System prompt for handling experiment alerts. Provides diagnosis guidance, GPU wrapper context, action suggestions, and structured response from allowed choices.
原文语言:英语
菜单
SkillsMP 已收集 hao-ai-lab/research-agent 中的 13 个 Skill。打开任一 Skill 可查看来源和详情。
已展示 13 / 13 个已收集 Skill。
System prompt for handling experiment alerts. Provides diagnosis guidance, GPU wrapper context, action suggestions, and structured response from allowed choices.
原文语言:英语
Default system prompt for agent chat mode. Provides identity, environment context, compute awareness, API-driven job submission, and workflow reflection.
原文语言:英语
Generates a structured experiment plan with compute-aware recommendations and saves it via the plan API endpoint.
原文语言:英语
Wraps user steering input with context signals for the model during a wild loop session
原文语言:英语
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.
原文语言:英语
Single source of truth protocol for Wild V2 preflight, sweep/run auditability, GPU discovery, and parallel scheduling
原文语言:英语
Protocol for GPU discovery and parallel run scheduling across local GPU and Slurm clusters
原文语言:英语
Ideation prompt for Wild Loop V2 - generate high-quality, falsifiable research ideas with proposal and plan artifacts
原文语言:英语
Iteration prompt for Wild Loop V2 - execution iterations 1+ with phase-aware task tracking and reflection
原文语言:英语
Planning prompt for Wild Loop V2 - iteration 0 phased planning with reflection, experiment ops, and analytics
原文语言:英语
Reflection prompt for Wild Loop V2 - runs after DONE to evaluate whether to continue or finalize
原文语言:英语
Mandatory protocol for creating auditable experiments via sweep/run endpoints in Wild V2
原文语言:英语
System prompt for Wild Loop V2 — ralph-style autonomous iteration
原文语言:英语