Browse the metahub catalog

Structure a raw invention idea into a formal invention disclosure. Use when user says "构建发明", "structure invention", "发明构建", "invention disclosure", or wants to formalize a rough idea into a patent-ready structure.

Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab). Use when the user says '写面试 cheat sheet', '写一份 X 教程', '帮我准备 Y 面试题', '出一份 X 速查', or wants a 600-1000 line Chinese tutorial on a specific ML topic.

Workflow 1: Full idea discovery pipeline to go from a broad research direction to validated, pilot-tested ideas. Use when user says "找idea全流程", "idea discovery pipeline", "从零开始找方向", or wants the complete idea exploration workflow.

Local document and PDF parsing with spatial text and bounding boxes. Use for extracting text from PDFs, DOCX, Office files, and images; OCR on scans; layout-preserved JSON for RAG; batch-ingesting paper folders; or page screenshots for multimodal agents — even when the user does not name liteparse. Prefer over MarkItDown when you need bboxes, fast local parsing, or PNG page renders; prefer over the pdf skill for merge/split/forms.

Electronic lab notebook API integration. Access notebooks, manage entries/attachments, backup notebooks, integrate with Protocols.io/Jupyter/REDCap, for programmatic ELN workflows.

Automated 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). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming.

Use when the user is doing AI/ML work in a scientific domain such as biology, chemistry, physics, astronomy, climate, genomics, materials, medicine, ecology, energy, engineering, math, drug discovery, protein design, weather modeling, theorem proving, single-cell, or PDE solving. Hugging Science is a curated catalog of scientific datasets, models, blog posts, and interactive Spaces. This skill helps discover and use resources via `datasets`, `transformers`, the HF Inference API, `gradio_client`, and methodology citations.

Analyze and engineer protein glycosylation. Scan sequences for N-glycosylation sequons (N-X-S/T), predict O-glycosylation hotspots, and access curated glycoengineering tools (NetOGlyc, GlycoShield, GlycoWorkbench). For glycoprotein engineering, therapeutic antibody optimization, and vaccine design.

Submit and manage protocols on Ginkgo Bioworks Cloud Lab (cloud.ginkgo.bio), a web-based interface for autonomous lab execution on Reconfigurable Automation Carts (RACs). Use when the user wants to run protein expression and purification (cell-free, E. coli, or Pichia), HiBiT or A280 or LabChip quantification, IVT mRNA/circRNA synthesis, thermal shift / developability assays, Echo-MS enzyme or analyte methods, SPR target onboarding, fluorescent pixel art, or otherwise interact with Ginkgo Cloud Lab services. Covers protocol selection, input preparation, pricing, and ordering workflows.

Fast CLI/Python queries to 20+ bioinformatics databases. Use for quick lookups: gene info, BLAST/BLAT, viral sequence downloads, AlphaFold structures, enrichment analysis, OpenTargets, COSMIC, CELLxGENE, and 8cube mouse specificity/expression data. Best for interactive exploration and simple queries. For batch processing or advanced BLAST use biopython; for multi-database Python workflows use bioservices.

This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.

Parse 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.

Design experiments and studies BEFORE data is collected — choosing a design, randomizing, blocking, and laying out treatment combinations so the results will actually be interpretable. Use whenever someone is planning a study, asks how to assign subjects/samples to groups, mentions randomization, blocking, stratification, controls, factorial or fractional-factorial designs, design of experiments (DOE), screening many factors, response-surface optimization, crossover or repeated-measures or split-plot designs, cluster/group randomization, Latin squares, plate layouts, batch/run-order effects, replication vs. pseudoreplication, or sequential/adaptive/group-sequential designs. Trigger this even for informal phrasings like "how should I set up this experiment", "how do I avoid confounding", "what's the best way to test these 6 factors", or "assign these mice to conditions". For computing the sample size or power once the design is chosen, use statistical-power; for analyzing data already collected, use statistical-analysis.

Use when working directly with the `esm` Python SDK, ESM3 or ESMC model IDs, Forge/Biohub inference clients, or ESMFold2 folding workflows.

DiffDock and DiffDock-L molecular docking. Use for protein-small-molecule pose prediction from PDB or sequence plus SMILES/SDF/MOL2, batch docking, virtual screening, and pose-confidence interpretation. Not for binding affinity prediction.

This skill should be used when the harness, scaffold, workflow, or optimizer itself is the optimization target: recursive self-improvement (RSI) loops, meta-harnesses, self-improving harnesses that mine their own failures and propose bounded edits, evolutionary or population-based search over agent scaffolds, acceptance gates for self-modifying systems, and agentic context evolution where the mechanism that produces context is versioned and evolved. Route governance of a single autonomous loop (locked surfaces, durable logs, rollback, novelty gates, approval boundaries) to harness-engineering, measurement and quality-gate design to evaluation, judge design to advanced-evaluation, and remote sandbox infrastructure to hosted-agents.

UI must comply with WCAG 2.2 Level AA, as required by the European Accessibility Act (EN 301 549). Do not deviate without deliberate justification. Disabled UI elements are explicitly exempt from colour contrast requirements. Use when designing, building, or reviewing any user-facing interface for accessibility compliance.

The most important actions and content in a UI should be visually prominent — through size, colour, weight, and position. Visual hierarchy guides the user's eye to what matters most and signals which action is primary. Use when designing button groups, CTAs, dashboards, cards, or any layout where actions or content have different importance levels.

Related features and tasks — such as purchase flows, onboarding, or multi-step configuration — should be designed as natural, guided paths that feel coherent and fit the product hierarchy. Use wizards for complex sequential tasks. Use when designing flows, onboarding, checkout, setup sequences, or any multi-step user journey.

