clasen

Creates high-clarity product and technical specifications by interrogating requirements before planning. Use when the user asks to "crear especificaciones", "write a spec", "define requirements", "hacer el plan", "scope a project", or shares an idea that is still vague. This skill asks exhaustive follow-up questions first and only proposes a structured plan after unknowns are surfaced.

Orchestrates structured task execution with planning, progress tracking, self-improvement, and verification gates. Use at the start of any coding session, when given a non-trivial task (3+ steps or architectural decisions), when corrected by the user, when fixing bugs, or when the user mentions "plan", "todo", "track progress", "verify", "lessons learned", "fix this bug", or "task management". Applies to all coding workflows where structured methodology improves quality and reduces mistakes.

Work with BlockNote, a block-based rich text editor for React. Use when the user mentions "blocknote", "BlockNote editor", "block-based editor", "insertBlocks", "updateBlock", "removeBlocks", "replaceBlocks", "editor.document", "InlineContent", "StyledText", "nestBlock", "unnestBlock", "addStyles", "toggleStyles", "removeStyles", "createLink", "getTextCursorPosition", "setTextCursorPosition", "getSelection", "setSelection", "forEachBlock", "useCreateBlockNote", "BlockNoteView", "paragraph block", "heading block", "bulletListItem", "PartialBlock", or asks how to manipulate blocks, style text, insert content, or read document structure in BlockNote.

Process images with the Sharp library for Node.js — resize, convert formats, composite, apply effects, and manage metadata. Use when the user mentions "sharp", "image processing", "resize image", "convert image", "image format", "jpeg quality", "png compression", "webp", "avif", "image thumbnail", "crop image", "watermark", "overlay image", "blur image", "sharpen image", "image metadata", "EXIF", "ICC profile", "colour space", "alpha channel", "animated gif", "image pipeline", or asks how to manipulate images in Node.js/TypeScript. Also use for "sharp constructor", "sharp cache", "sharp concurrency", "toFile", "toBuffer", or any Sharp API method.

Manage domains through the Namecheap API — register, renew, transfer, configure DNS, and manage nameservers. Use when the user mentions "namecheap", "register domain", "domain DNS", "nameservers", "domain transfer", "renew domain", "check domain availability", "DNS records", "email forwarding", "WHOIS", or any domain registrar operations. Also use when managing A records, CNAME, MX records, or TXT records for Namecheap domains.

Interactive guide for creating new agent skills from scratch. Use this skill when the user wants to create a skill, write a SKILL.md, package a skill folder, or convert an existing workflow into a reusable skill. Also trigger when the user mentions "create skill", "new skill", "SKILL.md", "teach the agent", or wants to standardize a repeatable process into a skill.

Instructions for using the GPTrans Node.js library for AI-powered translations with smart batching, caching, context-aware translations, refinement, and image translation. Use when adding i18n/localization to a Node.js project, translating text or images between languages, or managing multilingual content.

Instructions for using the ModelMix Node.js library to interact with multiple AI LLM providers through a unified interface. Use when integrating AI models (OpenAI, Anthropic, Google, Groq, Perplexity, Grok, etc.), chaining models with fallback, getting structured JSON from LLMs, adding MCP tools, streaming responses, or managing multi-provider AI workflows in Node.js.

Instructions for working with DeepBase, a multi-driver persistence library for Node.js. Use when the user needs to store or retrieve data, add persistence to a project, set up a key-value store, work with SQLite/MongoDB/Redis/JSON storage, migrate data between backends, handle multi-driver failover, or says things like "save data", "persist data", "I need a database", "store user data", "set up storage", or "integrate DeepBase". Do NOT use for full ORM/relational query needs or raw SQL work.

Instructions for using the ModelMix Node.js library to interact with multiple AI LLM providers through a unified interface. Use when writing code that calls AI models (OpenAI, Anthropic, Google, Groq, Perplexity, Grok, Moonshot, MiniMax, Fireworks, Together, Lambda, Cerebras, OpenRouter, Ollama, LM Studio), chaining models with fallback, getting structured JSON from LLMs, adding MCP tools, streaming responses, managing multi-provider AI workflows, round-robin load balancing, or rate limiting API requests in Node.js. Also use when the user mentions "modelmix", "ModelMix", asks to "call an LLM", "query a model", "add AI to my app", or wants to integrate any supported provider.

Transcribe audio to text with WhisperMix in Node.js (OpenAI, Groq, Whisper local or Parakeet local).

Guidance for working on the SfxMix audio processing library. Use when modifying SfxMix APIs, FFmpeg processing steps, demo audio scripts, chunk splitting, silence detection, or README examples for this project.

Virtual hosting for multiple HTTPS sites with Let's Encrypt SSL automation. Each domain gets isolated VirtualServer instance, supports Express/Socket.IO/custom handlers, static sites (index.html only, no Node), local HTTP dev mode with CRC32-based ports, automatic www redirects, and SNI certificate management. Static site logic is modular (lib/static-site-handler.js, lib/resolve-site-app.js).

Set up and manage environment-specific configuration in Node.js projects using the Configre library. Use when the user wants to add configuration management, create environment configs, set up hostname-based settings, or mentions "configre", "config files", "environment config", or "per-host settings".

Instructions for generating speech audio files using the VoiceMix Node.js library