memory_retrieval_system

Scan archived Markdown files with ripgrep and read specific line ranges.

6|2|Updated Jan 23, 2026
One-click install
npx skills add https://github.com/valkryhx/google_adk_agent --skill memory-retrieval-system
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: memory_retrieval_system
Source: https://github.com/valkryhx/google_adk_agent/tree/main/skills/memory_retrieval_system
Command: npx skills add https://github.com/valkryhx/google_adk_agent --skill memory-retrieval-system

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill allows you to retrieve past Swarm conversations and action logs, overcoming the limitations of large language model context windows by using a two-tiered retrieval system.

Core Features & Use Cases

  • L0 Broad Scan (search_memory): Quickly scans the memory archive using ripgrep to provide a compact index of relevant files and line numbers.
  • L2 Precise Read (read_memory): Reads specific line ranges from identified files for detailed context.
  • Use Case: If you need to find the exact JSON payload used in a previous API call, you'd first use search_memory with keywords like "API name" or "error message", then use read_memory on the returned file path and line numbers to get the precise details.

Quick Start

Search your memory archive for any mention of 'API_KEY_ERROR' and then read the relevant lines from the identified file.

Frequently Asked Questions about memory_retrieval_system

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I search past conversation logs to find specific context?

You can retrieve past Swarm conversations and action logs using a two-tiered system: a broad scan with ripgrep generates a compact index of file paths and line numbers, followed by a precise read of specific line ranges to extract exact context.

What is the best way to retrieve a JSON payload from previous action logs?

To retrieve a JSON payload from previous action logs, search your memory archive using keywords like the API name or error message to generate a compact index, then read the specific line ranges from the identified file to get the precise details.

How does ripgrep handle memory retrieval for large volumes of archived Markdown files?

Ripgrep handles memory retrieval for large volumes of archived Markdown files by performing an L0 broad scan that generates a compact index of relevant file paths and line numbers, ensuring efficient recall without loading entire files into the context window.

Can I use this memory retrieval system to overcome context window limitations in large language models?

Yes, this memory retrieval system overcomes large language model context window limitations by using a two-tiered approach: L0 broad scanning generates a compact index of file paths and line numbers, while L2 precise reading retrieves only the specific content needed from identified line ranges.

Do I need any external dependencies to run the memory search and read functions?

No external dependencies are required to run the memory search and read functions. The system operates using included scripts and relies on ripgrep for L0 broad scanning and precise reading of specific line ranges from daily archived Markdown files.