UI density — how much information and how many features appear at once — should match the primary platform and user type. Desktop supports dense, feature-rich interfaces; mobile requires focused, reduced layouts. Enterprise power users tolerate higher density than occasional users. Use when designing data tables, dashboards, toolbars, or adapting a desktop product for mobile.

UI should make it immediately clear where the user is, what context they are operating in, and what their actions will affect. Use lines, regions, colour areas, breadcrumbs, and scope labels to communicate hierarchy and context — especially in deep navigation structures or multi-section layouts.

Tabs organise related content under a shared context — switching tabs swaps the view without leaving the page. Use when a screen has multiple distinct content areas that share a common header or action set, and when the user needs to switch between them frequently. Use when designing tabbed layouts, content panels, settings pages, detail views, or dashboards with multiple data views.

Sticky and fixed positioning keeps critical UI persistent as the user scrolls — headers at the top, toolbars at the bottom on mobile. Use deliberately: too many fixed layers create visual noise and reduce content area. Use when designing navigation headers, bottom toolbars, floating action buttons, or table column headers.

Keep status and error colours minimal and consistent — too many semantic colours confuse users. Each colour must mean exactly one thing. Errors should be recoverable, large failures must be prevented, and the UI should always give the user a path forward. Use when designing status indicators, error states, form validation, alerts, or any feedback system.

Semantic HTML5, SEO fundamentals, alt texts, progressive enhancement, SPA considerations, device capability detection, and user context awareness. Good HTML is the foundation of accessibility, SEO, and resilient UI. Use when building any web UI, reviewing markup quality, or optimising for search and accessibility.

Scroll areas inside a layout should be avoided wherever possible. When unavoidable, allow only one scroll axis at a time and always keep the user in control. Use when designing layouts, data tables, panels, or any component that might introduce an inner scroll container.

Mobile, tablet, and desktop are different interaction paradigms — not the same layout scaled up or down. Sections can be hidden, repositioned, or made sticky on mobile. Navigation and primary actions move. Use when designing responsive layouts, adapting desktop UI for mobile, or deciding what to show on each breakpoint.

Any component rendered many times — cards, list rows, table cells, nav items, tiles, KPI widgets, feed entries — is a fixed slot model, not a free-form box. The same slots appear in the same place in every instance and stay aligned across siblings even when text and values vary in length. Reserve space for optional slots, pin anchor elements (CTA, price, value), clamp overflowing text, and give the full value back via title/tooltip. Use when building or reviewing any repeated component whose content length differs between instances.

UI patterns borrowed from the physical world feel immediately intuitive — cards feel graspable, carousels feel scrollable, drawers feel pullable. Use real-world metaphors deliberately to reduce the learning curve and make interactions feel natural. Use when designing layout patterns, gestures, or navigation paradigms.

Audit UI performance with Lighthouse and fix Core Web Vitals — LCP, CLS, INP. Fast UI is good UX. Use when optimising page load, fixing layout shift, reducing input delay, improving Lighthouse scores, or reviewing images, fonts, and render-blocking resources.

Operational expert tools — used by domain specialists for hours every day — require a different design approach than consumer or occasional-use software. Information density, workflow linearity, and at-a-glance status take priority over whitespace and discoverability. Use when designing dispatch tools, warehouse management, logistics, scheduling, or any B2B tool whose primary users are trained specialists.

|

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

Provides context about the Roo Code evals system structure in this monorepo. Use when tasks mention "evals", "evaluation", "eval runs", "eval exercises", or working with the evals infrastructure. Helps distinguish between the evals execution system (packages/evals, apps/web-evals) and the public website evals display page (apps/web-roo-code/src/app/evals).

Phylogenetic tree toolkit (ETE). Tree manipulation (Newick/NHX), evolutionary event detection, orthology/paralogy, NCBI taxonomy, visualization (PDF/SVG), for phylogenomics.

Legacy error-resolution reference archive retained for migration. Do not route user tasks here; use systematic-debugging for active bug, stack-trace, and root-cause work.

Access European Nucleotide Archive via API/FTP. Retrieve DNA/RNA sequences, raw reads (FASTQ), genome assemblies by accession, for genomics and bioinformatics pipelines. Supports multiple formats.

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.

Python library for accessing, analyzing, and extracting data from SEC EDGAR filings. Use when working with SEC filings, financial statements (income statement, balance sheet, cash flow), XBRL financial data, insider trading (Form 4), institutional holdings (13F), company financials, annual/quarterly reports (10-K, 10-Q), proxy statements (DEF 14A), 8-K current events, company screening by ticker/CIK/industry, multi-period financial analysis, or any SEC regulatory filings.

Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.

This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.

Umbrella skill for document workflows (PDF/DOCX/XLSX/PPTX). Dispatches to the most specific document skill to reduce noise and improve routing precision.

Write documentation following Metabase's conversational, clear, and user-focused style. Use when creating or editing documentation files (markdown, MDX, etc.).

DNAnexus cloud genomics platform. Build apps/applets, manage data (upload/download), dxpy Python SDK, run workflows, FASTQ/BAM/VCF, for genomics pipeline development and execution.

Minimal compatibility wrapper for vibe Dialectic Mode (multi-perspective design analysis).

|

Design experiments and quasi-experiments before analysis. Use when choosing study design, treatment/control structure, outcomes, assumptions, validation plans after scientific experiment failure, or which of DiD, ITS, synthetic control, or regression discontinuity fits the research question. For fitting models or estimating effects on existing data, use performing-causal-analysis instead.

Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.