic math.
- ▌ Scientific Slides · yuukiasBuild slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX Beamer.
- ▌ Skill Installer · yuukias bundleInstall external Codex skills from curated lists or GitHub repo paths. Use for third-party skill downloads; for AI_Skills_Collection installs prefer ai-skills repo/user targets and treat codex-home as explicit legacy compatibility.
- ▌ Deeptools · yuukias bundleNGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization.
- ▌ Bayesian Modeling · yuukias bundleBayesian and statistical modeling workflows with PyMC, diagnostics, simulation, and model reporting.
- ▌ Polars Bio · yuukias bundleHigh-performance genomic interval operations and bioinformatics file I/O on Polars DataFrames. Overlap, nearest, merge, coverage, complement, subtract for BED/VCF/BAM/GFF intervals. Streaming, cloud-native, faster bioframe alternative.
- ▌ Biopython · yuukias bundleComprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
- ▌ Clinicaltrials Database · yuukiasArchived provider note for ClinicalTrials.gov lookup. Use research or clinical workflow skills for active project routing.
- ▌ Publication Figure Palettes · yuukias bundleChoose publication figure palettes, contextual Notion-derived style candidates, presets, and snippets with provenance and experimental gates.
- ▌ Etetoolkit · yuukias bundlePhylogenetic tree toolkit (ETE). Tree manipulation (Newick/NHX), evolutionary event detection, orthology/paralogy, NCBI taxonomy, visualization (PDF/SVG), for phylogenomics.
- ▌ Scikit Bio · yuukias bundleBiological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for microbiome analysis.
- ▌ Clinical Decision Support · yuukias bundleProduce group-level clinical decision support, cohort evidence summaries, biomarker-stratified analyses, and guideline-style recommendation documents. Use for research, pharmaceutical, or policy documents, not bedside individual care.
- ▌
- ▌ Phylogenetics · yuukias bundleBuild and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
- ▌ Dnanexus Integration · yuukias bundleDNAnexus cloud genomics platform. Build apps/applets, manage data (upload/download), dxpy Python SDK, run workflows, FASTQ/BAM/VCF, for genomics pipeline development and execution.
- ▌ Latchbio Integration · yuukias bundleLatch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.
- ▌ Medical Imaging Deep Learning · yuukias bundleUse for medical-imaging deep learning tasks involving segmentation, MONAI/nnU-Net baselines, registration or warping, temporal/video imaging, missing-modality fusion, proposal/cascade/refinement models, external method adaptation, and validation evidence gates.
- ▌ Clinical Guideline Checking · yuukias bundleCheck clinical guideline claims against current authoritative sources, jurisdictions, population boundaries, recommendation strength, and update dates before using them in medical documents.
- ▌ Publication Figures · yuukias bundlePublication figure orchestration with contextual palette discovery, Matplotlib, Seaborn, Plotly, and export-ready layout.
- ▌ Neuropixels Analysis · yuukias bundleNeuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology.
- ▌ Medical Imaging Classical Features · yuukias bundleUse when enforcing reproducible medical-imaging preprocessing, physical-space geometry, classical registration baselines, radiomics protocols, or DICOM SEG/SR provenance.
- ▌ Medical Literature Evidence Review · yuukias bundleReview medical literature evidence with dated source notes, evidence hierarchy, population applicability, uncertainty, and safety boundaries. Use for medical evidence summaries, not direct care advice.
- ▌ Find · yuukiasQuickly find pages or databases in Notion by title keywords. Returns precise matches rather than comprehensive results.
- ▌ Medical Imaging Terminology Measurement · yuukias bundleUse medical imaging terminology and measurement conventions with source checks, modality-specific caveats, structured reporting boundaries, and uncertainty language.
- ▌ Search · yuukiasSearch the user's Notion workspace using the Notion MCP server. Use for finding pages, databases, and content by keywords or natural-language queries.
- ▌ Bioinformatics Database Retrieval · yuukias bundleUse for gene, protein, pathway, variant, expression, disease, and structure database lookups. Prefer workflow-specific skills for scanpy, scvi-tools, pysam, or DICOM work.
- ▌ Tasks Plan · yuukiasCreate an implementation plan from a Notion task or specification. Breaks down requirements into actionable steps with estimates and dependencies.
- ▌ Create Page · yuukiasCreate a new Notion page, optionally under a specific parent. Automatically structures content based on page type (meeting notes, project pages, etc.).
- ▌ Create Task · yuukiasCreate a new task in the user's Notion tasks database with sensible defaults for due date, status, owner, and project.
- ▌ Tasks Build · yuukiasBuild a task from a Notion page URL. Fetches task details, marks it in progress, implements the work, and updates status in Notion.
- ▌ Tasks Setup · yuukiasSet up a Notion task board for tracking tasks. Guides users through using a template or connecting an existing board.
- ▌ Database Query · yuukiasQuery a Notion database by name or ID and return structured, readable results with optional filters and sorting.
- ▌ Knowledge Capture · yuukiasTransform conversations and discussions into structured documentation pages in Notion. Captures insights, decisions, and knowledge from chat context with proper organization and linking.
- ▌ Tasks Explain Diff · yuukiasGenerate a rich Notion document explaining code changes. Creates comprehensive documentation with background, intuition, code walkthrough, and verification steps.
- ▌ Create Database Row · yuukiasInsert a new row into a specified Notion database using natural-language property values. Handles property name matching and validation.
- ▌ Meeting Intelligence · yuukiasPrepare meeting materials by gathering context from Notion, enriching with research, and creating both an internal pre-read and external agenda saved to Notion.
- ▌ Research Documentation · yuukiasSearch across your Notion workspace, synthesize findings from multiple pages, and create comprehensive research documentation with proper citations and actionable insights.
- ▌ Spec To Implementation · yuukiasTurn product or tech specs into concrete Notion tasks. Breaks down spec pages into detailed implementation plans with clear tasks, acceptance criteria, and progress tracking.
- ▌ Modal · yuukias bundleRun Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.
- ▌
- ▌ Pufferlib · yuukias bundleHigh-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (Atari, Procgen, NetHack).
- ▌
- ▌ Aeon · yuukias bundleThis skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search.
- ▌ Dask · yuukias bundleDistributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.