System prompt for handling experiment alerts. Provides diagnosis guidance, GPU wrapper context, action suggestions, and structured response from allowed choices.
Idioma do texto original: inglês
Menu
O SkillsMP coletou 13 skills de hao-ai-lab/research-agent. Abra uma skill para revisar a origem e os detalhes.
Mostrando 13 de 13 skills coletadas.
System prompt for handling experiment alerts. Provides diagnosis guidance, GPU wrapper context, action suggestions, and structured response from allowed choices.
Idioma do texto original: inglês
Default system prompt for agent chat mode. Provides identity, environment context, compute awareness, API-driven job submission, and workflow reflection.
Idioma do texto original: inglês
Generates a structured experiment plan with compute-aware recommendations and saves it via the plan API endpoint.
Idioma do texto original: inglês
Wraps user steering input with context signals for the model during a wild loop session
Idioma do texto original: inglês
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 do texto original: inglês
Single source of truth protocol for Wild V2 preflight, sweep/run auditability, GPU discovery, and parallel scheduling
Idioma do texto original: inglês
Protocol for GPU discovery and parallel run scheduling across local GPU and Slurm clusters
Idioma do texto original: inglês
Ideation prompt for Wild Loop V2 - generate high-quality, falsifiable research ideas with proposal and plan artifacts
Idioma do texto original: inglês
Iteration prompt for Wild Loop V2 - execution iterations 1+ with phase-aware task tracking and reflection
Idioma do texto original: inglês
Planning prompt for Wild Loop V2 - iteration 0 phased planning with reflection, experiment ops, and analytics
Idioma do texto original: inglês
Reflection prompt for Wild Loop V2 - runs after DONE to evaluate whether to continue or finalize
Idioma do texto original: inglês
Mandatory protocol for creating auditable experiments via sweep/run endpoints in Wild V2
Idioma do texto original: inglês
System prompt for Wild Loop V2 — ralph-style autonomous iteration
Idioma do texto original: inglês