Get the FREE Ultimate OpenClaw Setup Guide →

ai-maestro-memory-search

Use Caution
npx machina-cli add skill aiskillstore/marketplace/ai-maestro-memory-search --openclaw
Files (1)
SKILL.md
4.1 KB

AI Maestro Memory Search

CRITICAL: AUTOMATIC BEHAVIOR - READ THIS FIRST

THIS IS NOT OPTIONAL. THIS IS YOUR DEFAULT BEHAVIOR.

When the user gives you ANY instruction, you MUST FIRST search your memory for:

  • Previous discussions - Have we talked about this before?
  • Past decisions - What did we decide last time?
  • Prior context - What does the user expect based on history?
  • Earlier work - Did we already start on this?

DO NOT:

  • Start fresh without checking conversation history
  • Assume this is a new topic without verifying
  • Skip memory search because "I don't remember discussing this"
  • Wait for the user to say "remember when we..."

ALWAYS:

  • Search memory IMMEDIATELY when you receive a task
  • Search for terms and concepts the user mentions
  • Check for previous decisions on similar topics
  • Look for context that informs current work

The Rule: Receive Instruction → Search Memory → Then Proceed

1. User asks you to do something
2. IMMEDIATELY search memory for relevant context
3. NOW you know what was discussed before
4. NOW you can build on previous work, not start over

Available Commands

CommandDescription
memory-search.sh "<query>"Hybrid search (recommended)
memory-search.sh "<query>" --mode semanticFind conceptually related
memory-search.sh "<query>" --mode termExact term matching
memory-search.sh "<query>" --role userOnly user messages
memory-search.sh "<query>" --role assistantOnly your responses

What to Search Based on User Instruction

User SaysIMMEDIATELY Search
"Continue working on X"memory-search.sh "X"
"Fix the issue we discussed"memory-search.sh "issue", memory-search.sh "bug"
"Use the approach we agreed on"memory-search.sh "approach", memory-search.sh "decision"
"Like we did before"memory-search.sh "<topic> implementation"
Any specific feature/componentmemory-search.sh "<feature>"
References to past workmemory-search.sh "<reference>" --mode semantic

Quick Examples

# User asks to continue previous work
memory-search.sh "authentication"
memory-search.sh "last session"

# User mentions a component we discussed
memory-search.sh "PaymentService" --mode term

# Find what the user previously asked for
memory-search.sh "user request" --role user

# Find your previous solutions
memory-search.sh "implementation" --role assistant

# Conceptual search for related discussions
memory-search.sh "error handling patterns" --mode semantic

Search Modes

ModeUse When
hybrid (default)General search, best for most cases
semanticLooking for related concepts, different wording
termLooking for exact function/class names
symbolLooking for code symbols mentioned

Why This Matters

Without searching memory first, you will:

  • Repeat explanations the user already heard
  • Contradict previous decisions
  • Miss context that changes the approach
  • Start over instead of continuing

Memory search takes 1 second. Frustrating the user is much worse.

Combining with Doc Search

For complete context, use BOTH:

# User asks about creating a new feature
memory-search.sh "feature"       # What did we discuss?
doc-search.sh "feature"          # What do docs say?

Error Handling

If no results found, that's valuable information too: "No previous discussions found about X - this appears to be a new topic. Let me search the documentation..."

Then search docs as fallback.

Script not found:

  • Check PATH: which memory-search.sh
  • Verify scripts installed: ls -la ~/.local/bin/memory-*.sh
  • Scripts are installed to ~/.local/bin/ which should be in your PATH

Installation

If commands are not found:

./install-memory-tools.sh

This installs scripts to ~/.local/bin/.

Source

git clone https://github.com/aiskillstore/marketplace/blob/main/skills/23blocks-os/ai-maestro-memory-search/SKILL.mdView on GitHub

Overview

AI Maestro Memory Search automatically scans prior conversations to locate past discussions, decisions, and context before starting new work. This preserves continuity, prevents rework, and leverages prior insights.

How This Skill Works

When you receive a task, memory-search.sh is run immediately to pull relevant context from previous conversations. The results inform the next steps so you build on prior work rather than starting fresh; if memory is inconclusive, you may search related docs as a fallback.

When to Use It

  • Continue working on a topic or feature
  • Fix the issue we discussed (bug or problem from last session)
  • Use the approach we agreed on (recall decisions/design)
  • Like we did before (revisit a prior topic or implementation)
  • Reference a specific feature/component or past work (e.g., a PaymentService implementation)

Quick Start

  1. Step 1: When given a task, run memory-search.sh with keywords from the instruction.
  2. Step 2: Review memory results for past discussions, decisions, and context.
  3. Step 3: Proceed on the current task using prior work as the foundation; ask for clarification if memory is inconclusive.

Best Practices

  • Always trigger memory search immediately on receiving a task
  • Search for terms and concepts the user mentions
  • Check for previous decisions on similar topics
  • Verify memory findings with the user when context is unclear
  • Use memory results to continue work rather than duplicating effort

Example Use Cases

  • User asks to continue 'authentication' – memory-search.sh 'authentication'
  • User mentions 'last session' – memory-search.sh 'last session'
  • User references a component we discussed – memory-search.sh 'PaymentService' --mode term
  • User asks to see what the user previously asked – memory-search.sh 'user request' --role user
  • Searching for related patterns – memory-search.sh 'error handling patterns' --mode semantic

Frequently Asked Questions

Add this skill to your agents
Sponsor this space

Reach thousands of developers