Loading...
Loading...
Found 51 Skills
Probability, distributions, hypothesis testing, and statistical inference. Use for A/B testing, experimental design, or statistical validation.
Use when invalid data causes failures deep in execution - validates at every layer data passes through to make bugs structurally impossible rather than temporarily fixed
Professional Pydantic v2.12 development for data validation, serialization, and type-safe models. Use when working with Pydantic for (1) creating or modifying BaseModel classes, (2) implementing validators and serializers, (3) configuring model behavior, (4) handling JSON schema generation, (5) working with settings management, (6) debugging validation errors, (7) integrating with ORMs or APIs, or (8) any production-grade Python data validation tasks. Includes complete API reference, concept guides, examples, and migration patterns.
Digital archiving workflows with AI enrichment, entity extraction, and knowledge graph construction. Use when building content archives, implementing AI-powered categorization, extracting entities and relationships, or integrating multiple data sources. Covers patterns from the Jay Rosen Digital Archive project.
Generates comprehensive synthetic fine-tuning datasets in ChatML format (JSONL) for use with Unsloth, Axolotl, and similar training frameworks. Gathers requirements, creates datasets with diverse examples, validates quality, and provides framework integration guidance.
Use when building joi schemas, custom validators, extensions, or working with joi's validation pipeline. Covers all types, references, templates, errors, and the extension API.
The drum sounds. Bear and Bloodhound gather for safe data movement. Use when migrating data that requires both careful movement and codebase understanding.
Use when invalid data causes failures deep in execution, requiring validation at multiple system layers - validates at every layer data passes through to make bugs structurally impossible
Expert for developing Streamlit data apps for Keboola deployment. Activates when building, modifying, or debugging Keboola data apps, Streamlit dashboards, adding filters, creating pages, or fixing data app issues. Validates data structures using Keboola MCP before writing code, tests implementations with Playwright browser automation, and follows SQL-first architecture patterns.
Navigate the Valibot repository structure. Use when looking for files, understanding the codebase layout, finding schema/action/method implementations, locating tests, API docs, or guide pages. Covers monorepo layout, library architecture, file naming conventions, and quick lookups.
Production-ready RNA-seq differential expression analysis using PyDESeq2. Performs DESeq2 normalization, dispersion estimation, Wald testing, LFC shrinkage, and result filtering. Handles multi-factor designs, multiple contrasts, batch effects, and integrates with gene enrichment (gseapy) and ToolUniverse annotation tools (UniProt, Ensembl, OpenTargets). Supports CSV/TSV/H5AD input formats and any organism. Use when analyzing RNA-seq count matrices, identifying DEGs, performing differential expression with statistical rigor, or answering questions about gene expression changes.
Multi-layer validation pattern - validates data at EVERY layer it passes through to make bugs structurally impossible, not just caught.