Machine Learning

Molecular fingerprint generation for ML. Use when encoding molecules as feature vectors for machine learning models.

Reduce polygon count in 3D meshes while preserving shape. Use for optimizing models for real-time rendering, 3D printing, and reducing file sizes. Supports quadric error metrics, vertex clustering, and edge collapse methods.

Fetch and extract content from web pages. Use when retrieving page content, extracting text and metadata, parsing HTML, or scraping structured data from URLs.

YAML data serialization format. Use when reading/writing configuration files, Kubernetes manifests, or structured data.

Parse and extract data from HTML documents using BeautifulSoup. Use this skill when working with HTML files, extracting text content, navigating DOM structures, finding elements by tags/classes/IDs, or scraping structured data from web pages that have already been fetched.

Generate documents using Jinja2 templates with variable substitution, loops, conditionals, and filters. Use when creating reports from templates, generating emails, building HTML documents, or producing any text output from structured data.

Convert HTML/CSS documents to PDF using WeasyPrint for web-styled reports. Use when generating PDFs from HTML templates, creating styled PDF reports from web content, or producing print-ready documents with CSS styling.

Statsmodels library for statistical modeling and econometrics. Use for time series decomposition, trend analysis, regression, and seasonal adjustment of economic data.

Build web crawlers and spiders using the Scrapy framework. Use this skill when building large-scale web crawlers, following links across multiple pages, handling request throttling, or creating production scraping pipelines. NOT needed for parsing single HTML files or processing already-fetched content.

Template engine for Python. Use when generating HTML, reports, or dynamic text from templates.

Use RAxML for maximum likelihood phylogenetic tree inference from sequence alignments. Use when you need maximum likelihood inference with bootstrap support values for phylogenetic analysis.

Developing, testing, and deploying Streamlit data applications on Snowflake. Use this skill when you're building interactive data apps, setting up local development environments, testing with pytest or Playwright, or deploying apps to Snowflake using Streamlit in Snowflake.

Advanced visual regression testing with pixel-perfect comparison, AI-powered diff analysis, responsive design validation, and cross-browser visual consistency. Use when detecting UI regressions, validating designs, or ensuring visual consistency.

IDE-grade project scaffolding wizard for creating new projects with comprehensive configuration. Supports 70+ project types: HTML/CSS websites, React, Next.js, Vue, Astro, Remix, React Native, Flutter, Expo, FastAPI, Django, Express, NestJS, Go/Gin, Rust/Axum, Spring Boot, Hono, Elysia, Chrome Extensions, VS Code Extensions, Tauri desktop apps, serverless functions, and more. Provides WebStorm/PyCharm-level project creation with interactive SDK selection, framework configuration, database setup, and DevOps tooling. Use when: creating a new project, setting up a framework application, initializing a codebase, scaffolding boilerplate, building extensions, creating mobile/desktop/web apps, setting up monorepos, or making static websites/landing pages.

Browser testing, web scraping, and UI validation using Playwright MCP. Use this skill when you need to test Streamlit apps, validate web interfaces, test responsive design, check accessibility, or automate browser interactions through MCP tools.

Launch a Streamlit GUI for Task Master tasks.json editing. Use when users want a visual interface instead of CLI/MCP commands.

Manage and synchronize AI agent skills from local SKILL.md files and remote Git repositories, generating Cursor rules with Agent Skills specification XML. This skill should be used when users need to sync skills, add/remove skill repositories, or set up the skills infrastructure.

Managing dbt-core locally - installation, configuration, project setup, package management, troubleshooting, and development workflow. Use this skill for all aspects of local dbt-core development including non-interactive scripts for environment setup with conda or venv, and comprehensive configuration templates for profiles.yml and dbt_project.yml.

Migrate Python projects from setup.py/setup.cfg to pyproject.toml for use with uv. Use when upgrading legacy Python packaging, converting setup.py to modern pyproject.toml format, setting up dependency groups for development/testing, and ensuring `uv run pytest` works correctly.

Expert MLOps engineer specializing in ML infrastructure, platform engineering, and operational excellence for machine learning systems. Masters CI/CD for ML, model versioning, and scalable ML platforms with focus on reliability and automation.