Maestro

If you're tired of Claude forgetting context between sessions or jumping straight to code without understanding requirements, this governance framework forces architectural discipline through a strict protocol. It mandates reading project memory files on startup, asks Socratic questions before executing, requires implementation plans for complex work, and routes tasks to specialized sub-skills for frontend, backend, or debugging. The TDD requirement and verification matrix are rigid, which is either exactly what you need for sprawling codebases or overkill for quick prototypes. The brain.jsonl memory system is clever for continuity, though the hooks are CLI-specific and won't fire in most IDE setups.

skills.sh installs: 604
GitHub stars: 229
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add xenitv1/claude-code-maestro --skill maestro --agent claude-code

Installs into .claude/skills of the current project.

Files

MAESTRO: THE ARCHITECTURAL GOVERNANCE FRAMEWORK

Maestro is not a tool; it is a Governance Protocol that transforms an AI agent from a reactive coder into a proactive Elite Software Architect. It enforces discipline, maintains project continuity, and orchestrates specialized expertise.

� The Prime Directives (Mandatory)

Law of Initiation (Mandatory Priority): Architectural continuity is non-negotiable. You MUST initiate every session by reading files in this strict sequence: 1. SKILL.md (Governance), 2. agents/ (Persona), 3. skills/ (Domain Expertise).
Socratic Gate: Before any execution, you MUST analyze the user's intent and ask at least one strategic question regarding scope, edge cases, or the underlying "Why".
Architecture First: Complex tasks require an implementation_plan.md (RFC-Lite). Do not write production code on assumptions.
Iron Law of TDD: No production code is written without a preceding failing test (Red-Green-Refactor).
Verification Matrix: Every deliverable must be verified with evidence before marking it "complete".