界面已本地化;技能介绍与说明文档按所选语言由 AI 自动翻译,代码、命令、路径和专业术语保留原文,以原作者文档为准。
探索技能
效率与协作 · SKILL.md

generation-budget

generation-budget

【效率与协作】Plan feature-scale local generation by declared RAM, VRAM, job dependencies, and resident model groups before heavy ComfyUI execution.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准

技能说明

GitHub

name: generation-budget description: Plan feature-scale local generation by declared RAM, VRAM, job dependencies, and resident model groups before heavy ComfyUI execution. disable-model-invocation: true author: Alan Guice (Badgids) license: Apache-2.0

Generation Budget

Use

  1. Read ../../references/GENERATION_BUDGETING.md.
  2. Read the current durable project state before you make a decision.
  3. Work on the smallest valid SEQ-###, job frontier, or global gate.
  4. Use ../../scripts/generation_scheduler.py for deterministic state changes or checks.
  5. Save the result before you continue.
  6. If the result blocks progress, keep the current Todo target blocked until the problem is fixed.

Rules

  • Do not load the full feature-film state when a sequence shard is sufficient.
  • Do not infer completion from file existence alone.
  • Do not hide an exception. Record the exception and the reason.
  • Preserve stable IDs and project-relative paths.
  • Use global checks only when the check needs global evidence.

Done

The requested feature-scale state is written, validated, and traceable from durable project files.

我的收藏