Maestro

Maestro spec-driven development for Claude Code. Load this skill when invoking Maestro commands so workflows stay aligned with LeIndex and the Rust TUI.

Maestro spec-driven development for Gemini CLI. Load this skill when invoking Maestro commands so workflows stay aligned with LeIndex and the Rust TUI.

Maestro spec-driven development for Amp CLI. Load this skill when invoking Maestro commands so workflows stay aligned with LeIndex and the Rust TUI.

Show users how Maestro works - the opinionated setup with hooks, memory, and coordination

Full 5-layer analysis of a specific function for debugging or deep understanding

Get a token-efficient overview of any project using the TLDR stack

Maps questions to the optimal LeIndex command

Friendly onboarding when users ask about capabilities

Completion Check: Verify Infrastructure Is Wired

Semantic memory retrieval that queries stored learnings from past sessions

Store a learning, pattern, or decision in the memory system for future recall

Search Mathlib for lemmas by type signature pattern

Spec-driven development framework that integrates with OpenCode to provide structured project planning, track management, and implementation workflow. Use when you need to: (1) Initialize a new Maestro project with product definition, tech stack, and workflow configuration, (2) Create new tracks (features/bug fixes) with interactive specification generation, (3) Implement tracks with automatic agent selection based on task complexity, (4) View project status and progress across all tracks, (5) Revert work at track/phase/task level. This skill provides a complete TDD workflow with project memory, git-aware tracking, and multi-agent orchestration.

Semantic search across codebase using LEANN vector index

Token-efficient code analysis via 5-layer stack (AST, Call Graph, CFG, DFG, PDG). 82% savings (balanced mode) with semantic completeness.

System health check (MOT) for skills, agents, hooks, and memory

Agent Context Isolation

Agentic Workflow Pattern

Guide for integrating Agentica SDK with Maestro CLI proxy

Reference guide for Agentica multi-agent infrastructure APIs

Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity

Fast file editing via Morph Apply API (10,500 tokens/sec, 98% accuracy)

Fast codebase search via WarpGrep (20x faster than grep)

OPC Architecture Understanding

Background Agent Pings

Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".

Search past reasoning for relevant decisions and approaches

Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.

Explicit Identity Across Boundaries

Git Commit Rules

Interactive workspace discovery - learn what tools, workflows, agents, and hooks are available

Complete Maestro hooks reference - input/output schemas, registration, testing patterns

Hook Development Rules

Problem-solving strategies for fields in abstract algebra

Problem-solving strategies for groups in abstract algebra

Problem-solving strategies for rings in abstract algebra

Problem-solving strategies for categories functors in category theory

Problem-solving strategies for limits colimits in category theory

Problem-solving strategies for natural transformations in category theory

Problem-solving strategies for analytic functions in complex analysis