Menü
SkillsMP hat 13 Skills aus hao-ai-lab/research-agent gesammelt. Öffne einen Skill, um Quelle und Details zu prüfen.
Es werden 13 von 13 gesammelten Skills angezeigt.
System prompt for handling experiment alerts. Provides diagnosis guidance, GPU wrapper context, action suggestions, and structured response from allowed choices.
Quellsprache: Englisch
Default system prompt for agent chat mode. Provides identity, environment context, compute awareness, API-driven job submission, and workflow reflection.
Quellsprache: Englisch
Generates a structured experiment plan with compute-aware recommendations and saves it via the plan API endpoint.
Quellsprache: Englisch
Wraps user steering input with context signals for the model during a wild loop session
Quellsprache: Englisch
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.
Quellsprache: Englisch
Single source of truth protocol for Wild V2 preflight, sweep/run auditability, GPU discovery, and parallel scheduling
Quellsprache: Englisch
Protocol for GPU discovery and parallel run scheduling across local GPU and Slurm clusters
Quellsprache: Englisch
Ideation prompt for Wild Loop V2 - generate high-quality, falsifiable research ideas with proposal and plan artifacts
Quellsprache: Englisch
Iteration prompt for Wild Loop V2 - execution iterations 1+ with phase-aware task tracking and reflection
Quellsprache: Englisch
Planning prompt for Wild Loop V2 - iteration 0 phased planning with reflection, experiment ops, and analytics
Quellsprache: Englisch
Reflection prompt for Wild Loop V2 - runs after DONE to evaluate whether to continue or finalize
Quellsprache: Englisch
Mandatory protocol for creating auditable experiments via sweep/run endpoints in Wild V2
Quellsprache: Englisch
System prompt for Wild Loop V2 — ralph-style autonomous iteration
Quellsprache: Englisch