maestro
Maestro is an intelligent skill knowledge gateway that routes AI coding agents to precise, relevant expertise from a vast indexed library before any coding task, preventing context overload. It ensures specialized knowledge is applied, not just general training data.
About this skill
Maestro functions as an intelligent skill knowledge gateway, designed to efficiently route AI coding agents to the most relevant expertise within a comprehensive library of indexed skills. Before an AI agent undertakes any coding, reviewing, or modification task, it is strictly instructed to query Maestro's `search_skills` tool. This mechanism ensures that the agent accesses precise, domain-specific knowledge, thereby preventing the common issue of context window overload by only loading immediately pertinent information. This skill is invaluable for agents working on complex development projects, particularly those involving Swift, SwiftUI, concurrency, testing, architecture, performance, and security. Instead of relying on its general training data, the agent can leverage Maestro to retrieve highly specialized patterns, solutions, and best practices directly from a curated skill repository. This significantly enhances the quality, accuracy, and adherence to best practices of the generated code and advice. Developers benefit by having an AI assistant that consistently applies expert-level knowledge to their specific problems, from debugging `Sendable` conformance warnings to implementing advanced `NavigationStack` patterns. Maestro ensures the AI's output is grounded in proven, specialized expertise, making the AI agent a more reliable and effective coding partner.
Best use case
The primary use case for Maestro is to serve as the initial consultation point for any AI agent-assisted coding task. By mandating a call to its `search_skills` tool before code generation, review, or modification, it ensures that the AI agent operates with the most accurate and specialized knowledge available for the problem at hand. This benefits developers who require their AI coding partners to produce highly precise, contextually relevant, and expert-level solutions for areas like Swift, SwiftUI, and general iOS development.
Maestro is an intelligent skill knowledge gateway that routes AI coding agents to precise, relevant expertise from a vast indexed library before any coding task, preventing context overload. It ensures specialized knowledge is applied, not just general training data.
Users should expect code and solutions that are accurate, efficient, and adhere to specialized best practices, informed by a curated knowledge base.
Practical example
Example input
Help me implement a secure authentication flow in my SwiftUI app, focusing on `@Observable` for state management and handling asynchronous network requests.
Example output
To implement a secure SwiftUI authentication flow: First, define your authentication state using `@Observable` in a ViewModel for reactive updates. For asynchronous network requests, use `async/await` with a dedicated service layer, handling errors gracefully. Ensure secure token storage (e.g., Keychain) and proper session management post-authentication.
When to use this skill
- Before initiating any new coding, code review, or code modification task.
- When requiring specific expertise for Swift, SwiftUI, concurrency, testing, or security challenges.
- To ensure the AI agent uses specialized knowledge rather than general training data.
- For complex tasks spanning multiple technical domains within iOS development.
When not to use this skill
- For tasks that do not involve coding, code review, or code modification.
- When the required knowledge is general-purpose and not domain-specific.
- If the task falls outside the areas covered by the indexed skill library (e.g., non-Swift/iOS specific languages or frameworks).
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/maestro/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How maestro Compares
| Feature / Agent | maestro | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | easy | N/A |
Frequently Asked Questions
What does this skill do?
Maestro is an intelligent skill knowledge gateway that routes AI coding agents to precise, relevant expertise from a vast indexed library before any coding task, preventing context overload. It ensures specialized knowledge is applied, not just general training data.
How difficult is it to install?
The installation complexity is rated as easy. You can find the installation instructions above.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
SKILL.md Source
# Maestro — Skill Knowledge Gateway
## Critical Rule
BEFORE writing, reviewing, or modifying any code, ALWAYS call the `search_skills` MCP tool first. This retrieves precise, relevant knowledge from the indexed skill library. Do NOT rely on general knowledge when skill-specific expertise is available.
