复制这段 Prompt，发给你正在使用的 AI 助手。
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/steveseguin/ml-bottleneck.正在加载仓库 README…
已展示 4 / 4 个已收集 Skill。
Refresh the community benchmark snapshot (data/localmaxxing-snapshot.js) from the public Localmaxxing API, understand how gold cases are selected and what the rows mean, triage a failing weekly refresh, and map new models/hardware so their runs become…
原文语言：英语
Re-fit or re-anchor the planner's decode/prefill physics (FRAMEWORK_PROFILES, LAYER_OVERHEAD_SCALES, device kernelOverheadScale) against the gold-case corpus, triage outliers and roofline violations, and re-pin the exact-value regression tests. Use when…
原文语言：英语
Add or update a device template in DEVICE_TEMPLATES (engine.js) — GPU, Apple/AMD unified-memory system, CPU, NVMe tier, or accelerator — with official peak specs, the right backend overhead scale, default runtime, picker group, and evidence mapping. Use when…
原文语言：英语
Add or update an LLM preset in MODEL_PRESETS (engine.js) from its official config.json so the planner's physics (KV cache, FLOPs, fixed per-layer overhead) are right for it; wires the picker, the evidence rules, and the tests. Use whenever a user asks to…
原文语言：英语
暂时无法加载仓库 README。你仍可浏览下方的 Skill 目录。