comfyui-llama-model-bridge SKILL.md skillA
This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.
comfyui-llama-model-bridge from yc883123/cat-chat is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add yc883123/cat-chat/comfyui-llama-model-bridge@git:20260822.7fbbe2cPins git:20260822.7fbbe2c in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- yc883123/cat-chat
- Path
skills/comfyui-llama-model-bridge/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260822.7fbbe2c, committed Aug 22, 2026
- First version recorded
- Aug 22, 2026
- Size
- 3,859 bytes
- Repository stars
- 36
- License
- none declared
让 ComfyUI 模型目录中的 GGUF、Safetensors 语言模型与视觉 mmproj 在 llama.cpp、Ollama、LM Studio 和 Naiba-chat 之间安全互通或完成兼容性判断。用于配置或排查共享模型目录、本地 API、硬链接导入、Modelfile、Safetensors 转换、视觉能力识别、模型迁移、重复占用磁盘、运行端选型与效率问题。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# ComfyUI 模型与 Llama 模型互通 让 llama.cpp、Ollama、LM Studio 和 Naiba-chat 尽量复用用户已有的 ComfyUI GGUF 或 Safetensors 语言模型，并正确处理视觉投影文件；同时把不能作为聊天模型的扩散权重明确标记出来。 ## 工作流程 1. 确认 ComfyUI 的模型根目录和用户希望接入的运行端。 2. 运行 `python scripts/inspect_model_compatibility.py --root <模型目录>` 做只读盘点。脚本会扫描 GGUF 和 Safetensors：区分 GGUF 主模型/mmproj，并读取 Safetensors header 判断语言模型、视觉语言模型、扩散模型或未知格式。需要机器可读结果时添加 `--json`。 3. 先检查文件名、大小、路径和运行实例，再决定接入方式；不要在未验证前删除、移动或覆盖模型。 4. 按运行端接入： - llama.cpp：直接指向共享目录中的主 GGUF；视觉模型同时传入匹配的 mmproj。 - LM Studio：优先使用 `lms import --hard-link` 建立索引，避免复制大型模型；确认只有预期实例在运行。 - Ollama：官方模型优先使用 `ollama pull`；手工导入 GGUF 时使用 Modelfile，并为视觉模型明确配置匹配的 `ADAPTER`。不要把 `OLLAMA_MODELS` 误解为散装 GGUF 扫描目录。 - Safetensors：不要改扩展名冒充 GGUF。先确认它是语言模型而不是 ComfyUI 扩散模型；llama.cpp/LM Studio 通常需要标准配置和 tokenizer 后转换为 GGUF，Ollama 只有在目标架构与权重格式明确受支持时才尝试导入。 5. 在 Naiba-chat 中配置对应的本地 API 地址和模型名。 6. 先查询运行端能力接口，再用真实小图片完成视觉验证；不要只根据模型名称或旁边存在 mmproj 判断视觉可用。 7. 检查模型是否重复占盘、是否误加载多个实例，以及上下文或并发设置是否导致性能异常。 8. 给出可回退、可验证的操作步骤；涉及删除、覆盖或大规模迁移前必须让用户确认精确目标。 需要同时查看运行端状态时，按实际启用的服务追加 `--llama-url`、`--ollama-url` 或 `--lmstudio-url`。脚本只查询接口，不会加载、导入或删除模型。 ## 运行端选择与实测依据 …
Read the whole file at its exact version.
How to install
mdr add yc883123/cat-chat/comfyui-llama-model-bridge@sha256:5c59cb6a2a21cbd1The line at the top of this page pins the label git:20260822.7fbbe2c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_l7ffs7fzrutza35b)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Aug 22, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260822.7fbbe2c latest | 2026-08-22 | 7fbbe2c | 3,859 B | A | view · diff |
| git:20260822.1a191ac | 2026-08-22 | 1a191ac | 3,045 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3859 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
yc883123/cat-chat · 36 stars · license none declared · pushed 2026-10-19 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_l7ffs7fzrutza35b GET https://markdownregistry.com/api/v1/resolve?ref=yc883123/cat-chat/comfyui-llama-model-bridge GET https://markdownregistry.com/api/v1/blob/5c59cb6a2a21cbd19248df46565b7816a8860f27892d450b8129db3556f4f822
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from yc883123/cat-chat
Every file in yc883123/cat-chat