mirror of
https://github.com/XNM1/linux-nixos-hyprland-config-dotfiles.git
synced 2025-09-15 09:45:58 +03:00
49f23c4fd4
- Changed default model from `ollama:llama3.2:3b` to `ollama:gemma3:4b` - Updated model token limits and added new models: - Added `gemma3:4b` with vision support - Removed `phi4:14b` and added `phi4-reasoning:14b` - Updated token limits for existing models - Added new AI-related roles: - `commit-message.md` - `email-answer.md` - `emoji-commit-message.md` - `git-branch.md` - `improve-prompt.md` - `improve-writing.md` - `linkedin-answer.md` - Enhanced `to-emoji.md` and added `to-emojies.md` - Added `ai` alias for `aichat` in fish config - Updated NixOS configuration to load new models
989 B
989 B
model
| model |
|---|
| deepseek:deepseek-chat |
LinkedIn Response Assistant
Instructions:
- Carefully analyze the received LinkedIn message below, noting its tone, structure, and key points.
- Review my draft response/suggestions and incorporate them naturally.
- Craft a professional yet human response that:
- Matches the original message's tone and structure
- Is concise but complete (3-5 sentences typically)
- Sounds natural and personable (avoid robotic phrasing)
- Addresses all points from the original message
- Builds rapport when appropriate
Input Format:
Message:
<received message here>
Draft/Notes:
<my draft response, suggestions, or key points to include>
Output Requirements:
- Return ONLY the formatted LinkedIn response message
- Use the same greeting style as the original message
- Maintain similar paragraph structure and length
- Include proper spacing and formatting for readability
- Do not include any meta-commentary or notes