Explorar skills

Externalize a project that has become a hairball into a visible map plus one concrete next action. Use when the user says they are "overwhelmed", "lost", "stuck", "drowning", "buried", "spinning", "don't know where to start", "can't see the shape", "too many pieces/things/tabs", "spending too many cycles", or asks to "map this project" / "zoom out" / "what's next". Sub-actions: map (default), next

Claude Code Skills

Integra as APIs do Yandex AI Studio no Laravel para geração de texto (Responses API), OCR de Visão e Embeddings. Suporta YandexGPT, Yandex OCR, embeddings vetoriais e chamada de função com modelos Yandex.

World-class AI prompt engineering skill for creating, refining, and enhancing prompts for any LLM task. Use this skill whenever the user wants to: write a new prompt from scratch, improve or refine an existing prompt, enhance a vague instruction into a structured prompt, debug why a prompt isn't working, convert a rough idea into a production-ready prompt, or asks anything related to "prompt engin

Generate comprehensive architecture documentation for complex code modules with Graphviz diagrams and examples. Use when user asks to "explain this code", "document the architecture", or wants to understand how a module/system works.

Hugging Face Transformers with PyTorch Lightning - LightningModule integration, distributed training (FSDP/DeepSpeed), PEFT (LoRA/QLoRA), data pipelines with HF Datasets, evaluation metrics, and common NLP tasks

Invoke for any request to create, file, open, or record a new GitHub issue. Trigger on:\n- Direct creation: 「issue 作って」「起票して」「issue 立て(といて)」「issue 化して」「issue 作れる?」\n- Record intent: 「issue に残したい/残しておいてほしい」「issue として残しておきたい」\n- Issue types: bug reports (with repro steps), feature requests, refactoring tasks, doc fixes, code-review findings to track later\n\nDo NOT trigger for viewing, listing, sear

Design a structured UX or product research study including method selection, protocol, stimuli, and success criteria. Use this skill when a team needs to go beyond ad-hoc interviews to a rigorous, repeatable research design.

Trigger on "plan my saves", "plan my week from Timeln", "cascade my last X days", "prioritize my recent saves", "what should I do with my saves", "turn my saves into actions", "run the framework cascade", "eisenhower my saves". Use when the user wants to convert recent Timeln captures into a ranked action plan. NOT for quick recall (use timeln-quickly) or open-ended exploration (use timeln-find).

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering

Create and modify APIs using WunderGraph Cosmo Connect. Covers gRPC plugin development (Go/TypeScript), standalone gRPC services, schema-to-proto workflows, CLI commands (wgc), local router setup, graph.yaml composition, field resolvers, batching, federation entities, and deployment. Use when building Cosmo Connect subgraphs, plugins, gRPC services, or setting up a local Cosmo Router.