開發

Cloodle design system tokens for colors, typography, spacing, and components. Use when styling Cloodle interfaces, creating CSS, or implementing consistent visual design across the platform.

Use when working on the Miden compiler (`cargo miden`, `cargo-miden`) and its integration test suite, debugging compiler issues or failing tests, or implementing compiler changes and you need to inspect intermediate artifacts. Covers `MIDENC_EMIT` (the environment-variable equivalent of `--emit`) for emitting WAT/HIR/MASM (and related outputs), plus `MIDENC_EMIT_MACRO_EXPAND` for dumping macro-expanded Rust via `cargo expand` for integration-test fixtures.

This skill should be used when the user asks about "code review best practices", "how to review code", "review methodology", "code review framework", "impact prioritization", "root cause analysis", or needs guidance on systematic code review approaches and output templates.

Execute implementation plan by dispatching fresh subagent for each task, with code review between tasks

Slidev presentation for teaching Python with interactive code execution.

Manages application state with Zustand including stores, selectors, actions, and middleware. Use when managing client-side state, creating global stores, persisting state, or replacing Redux/Context.

Recharts for React data visualization. Covers line, bar, area, pie charts with responsive containers and customization. Triggers on recharts, chart, LineChart, BarChart.

Comprehensive PostgreSQL configuration and usage analysis for Rails applications. Use when Claude Code needs to analyze a Rails codebase for database performance issues, optimization opportunities, or best practice violations. Detects N+1 queries, missing indexes, suboptimal database configurations, anti-patterns, and provides actionable recommendations. Ideal for performance audits, optimization tasks, or when users ask to "analyze the database", "check for N+1 queries", "optimize PostgreSQL", "review database performance", or "suggest database improvements".

Comprehensive expertise for working with Microsoft's GenAIScript framework - a JavaScript/TypeScript-based system for building automatable LLM prompts and AI workflows. Use when creating, debugging, or optimizing GenAIScript scripts, implementing prompts-as-code, working with tools and agents, processing files (PDF, CSV, DOCX), defining schemas, or building AI automation workflows.

Master data science and machine learning with Python, TensorFlow, PyTorch, and MLOps. Learn to build predictive models, deep learning systems, and production ML pipelines.

Build cross-platform desktop applications with Rust using Tauri framework and native GUI alternatives

Configure FastAPI for Vercel deployment.Bundled Resources: Includes 'vercel.json', CORSMiddleware, Python logging, Pydantic models, and personalization endpoints.

Build MCP (Model Context Protocol) servers for CasareRPA integrations using Python FastMCP. Covers server structure, tool design, error handling, and RPA-specific patterns. See references/ for detailed guides. Use when: creating MCP servers, tool design, error handling, RPA-specific patterns, FastMCP, Context logging, lifespan hooks.

Diagnose and solve common beginner programming mistakes in Flask or Sinatra development with detailed explanations

Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes

Integrates Stripe payments including checkout, subscriptions, webhooks, and customer management. Use when accepting payments, setting up subscriptions, handling webhooks, or managing billing.

Discover and analyze lien positions from AcclaimWeb and RealTDM to detect HOA foreclosures and senior mortgage survival

Master user research methodologies, customer interviews, persona development, and journey mapping. Understand customer problems deeply before building.

Perform critical code review with automated fix suggestions. Use when reviewing code changes, pull requests, specific files, or branch diffs. Triggers on requests like "review this code", "critical review", "code review for PR

Build 3D visualizations using Three.js and React Three Fiber. Use when implementing 3D components, debugging rendering issues, optimizing performance, or creating interactive visualization features.