Loading...
Loading...
Found 1,564 Skills
Navigation links between rooms — the edges of the memory palace
Structured multi-perspective deliberation through adversarial dialogue
Plain text formatting that's readable raw AND rendered
A skill is documentation that learned to do things.
Many turns in one call. Instant communication. No round-trips.
Rules persuade. Structure IS argument. Design consciously.
Principios para escribir codigo de calidad. Usa cuando el usuario diga "buenas practicas", "best practices", "coding guidelines", "code quality", "clean code", "principios de codigo", "refactorizar con principios", "refactor with principles", o quiera seguir patrones de calidad.
Parliamentary procedure as forcing function for genuine deliberation
I mine pixels for atoms. Reality is just compressed resources.
Spatial organization of knowledge in navigable directories
Search, install, and publish skills. Use search_skills tool for discovery + auto-install. Manual publish via gateway.
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.