```
EVERY task → search_skills("description of what you need") → apply knowledge → respond
```
## How to Use
### Step 1: Search for Knowledge
Call the MCP tool with a description of what you need:
```
search_skills("Sendable conformance warning in actor class")
search_skills("SwiftUI @Observable state management pattern")
search_skills("write unit tests with Swift Testing #expect")
search_skills("NavigationStack deep linking coordinator pattern")
```
Tips for good queries:
- Include the specific problem: `"Fix Sendable warning"` not just `"concurrency"`
- Include the context: `"in actor class"` or `"for view model"`
- For compound tasks, make multiple calls:
```
search_skills("SwiftUI login form @Observable")
search_skills("async authentication network request")
search_skills("unit test login view model mock")
```
### Step 2: Apply Retrieved Knowledge
The tool returns 5–7 relevant chunks with:
- Which skill and file they come from
- The section and heading path
- The actual content with code examples and patterns
Apply this knowledge directly. Do not announce "according to the skill…" — just use the patterns naturally.
### Step 3: For Complex Tasks
If a task spans multiple domains, make multiple search calls:
| Task | Searches needed |
|------------------------|------------------------------------------|
| `"Build login screen"` | UI + auth + networking + testing |
| `"Fix data race"` | concurrency + actors + sendable |
| `"Add new feature"` | architecture + UI + testing |
| `"Performance audit"` | performance + SwiftUI + profiling |
## When MCP Is Not Available
If the `search_skills` tool is not available (e.g., Claude.ai without MCP):
1. Ask the user to run:
```bash
maestro context "description of task"
```
2. User pastes the output into the conversation
3. Apply the retrieved knowledge
Alternatively, the user can run:
```bash
maestro search "query"
```
to see results interactively.
## Skill Index
These are the skills available in the knowledge base. Use this index to understand WHAT is available, then call `search_skills` to get the ACTUAL content.
<!-- SKILL_INDEX_START -->
<!-- This section is auto-generated by `maestro index`. -->
<!-- Each entry is: skill name | domains | description summary -->
| Skill | Domains | Covers |
|----------------------|-----------------------------------|---------------------------------------------------------------------------------------------|
| ab-test-store-listing | ab-test-store-listing | When the user wants to A/B test App Store product page elements to improve conversion rate. Also use when t... |
| app-analytics | app-analytics | When the user wants to set up, interpret, or improve their app analytics and tracking. Also use when the us... |
| app-launch | app-launch | When the user wants to plan a launch strategy for a new app or major update. Also use when the user mention... |
| app-marketing-context | app-marketing-context | When the user wants to create or update their app marketing context document. Also use when the user mentio... |
| app-store-featured | app-store-featured | When the user wants to get featured on the App Store or understand the editorial process. Also use when the... |
| asc-build-lifecycle | asc-build-lifecycle | Track build processing, find latest builds, and clean up old builds with asc. Use when managing build reten... |
| asc-cli-usage | asc-cli-usage | Guidance for using the App Store Connect CLI in this repo (flags, output formats, pagination, auth, and dis... |
| asc-id-resolver | asc-id-resolver | Resolve App Store Connect IDs (apps, builds, versions, groups, testers) from human-friendly names using asc... |
| asc-metadata-sync | asc-metadata-sync | Sync and validate App Store metadata and localizations with asc, including Fastlane format migration. Use w... |
| asc-release-flow | asc-release-flow | End-to-end release workflows for TestFlight and App Store using asc publish, builds, versions, and submit c... |
| asc-signing-setup | asc-signing-setup | Set up bundle IDs, capabilities, signing certificates, and provisioning profiles with the asc CLI. Use when... |
| asc-submission-health | asc-submission-health | Preflight App Store submissions, submit builds, and monitor review status with asc. Use when shipping or tr... |
| asc-testflight-orchestration | asc-testflight-orchestration | Orchestrate TestFlight distribution, groups, testers, and What to Test notes using asc. Use when rolling ou... |
