maestro-bitcoin
Query Maestro Bitcoin APIs directly over HTTP using x402 USDC payments on Ethereum or Base. Use this skill when agents should read endpoint specs from docs.gomaestro.org and call APIs without local wrapper scripts.
brainstorming
Design-first methodology. Explore user intent, requirements and design before implementation. Turn ideas into fully formed specs through collaborative dialogue.
optimization-mastery
2026-grade Cross-Domain Optimization. Expertise in Interaction to Next Paint (INP), Partial Hydration, UUIDv7 indexing, and AI Token Stewardship. Performance is a feature, not an afterthought.
verification-mastery
Evidence before claims, always. No completion claims without fresh verification. The final gate before declaring success.
browser-extension
Master specialized skill for building 2025/2026-grade browser extensions. Deep expertise in Manifest v3, Service Worker persistence (Alarms, Offscreen API), Side Panel API, and Cross-Browser compatibility.
tdd-mastery
Test-Driven Development Iron Law. Write the test first. Watch it fail. Write minimal code to pass. No exceptions.
planning-mastery
Create concise, architectural implementation plans using the RFC-Lite format. STRICTLY LIMITED VERBOSITY.
backend-design
Elite Tier Backend standards, including Vertical Slice Architecture, Zero Trust Security, and High-Performance API protocols.
git-worktrees
Create isolated git workspaces for feature development. Smart directory selection, safety verification, and cross-platform support (Windows/Unix).
clean-code
The Foundation Skill. LLM Firewall + 2025 Security + Cross-Skill Coordination. Use for ALL code output - prevents hallucinations, enforces security, ensures quality.
ralph-wiggum
Surgical Debugger & Code Optimizer. Autonomous root-cause investigation, persistence-loop fixing, and high-fidelity code reflection. No new features, only fixes.
frontend-design
Elite Tier Web UI standards, including pixel-perfect retro aesthetics, immersive layouts, and UX psychology protocols.
debug-mastery
Systematic debugging methodology with 4-phase process, root cause tracing, and elite observability standards. No fixes without investigation.
maestro
Use when you need to act as an Elite Software Architect (Maestro) to manage complex repositories. It enforces a "Why over How" philosophy, maintains a persistent project memory (Brain), and orchestrates specialized sub-skills through a Plan-Act-Verify lifecycle.
ai-maestro-memory-search
PROACTIVELY search conversation history when receiving user instructions. Find previous discussions, decisions, and context BEFORE starting new work. Your memory is valuable - use it.
ai-maestro-code-graph-query
PROACTIVELY query the code graph database to understand relationships and impact of changes. Use this skill WHEN READING any file to understand context, when searching for files, when exploring the codebase, or when you need to understand what depends on a component. This is your primary tool for understanding code structure and avoiding breaking changes.
ai-maestro-agent-messaging
Send and receive messages between AI agents using AI Maestro's messaging system. Use this skill when the user asks to "send a message", "check inbox", "read messages", "notify [agent]", "tell [agent]", or any inter-agent communication.
ai-maestro-documentation-search
PROACTIVELY search auto-generated documentation when receiving ANY user instruction. Search for function signatures, API documentation, class definitions, and code comments BEFORE implementing anything. Your codebase documentation is valuable - use it first.
maestro-workflow
Multi-LLM orchestration implementing the 5-stage coding workflow: Example Analysis → Hypothesis → Implementation → Debug Loop → Recursive Improvement. Based on "Towards a Science of Scaling Agent Systems" (Kim et al., 2025): - Centralized Consult architecture (Claude orchestrates, others advise) - Measured coordination (avoid MAS overhead in tool-heavy stages) - Tests-first selection (Poetiq pattern, not voting) Use when: Debugging complex issues, analyzing unfamiliar code, refactoring, or any task that benefits from diverse LLM perspectives with verification.
qa-testing-mobile
Mobile app testing strategy and execution for iOS and Android (native + cross-platform): choose automation frameworks, define device matrix, control flakes, validate performance/reliability/accessibility, and set CI + release gates. Use when you need a mobile QA plan, device lab/CI setup, or guidance on XCUITest/Espresso/Appium/Detox/Maestro/Flutter testing.
resonance-frontend
Frontend/UX Engineer Specialist ("The Glasssmith"). Implements elite UI/UX using Design Protocols and Maestro Audits.
maestro:status
Show track progress overview with phase/task completion stats, next actions, and blockers.
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.
analyze
Primary deep read-only investigation workflow. Use this first to understand a problem before any implementation work.
learner
Extracts reusable principles from the current session and stores them as learned skills. Use when you want to capture durable patterns after completing work.
maestro:implement
Execute track tasks following TDD workflow. Single-agent by default, --team for parallel Agent Teams. Use when ready to implement a planned track.
doctor
Primary Maestro diagnostic flow. Diagnoses installation issues, detects configuration drift, and auto-fixes common problems.
security-review
Performs deep security analysis: checks auth flows, injection vectors, secrets, and dependencies. Reports findings with severity ratings and file:line evidence. Use when reviewing code for security vulnerabilities or performing security audits.
maestro:revert
Git-aware revert of track, phase, or individual task. Safely undoes implementation with plan state rollback.
review
Performs code review with plan-to-implementation comparison and structured diff analysis, including auto-fix support. Use when validating quality and addressing review findings.
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.
reset
Cleans stale Maestro state by removing old drafts, orphaned teams, and stale task directories. Use when the local Maestro state is inconsistent or cluttered.
research
Supporting follow-up mode for multi-source validation after analyze. Use to extend existing findings with docs/web cross-checks.
example-skill
Template for creating skills. Use when writing new code, reviewing code, or when the skill's specific domain applies. Replace this description with specifics.
trace
Shows agent execution timelines and performance summaries. Use when debugging orchestration flow or measuring run behavior.
maestro:review
Code review for a track against its spec and plan. Verifies implementation matches requirements, checks code quality and security.
setup-check
Fast prerequisite gate for Maestro runtime readiness. Use before `/design` or `/work` to verify required local tooling and flags.
planning
Generate comprehensive implementation plans through systematic discovery, synthesis, verification, and decomposition into beads. Use when asked to plan a feature, create a roadmap, design an implementation approach, or decompose work into trackable issues. Do NOT use for simple one-step tasks, quick fixes, or when the user just wants to execute an existing plan — use the work skill instead.
design
Conducts interview-driven planning via Prometheus agent asking clarifying questions before generating an implementation plan. Use when starting work on features or tasks.
psm
Manages isolated development sessions using git worktrees and tmux. Use when running parallel tasks that require separate environments.
init
Generates AGENTS.md file using the WHAT/WHY/HOW framework. Explores the codebase and produces a minimal (<100 line) context file with progressive disclosure.
pipeline
Runs sequential agent chains with context passed between stages. Use when work should flow through ordered specialist steps.
maestro-note
Capture decisions, constraints, and context to persistent notepad. Priority notes are injected into every session and implementation run.
context7
Fetches up-to-date library documentation via Context7 MCP for external libraries, APIs, and frameworks. Use when working with external dependencies or unfamiliar APIs.
release
Automates version bumping, tagging, publishing, and GitHub release creation. Use when preparing and shipping a project release.
maestro
Provides the Maestro workflow for interview-driven planning and team-based execution. Use when orchestrating work with /design, /planning, and /work.
project-conventions
Discovers project conventions from configuration files and coding-standard sources. Use when agents need repository-specific style and workflow rules.
setup
Scaffolds persistent project context files through a guided interview. Use when onboarding a repository to Maestro context workflows.