executing-plans
executing-plans
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
スキルを探す
生産性・共同作業 · SKILL.md
optimization_model_lru
optimization_model_lruEnable ModelManager LRU without CPU offload.
Independent GitHub snapshot · Automated classification · Original documentation governs
スキルの説明
GitHubname: optimization_model_lru description: > Enable ModelManager LRU without CPU offload. homepage: https://github.com/steliosot/comfy-agent metadata.clawdbot.os: ["darwin", "linux"] metadata.clawdbot.requires.bins: ["python3"] metadata.clawdbot.requires.env: [] metadata.clawdbot.files: ["skill.py", "skill.yaml", "scripts/*"] metadata.clawdbot.tags: ["comfyui", "skill", "ops", "optimization"] metadata.clawdbot.category: "ops" metadata.clawdbot.input_type: "application/json" metadata.clawdbot.output_type: "application/json" metadata.clawdbot.output_can_feed_into: [] metadata.clawdbot.accepts_input_from: [] metadata.clawdbot.priority: 70
optimization_model_lru
Enable ModelManager LRU without CPU offload.
This skill wraps configure_optimizations with fixed mode: model_lru.