What problem does it solve? AI coding assistants start every session with zero knowledge of your project, causing repeated debugging of solved bugs, architectural decisions that conflict with past choices, and constant re-asking for configuration details. This Skill establishes a persistent institutional knowledge system in docs/project_notes/ so context survives across sessions, team members, and AI tools. ## Core Features & Use Cases - Memory Infrastructure Setup: Creates four structured files in docs/project_notes/: bugs.md (bug log with solutions), decisions.md (Architectural Decision Records), key_facts.md (project configuration), and issues.md (work log with ticket references). - Memory-Aware Configuration: Updates CLAUDE.md and AGENTS.md with protocols so AI tools check memory files before proposing changes, search for known bug solutions, and document new decisions automatically. - Templates and Security Guidelines: Provides ready-to-use templates for all four memory files, including explicit rules about never storing credentials or secrets in version-controlled files. - Use Case: A deployment fails with a Pulumi state drift error. Instead of 45 minutes of debugging, the AI searches bugs.md, finds the documented solution (pulumi refresh --yes), and applies the fix in minutes. ## Quick Start Ask the AI to set up project memory in this repository so it creates the docs/project_notes memory files and configures CLAUDE.md to track bugs, decisions, and key facts.
