memorizer

Read three-tier memory files and write task insights to wiki/log.md.

13|4|Updated Mar 17, 2026
One-click install
npx skills add https://github.com/ob-labs/talos --skill memorizer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: memorizer
Source: https://github.com/ob-labs/talos/tree/main/skills/memorizer
Command: npx skills add https://github.com/ob-labs/talos --skill memorizer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Three-tier memory system provides contextual grounding by reading user preferences, project hot memory, and knowledge base, and it captures valuable insights after task completion to enrich future work.

Core Features & Use Cases

  • Reads from ~/.talos/profile.md to align with user preferences and style.
  • Aggregates project hot memory from wiki/hot.md and knowledge base entries from wiki/ to surface constraints, pitfalls, and reusable patterns.
  • Writes summaries and lessons to wiki/log.md after task completion to enrich the memory repository.

Quick Start

Run memorizer on the current task to load context and persist insights after completion.

Frequently Asked Questions about memorizer

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

FAQPage Schema
How do I persist task context and insights for future AI workflows?

To persist task context, a three-tier memory system reads user preferences, project hot memory, and a knowledge base, then writes valuable insights and summaries to a log file for reuse.

What is three-tier memory for project knowledge management?

Three-tier memory is a contextual grounding mechanism that aggregates user profile preferences, active project hot memory, and a persistent wiki knowledge base to inform ongoing tasks.

How do I write task summaries to a wiki knowledge base automatically?

You can automatically write task summaries to a wiki by running a memory management process that captures lessons and insights upon task completion, appending new entries to the wiki log.

Can I use markdown files to manage user preferences and project hot memory?

Yes, you can manage context using markdown files, reading user profile preferences and project hot memory directly from markdown sources to align workflows with established constraints.

What is the best way to retain project context across multiple AI task sessions?

The best way to retain project context is using a memory management system that reads from a knowledge base index and hot memory, then writes captured insights back to a persistent log.

When do I need a knowledge base index for task context retrieval?

You need a knowledge base index for task context retrieval when you must surface reusable patterns, constraints, and pitfalls from a wiki repository to accurately inform new tasks.