Machine Learning
1913 skills in Data & AI > Machine Learning
ml-model-explainer
Explain ML model predictions using SHAP values, feature importance, and decision paths with visualizations.
tanstack-start
Build full-stack React applications with TanStack Start on Cloudflare Workers. Type-safe routing, server functions, SSR/streaming, and seamless D1/KV/R2 integration.Use when: building full-stack React apps, need SSR with Cloudflare Workers, want type-safe server functions, or migrating from Next.js.RC status - v1.0 stable pending. Monitor tanstack/router#5734 (memory leak) before production use.
figma-to-compose
Generate Android Jetpack Compose UI from Figma using Figma Desktop MCP (get_metadata, get_variable_defs, create_design_system_rules, get_design_context, get_screenshot). Automatically detect icon/vector nodes in Figma, obtain SVG/path data when available, and convert icons to Android VectorDrawable XML using Android MCP Toolkit (convert-svg-to-android-drawable). Use when the user shares a Figma link/node-id and asks to implement UI in Compose from Figma.
eval-review
Review LLM-generated diff classifications for the diffview eval system. Use when the user invokes this skill or pastes yanked case data from evalreview (containing "# Diff Classification Review" header). Evaluates whether classifications accurately help code reviewers, provides pass/fail verdict with detailed critique.
ha-dashboard
Configure Home Assistant Lovelace dashboards, cards, views, and themes. Use when working with dashboard YAML, card configuration, view layouts, custom cards, or frontend theming.
claude-code-excellence-audit
Audits Claude Code project setup and provides score with recommendations. Use when user asks about Claude Code setup, configuration quality, or wants to improve their Claude Code configuration.
quick-view
Generate minimal HTML pages to review Claude Code output in a browser. Use when terminal output is hard to read, when reviewing lists/tables/drafts, or when user says "show me", "make this reviewable", "quick view", or "open as webpage". Produces unstyled semantic HTML only.
layercake
Expert guide for Layer Cake, a headless Svelte visualization framework managing scales, dimensions, and data flow while supporting SVG, Canvas, HTML, and WebGL rendering contexts for responsive data visualizations.
htmlgraph
HtmlGraph workflow skill combining session tracking, orchestration, and parallel coordination. Activated automatically at session start. Enforces delegation patterns, manages multi-agent workflows, ensures proper activity attribution, and maintains feature awareness. Use when working with HtmlGraph projects, spawning parallel agents, or coordinating complex work.
seo-expert
Elite SEO expertise covering technical optimization, Core Web Vitals, E-E-A-T, topic clusters, entity-based SEO, semantic search, advanced link building, AI/ML integration, and sustainable ranking strategies for 2025. Use for comprehensive SEO audits, strategy development, content optimization, and technical implementation.
feature-engineering-kit
Auto-generate features with encodings, scaling, polynomial features, and interaction terms for ML pipelines.
set-current-spec
This skill should be used when switching between specs, after creating a new spec with "/spec-kit:specify", when the user says "switch to spec 002" or "work on feature X", or when resuming work on a different feature. Updates progress.yml with the current working specification.
rust-error-handling
Production error patterns with thiserror and anyhow, including error classification, HTTP/gRPC protocol mappings, context chains, retry logic, and testing. Use when designing error types for libraries or applications, mapping errors to API responses, or implementing retry mechanisms.
get-current-spec
This skill should be used when commands need to determine which spec is active, when the user mentions "spec 001", "work on feature X", or when checking current spec context. Resolves the current working specification through user input, progress.yml, or user selection.
file-converter
This skill handles file format conversions across documents (PDF, DOCX, Markdown, HTML, TXT), data files (JSON, CSV, YAML, XML, TOML), and images (PNG, JPG, WebP, SVG, GIF). Use when the user requests converting, transforming, or exporting files between formats. Generates conversion code dynamically based on the specific request.
testing
Provides comprehensive testing and TDD guidance. Use for writing tests before implementing new features, creating reproduction tests for bug fixes, running regression tests during refactoring, and checking test coverage during code reviews. Enforces AAA pattern and 100% coverage goal.
bac-presentation-generator
Transforms markdown files into brand-compliant BAC HTML presentations with professional styling, proper typography, and integrated branding. Supports manual browser-based PDF export.
baseline-check
Autonomously run quality checks (RuboCop, RSpec) to establish baseline or detect regressions. Triggers before starting development work, after completing changes, when checking code quality, or when explicitly requested. Compares current metrics against previous baseline to identify improvements or regressions in code quality and test coverage.
skill-builder
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.
browser
Expert knowledge for modern browser technologies including HTML5, CSS (Grid, Flexbox, Container Queries, Scroll-Driven Animations, Anchor Positioning), Progressive Web Apps (PWA, Service Workers, Web Push, File System Access), and Browser APIs (Canvas, Geolocation, Web Storage, Web Share, Drag and Drop). Use when working with web standards, client-side features, responsive design, offline capabilities, or native-like web experiences.