memory-search

Search long-term memory by keyword with semantic retrieval and relevance scores.

6|Updated Feb 26, 2026
One-click install
npx skills add https://github.com/Acosmi/CrabClaw --skill memory-search-acosmi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: memory-search
Source: https://github.com/Acosmi/CrabClaw/tree/main/docs/skills/tools/memory/memory-search
Command: npx skills add https://github.com/Acosmi/CrabClaw --skill memory-search-acosmi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Memory-based retrieval of past conversations and knowledge to maintain continuity and context across sessions.

Core Features & Use Cases

  • Semantic long-term memory search by keywords to locate relevant past items.
  • Context restoration for continued conversations and decision auditing.
  • Use Case: When you need to recall what was discussed earlier or retrieve stored notes to inform current decisions.

Quick Start

Execute a memory search query like "previous discussion on project scope" to retrieve matching memories.

Frequently Asked Questions about memory-search

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

FAQPage Schema
How do I search past conversations and restore context from long-term memory?

Search long-term memory by keyword to retrieve past conversations and restore context. Semantic retrieval matches keyword queries against stored knowledge, returning entries with relevance scores to maintain continuity across sessions.

What is semantic memory retrieval and how does it work for recalling notes?

Semantic memory retrieval applies keyword queries across stored knowledge to locate relevant past items. It scores matched entries by relevance, allowing you to recall prior discussions and notes instead of manually searching through raw logs.

Can I limit the number of matched entries returned when searching my stored knowledge?

Yes, you can limit matched entries when searching stored knowledge. The semantic search supports keyword queries with an optional limit parameter, returning matched entries alongside their relevance scores for precise context restoration.

What's the best way to retrieve prior discussions on a specific project scope?

The best way to retrieve prior discussions on project scope is executing a memory search query. Semantic retrieval across UHMS memory locates matching past conversations and decisions, returning them with relevance scores for quick context restoration.

Do I need any external dependencies to use semantic search over UHMS memory?

No external dependencies are required to use semantic search over UHMS memory. The Skill operates independently to apply semantic retrieval across stored knowledge, matching keyword queries and returning entries with relevance scores.