菜单
[开发者向] 帮 contributor / 开发者从源码 dev 模式跑通 MiniCPM-Desk-Pet。 普通用户应直接下载 dmg 安装包，跟着 Onboarding 引导走，不应触发本 skill。 Use when a developer clones the repo and wants to run it from source, or asks to "部署桌宠 (从源码)", "跑起来 MiniCPM dev 模式", or hits errors during go.sh / npm start / uv sync.
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/OpenBMB/MiniCPM-Desk-Pet --skill deploy-minicpm-pet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
帮用户给 MiniCPM-Desk-Pet 桌宠做一个自定义人格 / 皮肤：微调一个 LoRA、转成 GGUF、 在 App 里上传并切换。覆盖"训练 → 转 GGUF → 上传 → 启用"的完整链路。 Use when the user wants a custom desktop-pet persona, asks "做一个自己的桌宠人格 / 角色", "训练 / 上传自定义 LoRA", "把我的 LoRA 用到桌宠上", "convert LoRA to GGUF for the pet", or hits errors uploading a .gguf adapter in Settings.
一键部署 MiniCPM 桌宠体验环境，后端采用 OpenVINO 推理引擎（Deploy MiniCPM Desk Pet with OpenVINO backend）. 使用本 Skill 可部署一个完整的桌宠体验环境，在 Intel AIPC 上本地运行，无需云端服务。 部署完成后，用户直接通过桌宠 UI 界面进行对话交互。 Use this skill when the user wants to deploy/set up/run the MiniCPM desk pet with OpenVINO backend, or build a local AI pet experience environment on Intel hardware. Trigger on: 部署桌宠/体验环境/搭建环境/本地推理/OpenVINO后端/桌宠环境/deploy pet/setup environment/run desk pet/ 英特尔/intel/AIPC/本地/离线/offline/MiniCPM/OpenVINO/桌宠. This is a DEPLOYMENT skill — it sets up the environment and launches the pet. After deployment, the user interacts with the pet directly through its UI (not via this script).
基于 SOC 职业分类
| name | deploy-minicpm-pet |
| description | [开发者向] 帮 contributor / 开发者从源码 dev 模式跑通 MiniCPM-Desk-Pet。 普通用户应直接下载 dmg 安装包，跟着 Onboarding 引导走，不应触发本 skill。 Use when a developer clones the repo and wants to run it from source, or asks to "部署桌宠 (从源码)", "跑起来 MiniCPM dev 模式", or hits errors during go.sh / npm start / uv sync. |
重要：这个 Skill 只针对开发者。普通最终用户走的是 下载 dmg → Onboarding 流程，不应使用本 Skill。如果对方只是想"用一下这个应用"，请引导他们去 Releases 下载 dmg。
v0.8 起推理后端从 PyTorch / transformers 切换到 llama.cpp。本 Skill 已按 v0.9 平铺布局更新；sidecar 结构与构建方式以
minicpm-sidecar/README.md为准。
This skill walks the agent through deploying the MiniCPM-Desk-Pet project on a colleague's machine from source. The project has 3 moving parts that need to come up in the right order: llama-server (compiled from vendored llama.cpp), the FastAPI gateway, and the Electron clawd-on-desk app.
Before doing anything, check what state the colleague's machine is in:
# Are we in the repo root?
ls README.md go.sh clawd-on-desk minicpm-sidecar 2>&1 | head -5
# What's already installed?
command -v node && node -v # need 18+
command -v uv && uv --version # go.sh installs if missing
command -v cmake && cmake --version # go.sh installs if missing (needed for llama-server)
If the user isn't in the repo root, cd to wherever they cloned it first.
The model weight (~600 MB – 1 GB GGUF) is NOT in the repo. Without it, the gateway boots in "waiting for model" mode and Onboarding prompts the user to download one.
Check first:
ls -la models/*.gguf 2>&1
If missing, three ways to obtain it:
Already have a .gguf locally (most likely if the colleague worked on MiniCPM before):
mkdir -p models
ln -s /absolute/path/to/your/minicpm5-0.9b.Q4_K_M.gguf models/
Let Onboarding download — just run ./go.sh and follow the wizard's "Download model" step (~2–5 minutes from Hugging Face).
From a teammate's machine (scp):
scp teammate@host:/path/to/minicpm5-0.9b.Q4_K_M.gguf ./models/
The gateway accepts both a .gguf file path and a directory containing .gguf files.
./go.sh
go.sh is idempotent. It will:
uv if missing (curl install.sh)cmake if missing (brew / apt)llama.cpp + cmake build llama-server (~5–10 min)uv sync in minicpm-sidecar/ (a few dozen MB: fastapi / uvicorn / httpx / huggingface_hub — no torch)npm install in clawd-on-desk/ (~1 minute, first time only)MINICPM_SIDECAR_DIR + MINICPM_PYTHON + MINICPM_MODEL_DIRnpm start to launch ElectronIf only the dependency-install part is needed (no launch yet):
./go.sh setup
Environment-check only (no install, no launch):
./go.sh doctor
Force a rebuild of llama-server (after pulling a new vendor pin):
./go.sh build-llama
Once Electron starts, you should see:
[sidecar] lines, eventually llama-server ready + gateway listening on :18765Quick sanity check (in another terminal):
curl -s http://127.0.0.1:18765/api/health | python3 -m json.tool
Expected ok: true plus reported backend (metal on Apple Silicon, cuda, or cpu).
Then click the pet (or ⌘⇧M), type "你好" — pet should think and reply within a few seconds.
Cannot find module 'electron' / npm start fails immediatelycd clawd-on-desk && npm install
ModuleNotFoundError: fastapi (or uvicorn / httpx)cd minicpm-sidecar && uv sync
llama-server: command not found / bin/<triple>/llama-server missingThe vendored llama.cpp didn't build. Re-run:
./go.sh build-llama
If cmake errors out, check cmake --version (need 3.20+) and re-install via brew / apt.
model not found / No GGUF files in MODEL_DIRThe gateway couldn't locate a .gguf. Drop one into models/ or override:
MINICPM_MODEL_DIR=/abs/path/to/dir ./go.sh start
# or point directly at one file via Onboarding's "选本地模型"
Probably the sidecar didn't come up. In the clawd-on-desk terminal, look for [sidecar] lines.
minicpm-sidecar/.venv/bin/python exists (cd minicpm-sidecar && uv sync)llama-server crashed during model load: check memory (Q4_K_M needs ~1 GB RAM resident; F16 needs ~2 GB)port 18765 in use (or 23333)Old sidecar / clawd HTTP server didn't die cleanly:
lsof -ti:18765 | xargs -r kill -9 # sidecar
lsof -ti:23333 | xargs -r kill -9 # clawd HTTP server
This is supposed to happen on first launch. Re-trigger via Settings → 🐾 MiniCPM, or restart the pet. Manual fallback (Claude as example):
cd clawd-on-desk
node -e "require('./hooks/install.js').installAll({silent:false})"
If a teammate already has an older checkout and wants the latest:
git pull
./go.sh setup # re-syncs deps + rebuilds llama-server if vendor pin changed
./go.sh start
uv sync, npm install, and cmake are idempotent — no-op if nothing changed.
The deploy is done when:
curl -s http://127.0.0.1:18765/api/health returns ok:trueSettings → 🐾 MiniCPM shows current model + adapter statusIf any of these fail, walk back through the corresponding "Common failure" section above.