maestro:note

Manage a persistent notepad for AI agents to capture and retrieve critical information across sessions.

Updated Mar 13, 2026
One-click install
npx skills add https://github.com/ReinaMacCredy/Maestro-CLI --skill maestro-note
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: maestro:note
Source: https://github.com/ReinaMacCredy/Maestro-CLI/tree/main/.codex/skills/maestro%3Anote
Command: npx skills add https://github.com/ReinaMacCredy/Maestro-CLI --skill maestro-note

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a persistent memory layer for AI agents, capturing crucial decisions, constraints, and learnings that span across sessions and tasks.

Core Features & Use Cases

  • Capture Decisions: Record architectural choices, API selections, and other critical decisions.
  • Enforce Constraints: Document hard constraints like rate limits, API versioning, or platform limitations.
  • Store Learnings: Save insights and discoveries made during implementation for future reference.
  • Priority Context: Pin vital information that must be injected into every worker prompt.
  • Working Memory: Maintain a searchable history of learnings, pruned periodically.
  • Manual Notes: Allow users to add their own sticky notes.

Quick Start

Capture the decision that all new endpoints must use the v2 response envelope by running the maestro:note skill with the content "All new endpoints MUST use v2 response envelope ({ data, meta, errors })" and the --priority flag.

Frequently Asked Questions about maestro:note

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

FAQPage Schema
How do I persist AI agent context and decisions across multiple sessions?

To persist AI agent context across sessions, use a structured notepad memory system that captures decisions, constraints, and learnings. This ensures critical project information is retained and searchable for future tasks.

What is the best way to enforce hard constraints like API versioning in AI agents?

The best way to enforce hard constraints like API versioning is to document them in a persistent memory layer. You can pin vital information as priority context, ensuring it is injected into every worker prompt.

How do I capture and retrieve architectural choices made during a development session?

You capture architectural choices by recording them in a persistent notepad designed for AI memory. This allows the agent to retrieve critical decisions and maintain consistent adherence to project guidelines.

Can I add my own manual notes to an AI agent's working memory?

Yes, you can add manual notes to working memory. The system supports user-created sticky notes alongside a searchable history of agent learnings that are pruned periodically.

Why does my AI agent forget project guidelines between different tasks?

AI agents forget project guidelines because they lack a persistent memory layer. Without a structured notepad to store constraints and learnings, context is lost when sessions end.

Does persistent AI memory work for storing rate limits and platform limitations?

Yes, persistent AI memory works for storing rate limits and platform limitations. You can enforce these hard constraints by documenting them for consistent retrieval across sessions.