| asc-xcode-build | asc-xcode-build | Build, archive, and export iOS/macOS apps with xcodebuild before uploading to App Store Connect. Use when y... |
| aso-audit | aso-audit | When the user wants a full ASO health audit, review their App Store listing quality, or diagnose why their ... |
| changelog-generator | changelog-generator | Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing cha... |
| code-analyzer | code-analyzer | Read-only code analysis for architecture review and code quality assessment. Use when reviewing PRs or anal... |
| competitor-analysis | competitor-analysis | When the user wants to analyze competitors' App Store strategy, find keyword gaps, or understand competitiv... |
| context-optimization | context-optimization | Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent... |
| creating-pr | creating-pr | Use when creating or updating pull requests with comprehensive descriptions and meaningful commits - stream... |
| dogfood | dogfood | Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when ask... |
| feature-marker | feature-marker | Platform-agnostic workflow automation with checkpoints (PRD/TechSpec/Tasks generation + implementation + te... |
| find-skills | find-skills | Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill f... |
| frontend-design | frontend-design | Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the ... |
| keyword-research | keyword-research | When the user wants to discover, evaluate, or prioritize App Store keywords. Also use when the user mention... |
| localization | localization | When the user wants to localize their App Store listing for international markets. Also use when the user m... |
| maestro | maestro | Intelligent skill knowledge gateway. Routes tasks to the right knowledge without loading all skills into co... |
| metadata-optimization | metadata-optimization | When the user wants to optimize App Store metadata — title, subtitle, keyword field, or description. Also u... |
| monetization-strategy | monetization-strategy | When the user wants to design or optimize their app's monetization — pricing, paywalls, subscriptions, or i... |
| peon-ping-config | peon-ping-config | Update peon-ping configuration — volume, pack rotation, categories, active pack, and other settings. Use wh... |
| peon-ping-log | peon-ping-log | Log exercise reps for the Peon Trainer. Use when user says they did pushups, squats, or wants to log reps. ... |
| peon-ping-toggle | peon-ping-toggle | Toggle peon-ping sound notifications on/off. Use when user wants to mute, unmute, pause, or resume peon sou... |
| peon-ping-use | peon-ping-use | Set which voice pack (character voice) plays for the current chat session. Automatically enables agentskill... |
| remotion-best-practices | remotion-best-practices | Best practices for Remotion - Video creation in React |
| retention-optimization | retention-optimization | When the user wants to reduce churn, improve user engagement, or increase lifetime value. Also use when the... |
| review-management | review-management | When the user wants to analyze, respond to, or improve their app reviews and ratings. Also use when the use... |
| screenshot-optimization | screenshot-optimization | When the user wants to design, optimize, or evaluate App Store screenshots and preview videos. Also use whe... |
| swift-code-reviewer-skill | swift-code-reviewer-skill | Perform thorough code reviews for Swift/SwiftUI code, analyzing code quality, architecture, performance, se... |
| swift-concurrency | swift-concurrency | Expert guidance on Swift Concurrency best practices, patterns, and implementation. Use when developers ment... |
| swift-expert | swift-expert | Swift specialist for iOS/macOS development with Swift 6.0+, SwiftUI, async/await concurrency, and protocol-... |
| swift-testing | swift-testing | Expert guidance on Swift Testing best practices, patterns, and implementation. Use when developers mention:... |
| swift-testing-expert | swift-testing-expert | Expert guidance for Swift Testing: test structure, #expect/#require macros, traits and tags, parameterized ... |
| swiftui-expert-skill | swiftui-expert-skill | Write, review, or improve SwiftUI code following best practices for state management, view composition, per... |
| ua-campaign | ua-campaign | When the user wants to plan or optimize paid user acquisition campaigns. Also use when the user mentions "A... |
| xcodebuildmcp-cli | xcodebuildmcp-cli | Official skill for the XcodeBuildMCP CLI. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test,... |
