Complete mandatory cleanup before presenting changes for user approval in AWAITING_USER_APPROVAL state

Vision and multimodal capabilities for Claude including image analysis, PDF processing, and document understanding. Activate for image input, base64 encoding, multiple images, and visual analysis.

Apply chronicle event effects to world state. Use when events need to modify entities (battles change force strength, treaties change relationships, deaths remove agents). This is the core simulation engine.

Rastreia fluxos documentais completos no Odoo, executa auditorias financeiras e gerencia conciliacoes bancarias. USAR QUANDO: - Rastrear NF de compra/venda: "rastreie NF 12345", "fluxo da nota 54321" - Rastrear pedido de compra: "rastreie PO00789", "fluxo do pedido de compra" - Rastrear pedido de venda: "rastreie VCD123", "fluxo do VFB456" - Rastrear por parceiro: "documentos do Atacadao", "fluxo do fornecedor Vale Sul" - Rastrear por CNPJ: "rastreie 18467441000123" - Rastrear por chave NF-e: "rastreie 3525..." - Ver titulos e conciliacoes: "pagamentos da NF 12345", "titulos do PO00789" - Verificar devolucoes: "devolucao da NF 54321", "nota de credito" - Auditoria de faturas de compra: "auditoria faturas novembro", "faturas fornecedores" - Auditoria de extrato bancario: "extrato bancario 2024", "conciliacao bancaria" - Mapeamento de vinculos: "extratos sem vinculo", "titulos soltos", "faturas sem pagamento" - Vincular extrato com fatura via Excel: "processar planilha de vinculacao", "conciliar via Excel" NA

Manages authentication flow for MutuaPIX (Laravel Sanctum + Next.js), handles mock mode security, and validates environment configurations

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

Discovers, validates, and integrates Model Context Protocol (MCP) tools into Claude Code skills. Searches MCP catalogs, scores candidates, generates tool configurations, and optionally sets up Docker runtimes. Use when creating skills that need external MCP tool integration.

Expert on Shelby Protocol architecture, erasure coding, placement groups, read/write procedures, Clay Codes, chunking, storage providers, RPC servers, and decentralized storage system design on Aptos blockchain. Triggers on keywords Shelby Protocol, erasure coding, Clay Codes, placement groups, Shelby architecture, storage provider, blob storage, chunking, Shelby whitepaper.

Analyzes polyglot codebases with multiple programming languages using PMAT (Pragmatic AI Labs MCP Agent Toolkit). Use this skill when: - Working with projects containing multiple programming languages - Assessing cross-language integration patterns and quality - Understanding language distribution and architectural boundaries - Comparing quality metrics across language ecosystems - Identifying language-specific best practices violations Supports 25+ languages including Rust, Python, TypeScript, JavaScript, Go, C++, Java, Ruby, PHP, Swift, Kotlin, C, C#, Scala, Haskell, Elixir, Clojure, Dart, Lua, R, and more. Provides unified quality assessment across heterogeneous codebases.

Use this skill when creating new skills via forced conceptual collision of existing patterns. Duct-tapes jank-builder to super-collider for autopoietic meta-skill generation.

Systematic methodology for constructing compact (<150 lines), expressive, Claude Code-integrated subagent prompts using lambda contracts and symbolic logic. Use when creating new specialized subagents for Claude Code with agent composition, MCP tool integration, or skill references. Validated with phase-planner-executor (V_instance=0.895).

Manages practice rules. Use when user states a preference or approach, or asks to add/modify rules for coding, architecture, tooling, or best practices.

Execute agentic coding tools directly via bash commands with output capture. Use this when the user requests to run AI agents (Gemini, Claude Code, etc.) and get their results directly.

Create or augment skills and documentation. Use when writing new skills, updating existing skills, or modifying project documentation like AGENTS.md.

Create codebase area context skills for rapid navigation. MUST BE USED for creating area context skills. Handles ONE-TIME auto-detection with Serena, template-based generation, and manual maintenance. Use when creating new area contexts or regenerating existing ones, or when user mentions "create context skill", "generate area context", "map codebase area", skill generation, codebase navigation, area mapping, or template-based skill creation.

Understand and navigate the DevPrep AI 7-folder architecture. Use this skill when asked about code organization, where to place new features, what modules exist, or when starting development tasks that need architecture context. Auto-triggers on keywords like "where should", "add module", "architecture", "structure", "organize", "place code", "what modules".

This skill should be used after productive sessions to extract learnings and route them to appropriate Reusable Intelligence Infrastructure (RII) components. Use when corrections were made, format drift was fixed, new patterns emerged, or the user explicitly asks to "harvest learnings" or "capture session intelligence". Transforms one-time fixes into permanent organizational knowledge by implementing updates across multiple files.

Server-Sent Events (SSE) streaming for Claude API with support for text, tool use, and extended thinking. Activate for real-time responses, stream handling, and progressive output.

Token-efficient codebase navigation through intelligent symbol loading and querying. Use this skill when implementing new features (find existing patterns), exploring codebase structure, searching for components/functions/types, or understanding architectural layers. Reduces token usage by 60-95% compared to loading full files. Layer split enables 50-80% additional backend efficiency.

Create comprehensive Claude Code plugins with proper structure, commands, agents, hooks, and marketplace configuration. Use when the user wants to build a new Claude Code plugin or asks how to create/structure a plugin.