Machine Learning

Cost estimation scripts and tools for calculating GPU hours, training costs, and inference pricing across Modal, Lambda Labs, and RunPod platforms. Use when estimating ML training costs, comparing platform pricing, calculating GPU hours, budgeting for ML projects, or when user mentions cost estimation, pricing comparison, GPU budgeting, training cost analysis, or inference cost optimization.

Format conventions for markdown knowledge vaults. Use when writing notes or when format/syntax questions arise. Covers the dual-reader principle (human + AI), YAML frontmatter, wikilinks, and sources.

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

Generate UML diagrams from source code (PlantUML)

JupyterLab ML/AI development environment management via Podman Quadlet. Supports multi-instance deployment, GPU acceleration (NVIDIA/AMD/Intel), token authentication, and per-instance configuration. Use when users need to configure, start, stop, or manage JupyterLab containers for ML development.

Curated project templates that guide feature-dev Phase 3 questions with research-backed technology choices. Provides standardized options for common project types (SaaS API, ML Service, CLI Tool, Full-Stack). Use when starting new projects or when feature-dev needs structured decision guidance. Do NOT use for existing projects with established stacks - analyze existing code instead.

Implement accessibility for the .NET 8 WPF widget host app. Use when improving keyboard navigation, screen reader support, focus states, and color contrast in XAML and styles.

Story-level quality orchestrator. Pass 1: code quality -> regression -> manual testing (fail fast). Pass 2: verify tests/coverage -> mark Story Done. Auto-discovers team/config.

Création d'interfaces web conformes au Design System de l'État Français (DSFR). Utiliser ce skill pour générer des pages HTML avec les composants officiels du gouvernement français, créer des formulaires administratifs, des tableaux de bord, ou tout site web respectant les standards de l'État.

Эксперт categorical encoding. Используй для ML feature engineering, one-hot, target encoding и embeddings.

Validate, format, and troubleshoot YAML configuration files

Advanced usage of uv, the extremely fast Python package and project manager from Astral. Use this skill when working with uv for project management (uv init, uv add, uv run, uv lock, uv sync), workspaces and monorepos, dependency resolution strategies (universal, platform-specific, constraints, overrides), Docker containerization, PEP 723 inline script metadata, uvx tool execution, Python version management, pip interface migration, pyproject.toml configuration, or any advanced uv workflow. Covers workspaces, resolution strategies, Docker best practices, CI/CD integration, and migration from pip/poetry/pipenv.

Generate Word documents (.docx) using direct OOXML manipulation. Use when the user asks to create Word documents, templates, resumes, invoices, letters, reports, proposals, or any .docx file with full control over formatting and structure.

Use AI to create ASCII text-based preview of PDF page layout. Transforms visual and extracted data into structured ASCII representation for HTML generation.

Diagnose and fix GitHub Actions workflow failures, CI/CD pipeline issues, YAML syntax errors, and workflow configuration problems. Use when debugging failed CI runs, fixing workflow errors, or optimizing GitHub Actions. Keywords: github actions, CI, workflow, pipeline, yml, yaml, actions failure, CI failure, workflow error

Validate Python toolchain alignment between mise, Poetry, and pyproject. Use when changing Python versions, editing pyproject.toml, or seeing Poetry/mise version solver errors. Invokes /toolchain-health to check: - .mise.toml python tool version - pyproject.toml python constraint - Poetry env python interpreter Keywords: python version, mise, poetry, toolchain, env use, lock, install

Use this skill when users need interactive HTML reports, dashboards, charts, or visualizations for LimaCharlie data. You generate the HTML, this skill serves it on localhost.

Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns, generate multiple output formats (XML, Markdown, plain text), preserve file structure and context, optimize for AI consumption with token counting, filter by file types and directories, add custom headers and summaries. Use when packaging codebases for AI analysis, creating repository snapshots for LLM context, analyzing third-party libraries, preparing for security audits, generating documentation context, or evaluating unfamiliar codebases.

Generate UML diagrams from project source code using PlantUML with online rendering

Expert in factor modeling, including Fama-French factors, quality factors, value factors, and multi-factor portfolio analysis. Use when students need to construct factor portfolios, run factor regressions, analyze factor exposures, or implement systematic equity strategies.