| zellij-specialist | zellij-specialist | Terminal multiplexer specialist for layout design, plugin development, and session management |
<!-- SKILL_INDEX_END -->
## Domains Covered
The knowledge base covers these domains (use these terms in your searches):
- **concurrency** — async/await, actors, Sendable, Task, isolation, data races, Swift 6
- **ui** — SwiftUI views, state management, modifiers, layout, navigation, sheets
- **testing** — Swift Testing, @Test, #expect, mocks, stubs, fixtures, parameterized
- **state-management** — @Observable, @State, @Binding, @Environment, property wrappers
- **performance** — view updates, ForEach optimization, lazy loading, profiling
- **security** — Keychain, credentials, force unwrap safety, input validation
- **architecture** — MVVM, TCA, dependency injection, repository pattern, coordinators
- **error-handling** — typed throws, Result, guard, do-catch patterns
- **navigation** — NavigationStack, coordinators, deep linking, sheets
- **migration** — Swift 5→6, breaking changes, deprecated API replacement
## Auto-Indexing
The RAG engine automatically indexes skills when:
- First `search_skills` call (empty index detected)
- Skills are modified (file hash change detection)
- Explicit: `maestro index` command
No manual indexing step is required for normal use.Related Skills
laravel-expert
Senior Laravel Engineer role for production-grade, maintainable, and idiomatic Laravel solutions. Focuses on clean architecture, security, performance, and modern standards (Laravel 10/11+).
debug-nw
Debug a Nativewind v5 setup issue. Walks through common configuration problems with metro, babel, postcss, and dependencies.
Go Production Engineering
You are a Go production engineering expert. Follow this system for every Go project — from architecture decisions through production deployment. Apply phases sequentially for new projects; use individual phases as needed for existing codebases.
Database Engineering Mastery
> Complete database design, optimization, migration, and operations system. From schema design to production monitoring — covers PostgreSQL, MySQL, SQLite, and general SQL patterns.
afrexai-code-reviewer
Enterprise-grade code review agent. Reviews PRs, diffs, or code files for security vulnerabilities, performance issues, error handling gaps, architecture smells, and test coverage. Works with any language, any repo, no dependencies required.
API Documentation Generator
Generate production-ready API documentation from endpoint descriptions. Outputs OpenAPI 3.0, markdown reference docs, and SDK quickstart guides.
bili-rs
Development skill for bili-rs, a Rust CLI tool for Bilibili (B站). Use when implementing features, fixing bugs, or extending the bilibili-cli-rust codebase. Provides architecture conventions, API endpoints, coding patterns, and project-specific constraints. Triggers on tasks involving adding CLI commands, calling Bilibili APIs, handling authentication, implementing output formatting, or working with the layered cli/commands/client/payloads architecture.
Puppeteer
Automate Chrome and Chromium with Puppeteer for scraping, testing, screenshots, and browser workflows.
pharaoh
Codebase knowledge graph with 23 development workflow skills. Query architecture, dependencies, blast radius, dead code, and test coverage via MCP. Requires GitHub App installation (read-only repo access) and OAuth authentication. Connects to external MCP server at mcp.pharaoh.so.
git-commit-helper
Generate standardized git commit messages following Conventional Commits format. Use this skill when the user asks to commit code, write a commit message, or create a git commit. Enforces team conventions for type prefixes, scope naming, message length, and breaking change documentation.
ask-claude
Delegate a task to Claude Code CLI and immediately report the result back in chat. Supports persistent sessions with full context memory. Safe execution: no data exfiltration, no external calls, file operations confined to workspace. Use when the user asks to run Claude, delegate a coding task, continue a previous Claude session, or any task benefiting from Claude Code's tools (file editing, code analysis, bash, etc.).
bnbchain-mcp
Interact with the BNB Chain Model Context Protocol (MCP) server. Blocks, contracts, tokens, NFTs, wallet, Greenfield, and ERC-8004 agent tools. Use npx @bnb-chain/mcp@latest or read the official skill page.