maestro

>-

>-

Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: \"Index this repo\", \"Reanalyze the codebase\", \"Generate a wiki\"

Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: \"Why is X failing?\", \"Where does this error come from?\", \"Trace this bug\"

Use when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: \"How does X work?\", \"What calls this function?\", \"Show me the auth flow\"

Use when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: \"What GitNexus tools are available?\", \"How do I use GitNexus?\"

Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: \"Is it safe to change X?\", \"What depends on this?\", \"What will break?\"

Use when the user wants to rename, extract, split, move, or restructure code safely. Examples: \"Rename this function\", \"Extract this into a module\", \"Refactor this class\", \"Move this to a separate file\"

Base procedures for all mission agents: startup, cleanup, and handoff. REQUIRED skill for all mission feature implementations.

Generate visual HTML blueprint pages and structured plan specs for maestro project features. Explores the codebase, produces a `.md` plan in maestro format (Context, Critical Files, Design Decisions, Phases with Tasks and acceptance criteria) saved to `.maestro/plans/`, plus a visual HTML presentation. Use when the user asks to blueprint a maestro feature, plan an implementation for this project, or says "blueprint X" while working in the maestro codebase. Also use proactively for non-trivial maestro changes that span multiple files or architectural concerns.

Enter conductor mode: plan, decompose, and dispatch -- sub-agents implement, not you. Use when user says 'you orchestrate', 'conduct this', 'delegate this', 'don't code yourself', 'break this into sub-agents', 'run this milestone without doing it yourself', or wants to stay in the driver seat while you manage agents. Works for formal mission/milestone execution and ad-hoc decomposition.

Define and register custom skills for use in Mission Control missions. Create skill definitions with frontmatter, procedures, and validation rules.

Plan and structure new missions. Brainstorm raw ideas into decomposed missions with milestones, features, agent types, constraints, and the exact `maestro handoff` command for the first external agent.

Run code scrutiny validation during mission checkpoints. Spawns review subagents, synthesizes results, and produces validation reports.

Run user testing validation during mission checkpoints. Determines testable assertions, sets up test environment, spawns flow validators, and synthesizes results.

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.

Guide for working with maestroCLI's v2 architecture. Covers the context-to-memory rename, 4-state task model, plain file backend, pre-agent hooks, research phase, and memory promotion. Use when touching v2 code, encountering legacy patterns (e.g. 'context' instead of 'memory', old task states), adding new v2 features, or debugging v2 behavior. Also use when you see imports from adapters/fs/context, references to 'contextAdapter', or task states that don't match the 4-state model.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

>-

Strengthen a raw user prompt into an execution-ready instruction set for Amp, Claude Code, 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.

Use for design or brainstorming in a Maestro repo before implementation starts. Map current behavior, decide one fork at a time, record decisions and notes, then hand the approved contract to maestro-feature.

Use for the Maestro feature lifecycle: author, accept, prepare, start, amend, ship, cancel, archive, and inspect a feature contract plus its child-task rollup.

Use after Maestro init/install or doctor warnings to tune a repository harness from verified repo evidence.