Maestro-CLI

Use when bootstrapping, updating, or reviewing AGENTS.md — teaches what makes effective agent memory, how to structure sections, signal vs noise filtering, and when to prune stale entries

Use before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Deep discovery and specification for ambitious features. Full BMAD-inspired interview with classification, vision, journeys, domain analysis, and FR synthesis. Same output contract (spec.md + plan.md) as a standard feature but far richer. Use for multi-component systems, regulated domains, or unclear requirements.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use when working with Docker containers — debugging container failures, writing Dockerfiles, docker-compose for integration tests, image optimization, or deploying containerized applications

Execute feature tasks following TDD workflow. Single-agent by default, --team for parallel Agent Teams, Sub Agent Parallels. Use when ready to implement a planned feature.

Create a new feature/bug track with spec and implementation plan. Interactive interview generates requirements spec, then phased TDD plan. Use when starting work on a new feature, bug fix, or chore.

Strategic analysis of a project to identify the single highest-leverage, most innovative addition. Use when the user asks what to build next, what the most impactful improvement would be, what's missing, or any question about strategic direction and priorities. Also use when stuck choosing between competing features.

Capture decisions, constraints, and context to persistent memory. Global memory is injected into every session and implementation run. Per-feature memory tracks working context.

Use when you need parallel, read-only exploration with task() (Scout fan-out)

Deep-review any plan (maestro, Codex, Claude Code plan mode, or plain markdown) using iterative subagent review loops with BMAD-inspired adversarial edge-case discovery. Spawns reviewer subagents that find issues using pre-mortem, inversion, and red-team techniques, auto-fixes them with structured fix strategies, and re-reviews until the plan passes with zero actionable issues. Use when the user says 'review the plan', 'deep review', 'check the plan thoroughly', 'review loop', 'validate before approving', or wants rigorous plan validation before execution. Also use proactively before plan-approve when the plan is complex or high-risk.

Strengthen a raw user prompt into an execution-ready instruction set for Claude Code, Amp, Codex, or another AI agent. Use when the user wants to improve an existing prompt, build a reusable prompting framework, wrap the current request with better structure, add clearer tool rules, or create a hook that upgrades prompts before execution.

Git-aware revert of feature, phase, or individual task. Safely undoes implementation with task state rollback.

Code review for a feature against its spec and plan. Verifies implementation matches requirements, checks code quality and security.

Review changed code for reuse, quality, and efficiency, then fix issues found. Use after implementing a task or feature -- catches duplication, hacky patterns, and wasted work before review.

Use when implementing any feature or bugfix, before writing implementation code

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Create interactive HTML visualizations of maestro state and debug data

Run a full end-to-end smoke test of all 34 maestro MCP tools AND the CLI commands in a single session. Use this skill when testing the maestro pipeline, verifying tool installation, validating a maestro setup, or checking that all tool groups work (feature, plan, task, memory, meta, graph, handoff, search). Trigger on "test maestro", "smoke test", "pipeline test", "verify all tools", "run pipeline test", or whenever the user wants to confirm maestro is functioning correctly -- even if they just say "does it work?" in a maestro context.

Deep discovery and specification for ambitious features. Full BMAD-inspired interview with classification, vision, journeys, domain analysis, and FR synthesis. Same output contract (spec.md + plan.md) as new-track but far richer. Use for multi-component systems, regulated domains, or unclear requirements.

Create a new feature/bug track with spec and implementation plan. Interactive interview generates requirements spec, then phased TDD plan. Use when starting work on a new feature, bug fix, or chore.

Deep-review any plan (maestro, Codex, Claude Code plan mode, or plain markdown) using iterative subagent review loops with BMAD-inspired adversarial edge-case discovery. Spawns reviewer subagents that find issues using pre-mortem, inversion, and red-team techniques, auto-fixes them with structured fix strategies, and re-reviews until the plan passes with zero actionable issues. Use when the user says 'review the plan', 'deep review', 'check the plan thoroughly', 'review loop', 'validate before approving', or wants rigorous plan validation before execution. Also use proactively before plan-approve when the plan is complex or high-risk.

Deep-review any plan (maestro, Codex, Claude Code plan mode, or plain markdown) using iterative subagent review loops with BMAD-inspired adversarial edge-case discovery. Spawns reviewer subagents that find issues using pre-mortem, inversion, and red-team techniques, auto-fixes them with structured fix strategies, and re-reviews until the plan passes with zero actionable issues. Use when the user says 'review the plan', 'deep review', 'check the plan thoroughly', 'review loop', 'validate before approving', or wants rigorous plan validation before execution. Also use proactively before plan-approve when the plan is complex or high-risk.

Structured research workflow for maestro features. Guides tool selection across three tiers (codebase exploration, Context7 for library docs, NotebookLM for deep analysis), defines research patterns, finding organization via memory_write, and completion criteria. Use during the research pipeline stage after feature_create and before plan_write. Also use when investigating a problem space, comparing technical approaches, gathering context on unfamiliar code, or needing to understand external library APIs before making architectural decisions.

Use before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Development workflow for maestroCLI itself. Encodes the hexagonal architecture pattern (port -> adapter -> use-case -> command -> MCP tool -> test) and project-specific conventions. Use when implementing new maestro features, adding CLI commands, extending the MCP server, creating new adapters, modifying ports, writing use-cases, or debugging maestro's own code. Also use when you need to understand how maestro's layers connect or where to put new code.

Create, update, or debug maestro built-in skills. Covers SKILL.md frontmatter, reference directory structure, step-file architecture, build-time embedding, naming conventions, alias management, and registry validation. Use when creating a new maestro built-in skill, modifying an existing SKILL.md, adding reference files, debugging skill loading failures, updating the skills registry, or working on the skills full port. Also use when frontmatter validation fails, skills don't appear in skill-list, or reference files fail to load.

Use when bootstrapping, updating, or reviewing AGENTS.md — teaches what makes effective agent memory, how to structure sections, signal vs noise filtering, and when to prune stale entries

Use before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use when working with Docker containers — debugging container failures, writing Dockerfiles, docker-compose for integration tests, image optimization, or deploying containerized applications

Execute track tasks following TDD workflow. Single-agent by default, --team for parallel Agent Teams, Sub Agent Parallels. Use when ready to implement a planned track.

Capture decisions, constraints, and context to persistent notepad. Priority notes are injected into every session and implementation run.

Use when you need parallel, read-only exploration with task() (Scout fan-out)

Strengthen a raw user prompt into an execution-ready instruction set for Claude Code, Amp, Codex, or another AI agent. Use when the user wants to improve an existing prompt, build a reusable prompting framework, wrap the current request with better structure, add clearer tool rules, or create a hook that upgrades prompts before execution.

Git-aware revert of track, phase, or individual task. Safely undoes implementation with plan state rollback.

Code review for a track against its spec and plan. Verifies implementation matches requirements, checks code quality and security.

Scaffolds project context (product, tech stack, coding guidelines, product guidelines, workflow) and initializes track registry. Use for first-time project onboarding.