菜单
Profile Kokoro and related Core ML packages to establish actual CPU, GPU, and Neural Engine placement, latency, and silent fallback behavior. Use for device compute plans, scheduling claims, package-shape changes, warmed timing, or hardware comparisons.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/mattmireles/kokoro-coreml --skill coreml-profile命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Applies David Ogilvy–style copy discipline to reader-facing text in kokoro-coreml: README and guides, bakeoff and performance narratives, CLI and script output, error messages, integration notes, and docstrings that read as product copy. Use when the user names **Ogilvy**, **copy**, **copywriting**, **marketing** language, **user-facing** strings, **empty states**, onboarding, or wants persuasive, specific prose grounded in facts. Do not use for implementation-only work with no wording decisions, pure internals with no voice requirement, or layout-only tasks.
Clarifies what “ship” means for kokoro-coreml: there is no Cloudflare-style multi-worker deploy script. Use for tagging releases, pushing the branch, coordinating with the macOS app repo, or verifying exports before handoff. Before treating a revision as releasable, run the repo’s primary checks (see git-commit / audit). Do not use when the user only wants local experiments with no remote or release intent.
Adopts the Ilya Sutskever persona and judgment for on-device ML work in kokoro-coreml: PyTorch tracing, Core ML conversion, MIL/op compatibility, ANE/GPU/CPU scheduling, precision and parity validation, and bakeoffs vs reference PyTorch. Use when the user asks for that stance, mentions **Ilya**, **Sutskever**, **Bitter Lesson**, **scale vs hand-engineering**, or wants architecture or prioritization help on export/performance—not when the task is a narrow workflow already covered by **audit**, **debug**, or **execute-plan** unless they want persona-layer reasoning on top. Do not use for work with no ML or Core ML angle (generic docs-only or unrelated-repo tasks).
基于 SOC 职业分类
正在显示 SKILL.md
| name | coreml-profile |
| description | Profile Kokoro and related Core ML packages to establish actual CPU, GPU, and Neural Engine placement, latency, and silent fallback behavior. Use for device compute plans, scheduling claims, package-shape changes, warmed timing, or hardware comparisons. |
Bind every measurement to the package hash, model/configuration, hardware, OS, Core ML compute-unit request, input shape/duration, warmup policy, and timing boundary. Inspect a device compute plan or physical trace when available; never infer Neural Engine placement from a requested compute unit or speed alone.
Start with scripts/dump_device_compute_plan.py,
scripts/inspect_coreml_compute_plan.m, and
README/Guides/apple-silicon/CoreML-Compute-Unit-Scheduling-guide.md.
Keep synthesis, phonemization, I/O, and individual model-stage timing separate.
