memory-keeping

Synchronize session progress and append audit logs to markdown state files.

Updated Jun 1, 2026
One-click install
npx skills add https://github.com/matejformanek/postgres-claude --skill memory-keeping
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: memory-keeping
Source: https://github.com/matejformanek/postgres-claude/tree/main/.claude/skills/memory-keeping
Command: npx skills add https://github.com/matejformanek/postgres-claude --skill memory-keeping

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the problem of context loss between AI sessions by ensuring that progress, verified facts, and discovered insights are durably recorded in the repository's state and ledger files.

Core Features & Use Cases

  • State Synchronization: Automatically updates STATE.md to reflect current project phases and next steps.
  • Audit Logging: Maintains append-only session logs and file-examined ledgers to provide a clear history of work.
  • Knowledge Verification: Updates coverage.md to track the confidence level and verification status of documented subsystems.
  • Use Case: When finishing a deep dive into PostgreSQL memory contexts, use this skill to record the session findings, update the coverage table, and set the next concrete task for the next session.

Quick Start

Invoke the memory-keeping skill to sync the current session progress and record the new findings into the repository state files.

Frequently Asked Questions about memory-keeping

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

FAQPage Schema
How do I maintain session state and audit trails across AI development sessions?

You can maintain session state by synchronizing progress into markdown state files and appending to session logs. This ensures project continuity and preserves verified facts when work spans multiple sessions.

What is the best way to track documentation coverage and verification status for PostgreSQL internals?

Tracking documentation coverage involves updating a markdown schema to record confidence levels and verification status of documented subsystems. This creates an auditable ledger of examined files and verified knowledge.

How does state tracking for deep dive development sessions work?

State tracking works by updating state files with current project phases and next steps whenever durable output is produced. It appends session logs to create a clear, append-only history of work for future reference.

Do I need a specific markdown schema to record session progress and file-examined ledgers?

Yes, strict adherence to a defined markdown-based state and coverage schema is required. This ensures auditability and context retention by standardizing how progress and file ledgers are recorded.

Can I use session logs to prevent context loss between AI coding sessions?

Yes, session logs prevent context loss by durably recording progress, verified facts, and discovered insights in repository state files. This ensures the next session starts with the correct context.

What are the limitations of using markdown files for knowledge management in PostgreSQL development?

The primary limitation is the strict requirement to follow the defined markdown schema. If session logs and state files are not updated accurately, auditability and context retention across sessions will degrade.