Explorar skills

Compiles a comprehensive entry for a named entity by scanning ALL files, gathering every mention, and assembling a structured profile. Use when building out a full entry for any character, species, location, or concept, or when user says "compile", "flesh out", "full entry for", or "everything about [entity]". Does NOT extract multiple entities from one source — use /extracting-entities.

Setup development environment with modern Python tooling (uv/pixi), install dependencies, and configure development tools (ruff, ty, pytest). Use when setting up new ML projects, configuring environments, or installing dependencies.

Rasputin Omnitool é um pacote de habilidades OpenClaw com um loop de agente planejador/executor/revisor e 12 ferramentas (pesquisa, navegador, sandbox, multimídia). É um agente equivalente ao Manus, construído a partir de software de código aberto.

Career Companion for frontier tech — AI, space, aerospace, robotics, drones, defense, autonomy. Searches live job openings, tailors resumes and CVs, runs mock interviews, researches salaries. Use when user asks about jobs, careers, job search, job hunting, applying, hiring, resume or CV review, interview prep, salary, compensation, or mentions companies like SpaceX, Rocket Lab, OpenAI, Anthropic,

Weekly strategic intelligence. Dispatches 5 analyst agents (Market Scout, Competitor Tracker, Audience Analyst, Growth Analyst, Product Scout), reads the last 7 daily reports, and produces a strategy brief + recommendations for PM ingestion. Reads pulse-config.yaml from the nearest research directory. Run Monday mornings or whenever you need strategic direction. Trigger: "run weekly strategy", "we

Capture full-page screenshots of one or more websites. Handles scroll-triggered animations, lazy-loaded content, cookie banners, and bot-protected sites. Uses a tiered approach: Microlink API first, Chrome browser fallback for protected sites. Use when you need design references, competitive analysis screenshots, or visual audits. Invoke with /site-capture:capture.

Execute training runs with proper monitoring, checkpointing, and experiment tracking. Use when starting training, resuming training, debugging training issues, or setting up multi-GPU/distributed training with PyTorch Lightning and Hydra.

Evidence-backed market sizing for bootstrapped founders. Use when user runs `/market-size`, asks to "size the market", "how big is the market", "TAM SAM SOM", "market opportunity", "is the market big enough", or needs bottom-up market research with demand validation and revenue ceiling analysis.

Use when you need to investigate an unfamiliar library, framework, architectural question, or technical decision — spawns the researcher agent which explores the codebase and searches external sources in parallel. Invoke before making technology choices or when the right approach is unclear.

Export trained PyTorch models to various formats (ONNX, TorchScript, TensorRT) and upload to model registries (Hugging Face Hub, MLflow). Use when deploying models, sharing trained weights, or preparing for production inference.

Debug common ML training issues (NaN loss, OOM, slow training, convergence problems) and provide solutions. Use when training fails, metrics don't improve, or encountering errors like NaN loss, CUDA OOM, or slow convergence.

Comprehensive guide for PyTorch Lightning - LightningModule, Trainer, distributed training, PyTorch 2.0 torch.compile integration, Lightning Fabric, and production best practices