maestro:iterative-retrieval
Progressive context retrieval pattern for multi-agent workflows. Use during maestro:design when architecting subagent context strategies or RAG-like retrieval pipelines.
maestro:java-coding-standards
Java coding standards for Spring Boot services covering naming, immutability, Optional, streams, and exceptions. Use during maestro:implement for Java code quality and maestro:review for Java review criteria.
maestro:jpa-patterns
JPA/Hibernate patterns for entity design, relationships, query optimization, and transactions in Spring Boot. Use during maestro:implement when building JPA entities or optimizing database access.
maestro:liquid-glass-design
iOS 26 Liquid Glass design system with dynamic glass materials, blur, reflection, and interactive morphing. Use during maestro:implement when building iOS 26 UI with the glass material system.
maestro:market-research
Market research, competitive analysis, and industry intelligence with source attribution. Use during maestro:design for research tasks, TAM/SAM/SOM estimates, or competitor analysis.
maestro:nutrient-document-processing
Nutrient DWS API for document processing, conversion, OCR, redaction, signing, and form filling. Use during maestro:implement when building document processing features with Nutrient.
maestro:plankton-code-quality
Write-time code quality enforcement via Plankton hooks for auto-formatting, linting, and Claude-powered fixes. Use across all maestro phases as a quality gate on file edits.
maestro:postgres-patterns
PostgreSQL query optimization, schema design, indexing, and security patterns. Use during maestro:implement when writing SQL queries or designing database schemas with PostgreSQL.
maestro:project-guidelines-example
Example project-specific skill template based on a real production application. Use during maestro:setup as a reference for creating custom project skills.
maestro:python-patterns
Pythonic idioms, PEP 8 standards, type hints, and best practices for Python applications. Use during maestro:implement when writing Python code -- naming, structure, and idiomatic patterns.
maestro:python-testing
Python testing with pytest, TDD methodology, fixtures, mocking, and parametrization. Use during maestro:implement when writing Python tests following TDD.
maestro:regex-vs-llm-structured-text
Decision framework for choosing regex vs LLM for structured text parsing. Use during maestro:design when planning text extraction approach, and maestro:implement when building parsers.
maestro:search-first
Research-before-coding workflow. Use during maestro:design to find existing tools, libraries, and patterns before writing custom code.
maestro:security-review
Comprehensive security checklist for authentication, input handling, secrets, API endpoints, and sensitive data. Use during maestro:review for security posture assessment.
maestro:security-scan
Scan Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks. Use during maestro:review to audit agent configuration security.
maestro:skill-stocktake
Audit Claude skills and commands for quality with Quick Scan or Full Stocktake modes. Use during maestro:review to assess skill quality and consistency.
maestro:springboot-patterns
Spring Boot architecture patterns, REST API design, layered services, and caching. Use during maestro:implement when building Java Spring Boot backend services.
maestro:springboot-security
Spring Security best practices for authentication, authorization, CSRF, secrets, and rate limiting. Use during maestro:review when reviewing Spring Boot security configuration.
maestro:springboot-tdd
Spring Boot TDD with JUnit 5, Mockito, MockMvc, and Testcontainers. Use during maestro:implement when writing tests for Spring services, controllers, and repositories.
maestro:springboot-verification
Verification loop for Spring Boot: build, static analysis, tests with coverage, security scans, and diff review. Use during maestro:review before Spring Boot releases or PRs.
maestro:strategic-compact
Strategic context compaction for long sessions. Use during maestro:design for multi-phase sessions approaching context limits, suggesting /compact at logical breakpoints.
maestro:swift-actor-persistence
Thread-safe data persistence using Swift actors with in-memory cache and file-backed storage. Use during maestro:implement when building persistence layers in Swift.
maestro:swift-concurrency-6-2
Swift 6.2 Approachable Concurrency with single-threaded default, @concurrent offloading, and isolated conformances. Use during maestro:implement when writing async Swift code.
maestro:swift-protocol-di-testing
Protocol-based dependency injection for testable Swift code with mock strategies and Swift Testing. Use during maestro:implement when writing testable Swift with DI.
maestro:swiftui-patterns
SwiftUI architecture with @Observable state management, view composition, navigation, and performance optimization. Use during maestro:implement when building SwiftUI views and features.
maestro:tdd-workflow
Test-driven development workflow enforcing Red-Green-Refactor with 80%+ coverage. Use during maestro:implement as the core TDD methodology for all code changes.
maestro:verification-loop
Comprehensive post-change verification system with build, test, lint, and quality gates. Use during maestro:review as the core verification workflow before PRs or releases.
maestro:visa-doc-translate
Translate visa application documents (images) to English and create bilingual PDFs. Use in any maestro phase when translating documents for visa applications.
init
Generates AGENTS.md and CLAUDE.md files using the WHAT/WHY/HOW framework. Explores the codebase and produces minimal (<100 line) context files with progressive disclosure.
maestro-design
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.
maestro-implement
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.
maestro-new-track
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.
maestro-note
Capture decisions, constraints, and context to persistent notepad. Priority notes are injected into every session and implementation run.
maestro-revert
Git-aware revert of track, phase, or individual task. Safely undoes implementation with plan state rollback.
maestro-review
Code review for a track against its spec and plan. Verifies implementation matches requirements, checks code quality and security.
maestro-setup
Scaffolds project context (product, tech stack, coding guidelines, product guidelines, workflow) and initializes track registry. Use for first-time project onboarding.
maestro-status
Show track progress overview with phase/task completion stats, next actions, and blockers.
maestro-dev
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.
maestro-pipeline-test
Run a full end-to-end smoke test of all maestro 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.
maestro-skill-author
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.
maestro-v2-migration
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.
maestro:brainstorming
Use before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
maestro:plan-review-loop
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.
maestro:research
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.
mcp-builder
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).
mcp-for-agents
>-
prompt-leverage
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.
maestro:agents-md
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
maestro:debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
maestro:design
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.
Page 2 of 3 · 119 results