Memory

Create a hierarchical file-based memory directory with per-category INDEX.md files.

2|Updated Apr 6, 2026

Search Tags:#indexing #memory #organization #sync #knowledge-management #personal-knowledge #long-term-storage

Ready to run

npx skills add https://github.com/augustscl/awesome-xiawang-skills --skill memory-augustscl

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: Memory
Source: https://github.com/augustscl/awesome-xiawang-skills/tree/main/memory-1.0.2
Command: npx skills add https://github.com/augustscl/awesome-xiawang-skills --skill memory-augustscl

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides a parallel, expandable personal memory store so agents and users never lose important long-term context that exceeds built-in memory limits.

Core Features & Use Cases

Infinite, organized storage: Hierarchical file-based memory rooted at ~/memory/ with user-defined categories and per-category INDEX.md files.
Immediate capture and reliable indices: Write entries as soon as information arrives, update indices, and use navigation-first or semantic search for retrieval.
Optional one-way sync: Selectively import items from built-in agent memory into this local system without modifying the built-in memory.
Use Case: Track detailed project histories, full contact profiles, decision reasoning, knowledge bases, and collections that grow over time.

Quick Start

Ask the agent to create ~/memory/ with categories for projects and people and save the current note as the first entry.

Frequently Asked Questions about Memory

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

FAQPage Schema

How do I store long-term project history and contact profiles when built-in agent memory is full?▼

You can store long-term project history and contact profiles by creating a hierarchical file-based memory directory rooted at ~/memory/ with user-defined categories and per-category INDEX.md files for infinite organized storage.

How does hierarchical file-based memory organize personal knowledge for long-term workflows?▼

Hierarchical file-based memory organizes personal knowledge by creating a root directory with user-defined categories, using per-category INDEX.md files to track entries and enable navigation-first or semantic search retrieval across long-term workflows.

Can I sync existing agent memory entries into a local-only personal knowledge management system?▼

Yes, you can selectively import items from built-in agent memory into your local-only hierarchical storage system using a one-way sync that captures data without modifying the original built-in memory.

What is the best way to capture decisions and notes immediately without losing context?▼

The best way to capture decisions and notes immediately is using a write-on-capture behavior that saves entries as soon as information arrives and automatically updates the per-category index files for reliable retrieval.

Does this local knowledge management approach require external dependencies or cloud services?▼

No, this local knowledge management approach operates entirely local-only with no external dependencies, using a hierarchical file-based memory directory structure to maintain structured storage for projects, people, decisions, and knowledge collections.