LLM 與 Agent

Generate Midjourney V7 image prompts for website sections. Analyzes page components, extracts aspect ratios from CSS, outputs prompts with SEO filenames. Use after completing page (skills 02-06). Triggers on "generate image prompts", "midjourney prompts", "create images for page".

Write unit tests for JavaScript files using Node.js native test runner. Use when creating new scripts, fixing bugs, or when prompted about missing tests.

Use when auditing Claude Code plugin security or implementing secure practices - security guidelines with credential handling, hook safety, and MCP security for November 2025 specifications

Master authentication and authorization patterns including OAuth 2.0, OpenID Connect, JWT tokens, refresh tokens, role-based access control (RBAC), claims-based authorization, and secure token storage for .NET applications with OpenIddict and ABP Framework.

Local search/indexing CLI (BM25 + vectors + rerank) with MCP mode.

Automatic memory capture and retrieval for Claude Recall MCP - ensures you never repeat yourself

Use when brainstorming completes and user selects research-first option - manages parallel research subagents (up to 4) across codebase, library docs, web, and GitHub sources, synthesizing findings and auto-saving to memory before planning

Comprehensive evaluation and improvement system for Claude Skills across all ~/.claude/ locations

Complete TDD workflow for implementing business logic (use cases) and API endpoints that make tests pass. Covers Zod safeParse validation, async/await patterns, Next.js API routes, service orchestration, and Clean Architecture compliance.

Critical Android code review for Payoo Android app. Focuses on high-impact issues - naming conventions, memory leaks, UIState patterns, business logic placement, lifecycle management, and MVI/MVVM pattern violations. Use when reviewing Kotlin files, pull requests, or checking ViewModels, Activities, Fragments, UseCases, and Repositories.

Add SQLite database storage with teaching examples

Guide for implementing Grafana Tempo - a high-scale distributed tracing backend for OpenTelemetry traces. Use when configuring Tempo deployments, setting up storage backends (S3, Azure Blob, GCS), writing TraceQL queries, deploying via Helm, understanding trace structure, or troubleshooting Tempo issues on Kubernetes.

Programmatic agent definitions for the Claude Agent SDK in TypeScript and Python. Use when creating agents for SDK-based applications rather than filesystem-based Claude Code.

Game audio design patterns for creating sound effects and UI audio. Use when designing sounds for games, writing AI audio prompts (ElevenLabs, etc.), creating feedback sounds, or specifying audio for abilities/UI. Includes psychological principles from Kind Games, volume hierarchy, frequency masking prevention, and prompt engineering for AI audio generation.

Guide for creating custom slash commands for Claude Code. Use this skill when you need to extend Claude Code's capabilities with custom workflows, plugin commands, or reusable prompts defined in Markdown.

Context engineering and prompt optimization standards based on Anthropic best practices.Covers clarity, structure, progressive discovery, and signal-to-noise optimization.USE WHEN user says 'prompt engineering', 'context engineering', 'optimize prompt','write better prompts', 'agent design', 'prompt structure', 'do prompt engineering','run prompt optimization', 'help with prompting', 'improve this prompt'.

Search technical documentation using executable scripts to detect query type, fetch from llms.txt sources (context7.com), and analyze results. Use when user needs: (1) Topic-specific documentation (features/components/concepts), (2) Library/framework documentation, (3) GitHub repository analysis, (4) Documentation discovery with automated agent distribution strategy

OpenCode CLI - open source AI coding agent with TUI, IDE integration, LSP support, and MCP servers.

This skill should be used when an agent is assigned to write a section of technical documentation. Provides guidance on breaking down large tasks, using doc-coauthoring workflow, and coordinating with VibeKanban task management. Use when task description mentions "write section", "document this component", or "expand documentation".

Comprehensive guide to localStorage patterns for the Plataforma B2B de treinamento técnico corporativo educational platform. This skill covers schema design, error handling strategies, quota management, and synchronization patterns essential for building resilient web applications with client-side persistence.Learn how to handle common localStorage errors (QuotaExceededError, SecurityError, DOMException), implement graceful degradation, manage storage quotas (5-10MB browser limits, 50KB per note), and sync localStorage with React state. The skill emphasizes defensive programming, user-friendly error messages, and fallback strategies.Real-world examples are taken directly from the project codebase, including CNotesView, BashNotesView, and auto-save patterns used across 5 learning systems. Each pattern is demonstrated with production code showing how localStorage is used to persist 227 educational modules' progress and user notes.Key topics include try/catch patterns for all localStorage operations, Quota