菜单
Use this skill when the user wants to list, inspect, or report MLX-VLM-supported models available in the local Hugging Face cache directory, including models shown by the server /v1/models endpoint, cache-dir overrides, JSON output, or issue-ready cached model lists.
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/Blaizzy/mlx-vlm --skill hf-cache-models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。
正在显示 SKILL.md
| name | hf-cache-models |
| description | Use this skill when the user wants to list, inspect, or report MLX-VLM-supported models available in the local Hugging Face cache directory, including models shown by the server /v1/models endpoint, cache-dir overrides, JSON output, or issue-ready cached model lists. |
Use this workflow to list locally cached Hugging Face models that MLX-VLM should treat as server-visible models.
Match the server /v1/models cache filter:
modelmain revision exists in the cacheconfig.json existstokenizer_config.json existsmodel.safetensors.index.json exists or at least one *.safetensors file existsThis is a cache/file-presence check that mirrors the server (mlx_vlm/server/app.py). It does not load the model or prove generation works. Pass --check-arch to additionally require that mlx-vlm ships an architecture for the model_type — this narrows the list from server-visible to probably loadable (folder-name match; it does not resolve MODEL_REMAPPING aliases, so use it as a strong hint, not proof).
Use the bundled script instead of rewriting cache-scanning logic:
uv run python skills/skills/hf-cache-models/scripts/list_supported_hf_cache_models.py
JSON output:
uv run python skills/skills/hf-cache-models/scripts/list_supported_hf_cache_models.py --json
Only models mlx-vlm can actually load (architecture present, not just files present):
uv run python skills/skills/hf-cache-models/scripts/list_supported_hf_cache_models.py --check-arch
Custom cache directory:
uv run python skills/skills/hf-cache-models/scripts/list_supported_hf_cache_models.py \
--cache-dir /path/to/huggingface/cache
When reporting the result, include:
curl http://127.0.0.1:8080/v1/modelsFor server-visible verification, start the server and compare with:
curl http://127.0.0.1:8080/v1/models
If this becomes part of a bug report, switch to Skill("mlx-vlm-skills:reproducible-github-issues").
Use this skill when the user wants to add or port a new model architecture to MLX-VLM — mapping a Hugging Face model_type to a new file under mlx_vlm/models, writing the ModelConfig, matching layer/weight names, reusing a similar existing model, adding a test class, and validating the port. Covers vision-language, language, audio, and diffusion model ports.
Use this skill when the user wants to benchmark an MLX-VLM change and present the numbers in a PR — fork-vs-main A/B comparisons, isolated-module micro-benchmarks, median-of-N timing with warmup, peak-memory reporting, correctness checks, parameter sweeps, and self-contained reproducible bench scripts to paste into a PR description.
Use this skill when the user wants to run or debug MLX-VLM inference from the command line, including uv run mlx_vlm.generate, image/audio/video inputs, local model paths, Hugging Face model IDs, deterministic repro commands, and CLI errors around processors, prompts, model loading, or missing weights.
基于 SOC 职业分类
