para-memory-files

Organize and recall knowledge across sessions using PARA-based memory layers.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/krishsharma1008/ADE --skill para-memory-files-krishsharma1008
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: para-memory-files
Source: https://github.com/krishsharma1008/ADE/tree/main/skills/para-memory-files
Command: npx skills add https://github.com/krishsharma1008/ADE --skill para-memory-files-krishsharma1008

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

File-based memory is hard to maintain across sessions. This skill provides a PARA-based memory system to store, retrieve, update, and organize knowledge across sessions, covering three memory layers: (1) Knowledge graph in PARA folders with atomic YAML facts, (2) Daily notes as raw timeline, (3) Tacit knowledge about user patterns. It also handles planning files, memory decay, weekly synthesis, and recall via qmd. Trigger on any memory operation: saving facts, writing daily notes, creating entities, running weekly synthesis, recalling past context, or managing plans.

Core Features & Use Cases

  • Three memory layers: Knowledge Graph, Daily Notes, and Tacit Knowledge, all paths relative to $AGENT_HOME.
  • Layer 1 (Knowledge Graph): each entity folder contains summary.md and items.yaml, with status and relationships encoded in YAML.
  • Layer 2 (Daily Notes): $AGENT_HOME/memory/YYYY-MM-DD.md serves as the raw timeline for easier recollection.
  • Layer 3 (Tacit Knowledge): $AGENT_HOME/MEMORY.md stores user patterns and operational preferences for faster adaptation.
  • Planning, memory decay, weekly synthesis, and recall via qmd to surface relevant context.
  • Never delete facts; use superseded_by and status to supersede outdated information.

Quick Start

Create a new memory entry by adding a durable fact to an entity under $AGENT_HOME/life, then record daily notes in $AGENT_HOME/memory/YYYY-MM-DD.md and update the entity summary.

Frequently Asked Questions about para-memory-files

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

FAQPage Schema
How do I organize long-term knowledge management files across sessions?

Long-term knowledge management files are organized across sessions using a PARA-based memory system with three layers: a knowledge graph for atomic facts, daily notes as a raw timeline, and tacit knowledge for user patterns.

What is the best way to structure daily notes for memory recall?

Daily notes for memory recall are structured as a raw timeline stored at $AGENT_HOME/memory/YYYY-MM-DD.md, allowing you to easily recollect past context and track daily events chronologically.

Can I use YAML frontmatter to manage knowledge graph entities?

Yes, you can use YAML frontmatter to manage knowledge graph entities by storing metadata like name and description, with each entity folder containing a summary.md and items.yaml encoding status and relationships.

How does memory decay and weekly synthesis work with PARA folders?

Memory decay and weekly synthesis work with PARA folders by surfacing relevant context through qmd recall, allowing you to synthesize weekly events and manage outdated information without deleting past facts.

Why should I use supersession rules instead of deleting outdated facts?

Supersession rules are used instead of deleting outdated facts to preserve history; outdated information is marked with a superseded_by status, ensuring the knowledge graph maintains a complete and accurate audit trail.

Does this knowledge management approach require specific directory paths?

Yes, this knowledge management approach requires specific directory paths relative to $AGENT_HOME, structuring the knowledge graph, daily notes, and tacit knowledge files under designated folders for consistent access.