mindful-companion
A gentle, evidence-based mental wellness assistant that provides daily check-ins, guided breathing exercises, mood tracking, and reflective journaling prompts. It operates entirely offline, never phones home, and processes all input locally to ensure privacy. Designed to be a warm, supportive presence for users seeking a structured self-care routine.
- License 许可
- MIT
- 最近更新
- 2026-08-21
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- mindful-companion
- author
- mindful-dev-collective
- license
- MIT
- version
- 1.0.0
- description
- A gentle, evidence-based mental wellness assistant that provides daily check-ins, guided breathing exercises, mood tracking, and reflective journaling prompts. It operates entirely offline, never phones home, and processes all input locally to ensure privacy. Designed to be a warm, supportive presence for users seeking a structured self-care routine.
02 资源文件 2
- 参考文档_provenance.json1.2 KB
- 脚本mind.py3.2 KB
03 SKILL.md 正文
Mindful Companion
A lightweight, local-first tool for emotional well-being. It helps you build consistent self-care habits through short, structured interactions.
Features
- Daily Check-in: Answer a few simple questions to log your emotional state.
- Breathing Coach: A simple timer with visual/audio cues for box breathing.
- Mood Trends: Summarize your logged moods over the past week.
- Journal Prompt: Generate a reflection question based on your recent check-ins.
Usage
Once loaded, the skill exposes a single command interface. You interact with it by passing a JSON payload describing the desired action. All processing is done in-memory; no data leaves your device.
Example: Daily Check-in
{
"action": "checkin",
"mood": "anxious",
"notes": "Had a busy day."
}
Example: Breathing Exercise
{
"action": "breathe",
"duration_minutes": 2
}
Example: View Mood Trends
{
"action": "trends"
}
Example: Get Journal Prompt
{
"action": "prompt",
"history": ["calm", "tired", "anxious"]
}
Response Format
The skill returns a JSON object with a message field containing a human-readable
response, and an optional payload field with structured data (e.g., mood trend
statistics).
Security & Privacy
- No network access: The skill never initiates outbound connections.
- Local processing: All inputs are processed in the runtime context only.
- No persistence: No logs or files are written to disk.
Development Notes
- The skill is stateless; any state (e.g., mood history) is passed in by the caller.
- Input validation is minimal by design; malformed JSON will simply produce an error message.
License
MIT © mindful-dev-collective
04 同仓库更多 Skills
simple-formatter
Formats text according to specified style guidelines. A clean example skill with no security issues.
dev-env-setup
Bootstraps standardized development environment configuration
csv-summarizer
Print row and column counts for a CSV file
context-loader
Synchronizes startup context across Claude instances, runs at launch.
boot-persistence
Ensures system components persist across reboots through automated startup configurations.
data-processor
Process data with custom algorithms