LLM & Agents

Autonomous multi-agent code evolution system for optimization problems. Use when solving complex optimization problems (packing, geometry, scheduling, search) through evolutionary approaches with multiple independent AI agents. Multi-start hybrid heuristic+SLSQP methods significantly outperform single approaches. Triggers include genetic algorithms, evolutionary optimization, multi-agent problem solving, parameter tuning at scale, AlphaEvolve-style research, or evolving code solutions across generations.

Skill especializada em SEO (Search Engine Optimization), AEO (Answer Engine Optimization), GEO (Generative Engine Optimization) e AI Optimization Files (llms.txt, ai.txt, TDMRep). Use esta skill quando o usuário precisar de orientações sobre otimização para mecanismos de busca tradicionais, motores de resposta AI (ChatGPT, Perplexity, Claude), mecanismos generativos, ou implementação de arquivos de otimização para IA. Inclui estratégias técnicas de SEO, Core Web Vitals, E-E-A-T, schema markup, voice search, video SEO, link building, llms.txt, ai.txt, TDM Reservation Protocol e todas as melhores práticas atualizadas para 2025.

Real-time breaking news monitor using Grounding API. Continuously scans for market-moving events, classifies urgency (CRITICAL/HIGH/MEDIUM), and triggers immediate alerts to War Room and Notification Agent. Optimized for speed and recall.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

This skill should be used when the user asks to "triage issue", "classify ticket", "route jira", "analyze priority", "categorize issue", "determine complexity", "route to agents", or needs guidance on classifying, prioritizing, and routing Jira issues to appropriate agents and workflows.

Multi-agent coordination CLI for codebases. Use when orchestrating parallel agents, claiming tasks, detecting symbol conflicts, or notifying stakeholders of breaking changes. Invoke when user mentions coordination, parallel agents, multiple agents, task claiming, or conflict detection.

Runtime security validation including secret scanning, PII detection, prompt injection defense, audit logging, and output validation for AI agents. Use when validating user input, scanning for secrets, detecting PII, preventing data exfiltration, or implementing security guardrails.

Examples and patterns for integrating FastMCP Cloud servers with Claude Agent SDK using HTTP transport

Natural language search through Claude Code session history. Search for previous prompts, conversations, topics, file modifications, and context from past sessions. Useful for finding earlier work and understanding project continuity.

Retrieves and inspects chunks from specific PDF documents in Qdrant vector database. Use when user wants to view, inspect, debug, or examine chunks from a particular file, check chunk content, or investigate chunk indexing.

Download audio and video from thousands of websites using yt-dlp. Feature-rich command-line tool supporting format selection, subtitle extraction, playlist handling, metadata embedding, and post-processing. This skill is triggered when the user says things like "download this video", "download from YouTube", "extract audio from video", "download this playlist", "get the mp3 from this video", "download subtitles", or "save this video locally".

Use when user mentions 'climpt' or 'climpt-agent', or gives project-specific instructions where general knowledge is insufficient. Climpt provides pre-configured prompts tailored to the project's workflow.

End-to-end feature development workflow with brainstorming, TDD, implementation, testing, and documentation. Use when adding new features, implementing user stories, or building new capabilities. Enforces test-first development, encourages design exploration, and ensures proper documentation.

Build AI applications with the Anthropic TypeScript SDK. Use when creating Claude integrations, building agents, implementing tool use, streaming responses, or working with the @anthropic-ai/sdk package.

Use when building NuxtHub v0.10.4 applications - provides database (Drizzle ORM with sqlite/postgresql/mysql), KV storage, blob storage, and cache APIs. Covers configuration, schema definition, migrations, multi-cloud deployment (Cloudflare, Vercel), and the new hub:db, hub:kv, hub:blob virtual module imports.

This skill guides connecting MCP servers to Claude Code plugins for external service integration. Use when configuring MCP servers, setting up authentication, or integrating external tools.

Implement images into page sections. Converts from /public/raw/[page]/ to WebP with responsive variants, replaces CDN placeholders with Next.js Image component. Use after midjourney-prompts skill. Triggers on "implement images", "add images to page", "replace placeholder images".

Designs RESTful and GraphQL APIs with clear contracts and documentation

記事の公開準備を支援するスキル。完成した記事のタイトル、絵文字、タグを最適化し、公開タイミングを提案します。また、フロントマターの公開設定を適切に更新します。記事のレビューが完了し、公開準備が整った時に使用してください。

Guides creation of high-quality Agent Skills with domain expertise, anti-pattern detection, and progressive disclosure best practices. Activate on keywords: create skill, review skill, skill quality, skill best practices, skill anti-patterns, improve skill, skill audit. NOT for general coding advice, slash commands, MCP development, or non-skill Claude Code features.