Data & AI

Deploy and manage AI permit research agents in E2B cloud sandboxes. Use when deploying permit research agents, running distributed AI research, scaling cloud-based compliance analysis, or building SaaS permit platforms. Supports 21 specialized agents with 92% grounding quality.

Use when capturing screenshots, automating browser interactions, or scraping web content. Covers Playwright Python API for page navigation, screenshots, element selection, form filling, and waiting strategies.

Generates offer packet documents that summarize compensation recommendations and candidate-specific details.

Comprehensive code review specialist providing security analysis, performance optimization, maintainability assessment, and best practice recommendations across multiple programming languages

Helps construct minimal, context-efficient task packages when delegating work to dev agents. Ensures agents receive only relevant information.

Generate images using OpenAI's GPT Image model. Use for creating images from text prompts. Keywords: image, generate, openai, gpt-image, dalle, picture, art, create.

RAN coverage analysis with signal strength mapping, cognitive consciousness, and intelligent optimization for comprehensive network coverage management. Use when analyzing signal coverage, optimizing antenna parameters, implementing coverage mapping, or enabling intelligent coverage management in 5G networks.

Use to validate process documentation. Apply TDD to skill writing: RED (run without skill, document failures) → GREEN (write skill) → REFACTOR (close loopholes). Test under pressure: time constraints, sunk cost, exhaustion, authority.

Android端末ファームウェアのセキュリティ分析。Security Patch Level (SPL) チェック、Android/Qualcomm/Samsung Security Bulletin照合、カーネルCVE確認、ファームウェアイメージ解析。Triggers on: Android firmware analysis, SPL check, security patch level, Android security bulletin, Qualcomm bulletin, Samsung security, kernel CVE, firmware security, device security assessment.

FoundationDB key patterns, query helpers, and tenant isolation for the T2 project. Use when working with FDB persistence, multi-tenant data access, or session management.

Write consistent, maintainable CSS following the project's methodology (Tailwind utility classes) while minimizing custom CSS and adhering to design system tokens. Use this skill when writing or editing CSS files, Tailwind classes in React components (.tsx, .jsx files), when implementing design system colors/spacing/typography, when using Tailwind utility classes, when deciding between framework utilities vs. custom CSS, when optimizing CSS for production with tree-shaking, when configuring Tailwind theme extensions, or when maintaining design consistency across the application.

Use when working with Deno edge functions, LLM integration, or embedding generation. Load for Deno.serve patterns, Zod request validation, OpenRouter LLM calls, and error handling. Covers function structure, CORS, and the call-llm/generate-embedding patterns.

Build interactive CLI questionnaires with validation, conditional logic, parameter mapping, and review capabilities using the question-and-answer library

Create distinctive, production-grade frontend interfaces with high design quality. Specialized in Svelte/SvelteKit applications with full-stack capabilities. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

User feedback patterns for interactions - loading states, success/error messages,form validation, empty states. Ensures users understand system state and next steps.Use when implementing user-facing state changes and interactions:- Form submissions with validation feedback, success/error messages- Async operations needing loading indicators (API calls, data fetching)- Error handling flows with clear recovery paths and retry options- Empty state designs with helpful messaging (no data, no results)- User mentions "form", "loading", "error", "validation", "async", "API call"Keywords: loading, success, error, form, validation, async, feedback, toast, empty stateFocus on WHEN to show feedback, WHAT type (toast/inline/modal), HOW LONG (timing).

Implements Schema.org structured data for AndesRC articles. Adds ExercisePlan, HowTo, and FAQPage markup. Optimizes meta titles and descriptions. Use before publication.

Extract Case/Support Ticket data using the async pipeline with denormalized medallion architecture. Use this skill to extract case data into Bronze layer with proper linkages to Company and Person entities.

Skill cho việc design, implement, và maintain tests hiệu quả.

Full-featured AI chatbot with Next.js 15, Auth.js, Drizzle ORM, and multi-model support.

Building reusable React state machine skills with XState v5 and the actor model. This skill should be used when implementing explicit state management for complex UI flows, multi-step forms, media players, modals with animations, or any component where impossible states should be unrepresentable.