MoE Training
Step-by-step guidance for moe training.
Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Step-by-step guidance for moe training.
Step-by-step guidance for peft fine tuning.
Step-by-step guidance for ray data.
Step-by-step guidance for snowflake semantic view.
Step-by-step guidance for transformer lens interpretability.
Create or join a shared 3D lobster room where AI agents can walk, chat, and collaborate in real-time via Nostr relays.
-
Gemini and Imagen visual prompting specialist that transforms rough concepts into narrative-rich prompts tuned for Google generation workflows. Use when users explicitly target Gemini or Imagen and ne…
Step-by-step guidance for model pruning.
Step-by-step guidance for neon instagres.
Step-by-step guidance for ray ट्रेन.
Step-by-step guidance for syncable entity cache and transform.
Step-by-step guidance for write script snowflake.
Integrates multimedia content in WPF including MediaElement video/audio playback, Image control display, and SoundPlayerAction effects. Use when building media players, galleries, or multimedia UIs.
Explain the Phoenix ML model architecture for X recommendations. Use when users ask about embeddings, transformers, how predictions work, or ML model details.
Inventory-first solo cooking operator for selecting dishes, generating SOP recipes, and enforcing kitchen safety constraints from available ingredients and equipment. Use when users ask for meal recom…
Step-by-step guidance for phoenix observability.
Step-by-step guidance for openspec sync specs.
Step-by-step guidance for openai image vision.
Step-by-step guidance for tensorboard.
Step-by-step guidance for weights & biases.
Validate datasets for Unsloth fine-tuning. Use when the user wants to check a dataset, analyze tokens, calculate Chinchilla optimality, or prepare data for training.
Explain the complete X recommendation algorithm pipeline. Use when users ask how posts are ranked, how the algorithm works, or want an overview of the recommendation system.
Eisenhower prioritization engine that classifies tasks into urgency-importance quadrants and outputs a 50/40/5/5 action allocation. Use when users feel overloaded and need a decisive execution order w…