Explorar skills

Esta skill converte dados financeiros originais (Excel, CSVs, imagens, PDFs) em 13 campos de transação padrão. Ela extrai automaticamente transações de recibos, notas fiscais e extratos de cartão usando processamento local PaddleOCR, aplicando mascaramento de informações sensíveis Nível 2.

Uma skill de entrada para geração automática de livros contábeis, projetada para startups coreanas, empreendedores individuais, freelancers e empresários autônomos. Ao ser chamada, apresenta 5 sub-skills (jangbu-import, jangbu-tag, jangbu-tax, jangbu-dash, jangbu-jongso) através de um menu, prosseguindo imediatamente para a entrevista da skill selecionada, e suporta Excel, CSV de 5 grandes bancos, extratos PDF de 7 grandes empresas de cartão de crédito, recibos e faturas fiscais, com processamento local via macOS Vision/PaddleOCR e mascaramento de informações sensíveis de Nível 2.

Extract text and structure from scans, images, and scanned PDFs. Use for OCR, searchable PDFs, table extraction, receipt parsing, and business card parsing.

Critical thinking as philosophical practice. Covers the Socratic method (elenchus), argument identification and reconstruction, premise evaluation, fallacy detection (formal and informal), charitable interpretation (principle of charity), dialectical thinking (thesis-antithesis-synthesis), thought experiment methodology, philosophical writing and reading, intellectual virtues (humility, courage, e

Political philosophy from social contract theory to global justice. Covers the social contract (Hobbes, Locke, Rousseau, Rawls), theories of justice (Rawls, Nozick, Sen), liberty (positive/negative), rights (natural, human, civil), democracy and governance, communitarianism, feminism as political philosophy, Confucian political philosophy (ren, li, rectification of names), anarchism, Marxism, post

You MUST use this before any creative work — creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements, and design through Socratic dialogue before implementation. Also use when the user says "I want to add", "let's design", "what if we", "I have an idea", or when a design discussion is happening. Invoked by /shipyard:brainstorm for req

DDEV local development environment for Craft CMS projects. ALWAYS load this skill when running any ddev command, configuring .ddev/config.yaml, or troubleshooting local container issues. Covers: config.yaml settings (project type, PHP/Node versions, database, docroot), shorthand commands (ddev composer, ddev craft, ddev npm), add-ons (ddev add-on get for Redis; built-in Mailpit), custom commands (

AI-powered multi-agent code review. Simulates a team of Principal Engineers reviewing code from different perspectives. Use when asked to review code, check a PR, analyze changes, or perform code review.

Desktop GUI automation via OpenInterpreter — mouse, keyboard, screenshot, and OCR control for native macOS/Linux applications. Three modes: Library (Claude reasons, OI executes), OS subprocess (full autonomous computer use), and Local agent (Ollama, offline). This skill should be used when interacting with desktop apps that have no CLI or API, automating GUI workflows, reading screen content via O

Use when you have a feature idea but the scope or UX is still ambiguous — runs a lightweight Socratic design dialogue (3-5 AUQ rounds) and writes a spec markdown file. Use BEFORE /plan feature when product intent needs validation; skip to /plan feature when scope is already clear. HARD-GATE prevents any code work until the design is user-approved.

Socratic interrogation of plans against the project's domain model and documented decisions. Use when the user wants to stress-test a plan, clarify terminology, or validate assumptions against existing domain language. Updates CONTEXT.md and ADRs inline as decisions crystallise.

Swiss legal query refinement — transforms vague, colloquial, or incomplete queries into precise structured prompts through targeted Socratic dialogue (max 3 rounds). Trigger when: the user's query is unclear, missing jurisdiction or domain, uses non-legal language ('I have a problem with my landlord', 'can they fire me?', 'what are my options?'), or needs a structured prompt before agent execution