para-memory-files

Store and retrieve durable knowledge across sessions using PARA-based memory files.

Updated Mar 28, 2026
One-click install
npx skills add https://github.com/chifamba/vashandi --skill para-memory-files-chifamba
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: para-memory-files
Source: https://github.com/chifamba/vashandi/tree/main/vashandi/skills/para-memory-files
Command: npx skills add https://github.com/chifamba/vashandi --skill para-memory-files-chifamba

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Persistent, file-based memory organized by Tiago Forte's PARA method to store, retrieve, update, and organize knowledge across sessions.

Core Features & Use Cases

  • Three memory layers: a knowledge graph in PARA folders with atomic YAML facts, daily notes as a raw timeline, and tacit knowledge about user patterns. Also handles planning files, memory decay, weekly synthesis, and recall via qmd.
  • Provides a deterministic memory lifecycle: save durable facts, rewrite summaries weekly, and never delete facts (only supersede and add superseded_by when needed).
  • Works across projects and contexts to maintain continuity and context over time.

Quick Start

Create the PARA memory folders under $AGENT_HOME and save your first atomic facts to life/<entity>/items.yaml.

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 persistent knowledge across sessions using the PARA method?

Persistent knowledge is organized using the PARA method by storing durable facts as atomic YAML files in a structured knowledge graph, maintaining daily notes as a raw timeline, and tracking tacit user patterns across sessions.

What is the best way to structure daily notes and a knowledge graph for long-running projects?

The best way to structure daily notes and a knowledge graph is to save raw timeline entries under memory/YYYY-MM-DD and organize durable facts into structured PARA folders within $AGENT_HOME for long-running project continuity.

How does memory decay and recall work in a file-centric knowledge base?

Memory decay and recall work by applying decay rules to older entries and retrieving past context via qmd, ensuring that outdated facts are superseded with a superseded_by reference rather than being deleted.

Can I use this PARA memory system for weekly synthesis across multiple projects?

Yes, you can use this PARA memory system for weekly synthesis across multiple projects and contexts, as it rewrites summaries periodically to maintain context continuity and synthesize knowledge over various timeframes.

How do I start saving atomic facts for daily knowledge management?

To start saving atomic facts for daily knowledge management, create the PARA memory folders under $AGENT_HOME and save your first entries as structured YAML files in life/<entity>/items.yaml.

Why are outdated facts superseded instead of deleted in a durable knowledge graph?

Outdated facts are superseded instead of deleted to maintain a deterministic memory lifecycle, preserving historical context while adding a superseded_by reference to point to the updated information.