System prompt for handling experiment alerts. Provides diagnosis guidance, GPU wrapper context, action suggestions, and structured response from allowed choices.
Idioma del texto original: inglés
Menú
SkillsMP ha recopilado 13 skills de hao-ai-lab/research-agent. Abre una skill para revisar su origen y sus detalles.
Mostrando 13 de 13 skills recopiladas.
System prompt for handling experiment alerts. Provides diagnosis guidance, GPU wrapper context, action suggestions, and structured response from allowed choices.
Idioma del texto original: inglés
Default system prompt for agent chat mode. Provides identity, environment context, compute awareness, API-driven job submission, and workflow reflection.
Idioma del texto original: inglés
Generates a structured experiment plan with compute-aware recommendations and saves it via the plan API endpoint.
Idioma del texto original: inglés
Wraps user steering input with context signals for the model during a wild loop session
Idioma del texto original: inglés
Ports new models into FastVideo with strict numerical alignment to official implementations. Use when adding a FastVideo model/pipeline, porting an official or Diffusers checkpoint, or debugging parity/alignment.
Idioma del texto original: inglés
Single source of truth protocol for Wild V2 preflight, sweep/run auditability, GPU discovery, and parallel scheduling
Idioma del texto original: inglés
Protocol for GPU discovery and parallel run scheduling across local GPU and Slurm clusters
Idioma del texto original: inglés
Ideation prompt for Wild Loop V2 - generate high-quality, falsifiable research ideas with proposal and plan artifacts
Idioma del texto original: inglés
Iteration prompt for Wild Loop V2 - execution iterations 1+ with phase-aware task tracking and reflection
Idioma del texto original: inglés
Planning prompt for Wild Loop V2 - iteration 0 phased planning with reflection, experiment ops, and analytics
Idioma del texto original: inglés
Reflection prompt for Wild Loop V2 - runs after DONE to evaluate whether to continue or finalize
Idioma del texto original: inglés
Mandatory protocol for creating auditable experiments via sweep/run endpoints in Wild V2
Idioma del texto original: inglés
System prompt for Wild Loop V2 — ralph-style autonomous iteration
Idioma del texto original: inglés