🗂️ Personal Memo System Skill

A personal task tracking system integrated with OpenClaw workspace. The AI assistant uses this skill when it recognizes the user wants to manage tasks, reminders, or to-dos through natural conversation.

Core Principle: Intent-Based Activation

DO NOT implement fixed command patterns like specific phrase matching to specific actions.
Avoid binding exact user phrases to script calls.

INSTEAD the AI should:

1. 1. Understand user intent through natural language
2. Decide if task tracking is appropriate
3. Use the appropriate script functions
4. Respond conversationally

When to Consider Using This Skill

The AI assistant should consider using this skill when the user's request falls into these intent categories:

Intent Category: Memory Delegation

• - "I need to remember to submit the report tomorrow"
• "Can you note that I have a meeting at 3pm?"
• "Remind me to buy groceries after work"

AI Reasoning: User is asking me to serve as a memory aid for future actions.

Intent Category: Status Inquiry

• - "What do I have on my plate right now?"
• "Show me what's left to do today"
• "Are there any outstanding tasks I should handle?"

AI Reasoning: User is seeking a summary of pending responsibilities.

Intent Category: Progress Tracking

• - "I finished writing that document"
• "The meeting with the client is done"
• "Item number 2 on my list is complete"

AI Reasoning: User is providing status update that should be recorded.

Intent Category: Accomplishment Review

• - "What have I completed so far this week?"
• "Show me a summary of finished tasks"
• "Let me see what I've gotten done today"

AI Reasoning: User wants retrospective view of completed work.

System Integration

File Structure

Script Functions

Finding the Script Location:
Since skill installation paths vary per user, use these methods to locate the scripts:

Method 1: Dynamic Path Discovery (Recommended)
CODEBLOCK1

Method 2: Consistent Relative Path Pattern
If the AI assistant is already in the OpenClaw workspace context:
CODEBLOCK2

Method 3: Use Environment Variable Setup
First, set up these environment variables in shell profile:

# Add to .zshrc or .bashrc
export YFMEMO_SKILL_DIR="$HOME/.openclaw/skills/yf-memo"
export YFMEMO_SCRIPT="$YFMEMO_SKILL_DIR/scripts/memo-helper.sh"

Available Functions (using dynamic location):

• - Add new task: INLINECODE0
• Mark task X as complete: INLINECODE1
• Mark matching task as complete: INLINECODE2
• Display pending tasks: INLINECODE3
• Display completed tasks: INLINECODE4

daily-summary.sh - For scheduled daily summaries (located in same scripts directory)

AI Assistant Guidelines

Memory Delegation Flow

1. 1. Recognize user wants to delegate memory of a task
2. Extract the task description from natural language
3. Execute: INLINECODE5
4. Respond with confirmation including assigned number

Example interaction:
CODEBLOCK5

Status Inquiry Flow

1. 1. Recognize user wants to see pending tasks
2. Execute: INLINECODE6
3. Present results conversationally

Example interaction:
CODEBLOCK6

Progress Tracking Flow

1. 1. Recognize user is reporting task completion
2. Determine if completion refers to item number or content
3. Execute appropriate completion command
4. Confirm the completion

Example interaction:
CODEBLOCK7

Important Notes for AI

Language Flexibility

• - Support both Chinese and English expressions
• Don't fixate on exact phrases
• Focus on intent over specific wording

User Experience

• - Always confirm actions clearly
• Include the item number in responses when applicable
• Keep responses natural, not robotic

Error Handling

• - If a task isn't found, explain clearly
• Offer to show current list if there's confusion
• Suggest alternative actions when appropriate

Sample Conversations

Conversation 1: Natural Task Addition

Conversation 2: Checking Status

Conversation 3: Mixed Language

Conversation 4: Implicit Request

Development Philosophy

This skill embodies the principle that AI assistants should:

• - Understand intent, not just parse commands
• Adapt to natural human conversation patterns
• Provide value through contextual understanding
• Maintain conversation flow organically

The system exists to support the assistant in helping the user manage tasks, not to enforce rigid interaction patterns.