Browse Skills

Paseo Help answers questions about the Paseo product and app, including setup, configuration, connectivity, providers, workspaces, updates, logs, and troubleshooting. Use it when a user inside Paseo asks how Paseo works, how to configure it, or why something is broken.

Contribute to Superset sets up a Superset open-source contribution, from fork and local dev setup to a merge-ready PR that follows the project's rules. Use when fixing a Superset bug or preparing a PR against superset-sh/superset.

DB Migrations creates Drizzle migrations on a fresh Neon branch when changing the packages/db schema. It generates migration files via drizzle-kit generate without applying them to shared or production databases.

Superset Doctor diagnoses and fixes Superset problems such as connection failures, offline hosts, terminals not attaching, and auth or update issues. Use it when something in Superset itself is broken or misbehaving, before filing feedback.

Superset Setup makes a repository Superset-ready by authoring .superset/config.json with setup, teardown, and run scripts so every new workspace boots configured, then verifies with a real workspace. Use it when setting up a project for Superset or fixing failing workspace setup.

Lambda Labs GPU Cloud reserves on-demand GPU instances for ML training and inference. Use it when you need dedicated GPUs, SSH access, persistent filesystems, or multi-node clusters.

Modal Serverless GPU runs GPU-backed ML workloads without managing servers. Use it to deploy models as APIs, run batch jobs, or scale inference and training on demand.

Ray Train orchestrates distributed machine learning training across single-GPU and multi-node clusters. Use it to scale PyTorch, TensorFlow, or HuggingFace training and run hyperparameter sweeps with fault tolerance.

SkyPilot Multi-Cloud Orchestration runs ML training, batch jobs, and serving across multiple clouds with automatic cost-based placement. Use it for spot instances, auto-recovery, distributed training, and avoiding vendor lock-in.

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

Provides concept mappings and implementation patterns for porting WordPress plugins, themes, or custom post types to EmDash CMS. Use when migrating or converting WordPress functionality to EmDash.

API Designer helps design REST and GraphQL APIs, creating OpenAPI specifications and planning API architecture including resource modeling, versioning, pagination, and error handling. Use it when you need to design or document an API contract.