knowledge-refiner

Deduplicate, consolidate, and archive stale memories with change reports.

4|Updated Mar 21, 2026
One-click install
npx skills add https://github.com/Kit4Some/Oh-my-ClaudeClaw --skill knowledge-refiner
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: knowledge-refiner
Source: https://github.com/Kit4Some/Oh-my-ClaudeClaw/tree/main/skills/knowledge-refiner
Command: npx skills add https://github.com/Kit4Some/Oh-my-ClaudeClaw --skill knowledge-refiner

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Memory refinement automates the health of the memory store by deduplicating, consolidating, archiving, and reporting changes to keep knowledge assets clean and actionable.

Core Features & Use Cases

  • Detect and merge duplicate memories, archive stale items, and promote important memories for efficient retrieval.
  • Provide auditable reports of changes and maintain a three-layer memory persistence to support long-term context.

Quick Start

Run a nightly memory refinement on the active store and generate a concise change report.

Frequently Asked Questions about knowledge-refiner

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

FAQPage Schema
How do I automate memory store deduplication and remove duplicate memories?

Automated memory refinement detects and merges duplicate memories in your store, consolidating related items and archiving stale data to keep knowledge assets clean and actionable.

What is memory refinement and how does it maintain knowledge base health?

Memory refinement is an automated maintenance process that optimizes knowledge base health by deduplicating, consolidating, archiving stale items, and promoting important memories for efficient retrieval.

Can I run nightly memory maintenance pipelines across different project categories?

Nightly memory maintenance pipelines support varying memory sizes, categories, and access patterns across multiple projects, providing auditable change reports after each automated refinement run.

Does memory refinement prompt for confirmation before archiving or deleting stale items?

Memory refinement implements strict guardrails and confirm prompts before executing destructive operations like archiving stale items, ensuring all changes are logged and auditable.

What is the best way to consolidate related memories and promote important ones for retrieval?

The best way to consolidate related memories is using automated refinement, which merges duplicates, archives stale items, and promotes important memories to support efficient retrieval and long-term context persistence.