Daily backup: Update TOOLS.md (Ollama rules), mark foot doctor task done, add memory files
This commit is contained in:
43
TOOLS.md
43
TOOLS.md
@@ -2,39 +2,20 @@
|
||||
|
||||
Skills define _how_ tools work. This file is for _your_ specifics — the stuff that's unique to your setup.
|
||||
|
||||
## What Goes Here
|
||||
### Ollama 本地模型使用规则
|
||||
|
||||
Things like:
|
||||
**通用规则**
|
||||
- 只用已下载的模型,绝不自动下载新模型
|
||||
- 需要未下载的模型时,先询问用户
|
||||
|
||||
- Camera names and locations
|
||||
- SSH hosts and aliases
|
||||
- Preferred voices for TTS
|
||||
- Speaker/room names
|
||||
- Device nicknames
|
||||
- Anything environment-specific
|
||||
**默认模型:kamekichi128/qwen3-4b-instruct-2507**
|
||||
- 用途:邮件摘要、轻量分析
|
||||
- 速度:快(~5秒)
|
||||
- 无需额外参数,直接调用即可
|
||||
|
||||
## Examples
|
||||
|
||||
```markdown
|
||||
### Cameras
|
||||
|
||||
- living-room → Main area, 180° wide angle
|
||||
- front-door → Entrance, motion-triggered
|
||||
|
||||
### SSH
|
||||
|
||||
- home-server → 192.168.1.100, user: admin
|
||||
|
||||
### TTS
|
||||
|
||||
- Preferred voice: "Nova" (warm, slightly British)
|
||||
- Default speaker: Kitchen HomePod
|
||||
```
|
||||
|
||||
## Why Separate?
|
||||
|
||||
Skills are shared. Your setup is yours. Keeping them apart means you can update skills without losing your notes, and share skills without leaking your infrastructure.
|
||||
|
||||
---
|
||||
**备选模型**
|
||||
- `ministral-3:3b` - 速度快,格式清晰
|
||||
- `gemma3:4b` - 适中速度
|
||||
- `qwen3:4b` - 较慢,仅备用
|
||||
|
||||
Add whatever helps you do your job. This is your cheat sheet.
|
||||
|
||||
Reference in New Issue
Block a user