Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Add a "code mode" tool to an existing MCP server so LLMs can write small processing scripts that run against large API responses in a sandboxed runtime — only the script's compact output enters the LLM context window. Use this skill whenever someone wants to add code mode, context reduction, script execution, sandbox execution, or LLM-generated-code processing to an MCP server. Also trigger when users mention reducing token usage, shrinking API responses, running user-provided code safely, or adding a code execution tool to their MCP server — in any language (TypeScript, Python, Go, Rust, etc.).

YouTube Ads specific analysis covering campaign types, creative quality, audience targeting, and measurement. Evaluates video ad performance across skippable in-stream, non-skippable, bumper, Shorts, Demand Gen, and Connected TV (CTV) formats. Covers VAC→Demand Gen migration, Shorts creative requirements, CTV shoppable ads, and frequency capping. Use when user says YouTube Ads, video ads, pre-roll, bumper ads, skippable in-stream, YouTube campaign, YouTube Shorts ads, Demand Gen, VAC, or CTV YouTube ads.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Automatically generate TLA+ specifications from program code, repositories, or system implementations. Use when asked to generate TLA+ spec, create TLA+ specification from code, convert program to TLA+, formalize system in TLA+, extract TLA+ model from code, or when working with formal specification of concurrent systems, distributed systems, protocols, algorithms, or state machines that need to be verified.

Generate unit tests with proper mocking for Python (unittest.mock/pytest) or Java (Mockito/JUnit) code. Use when users request test generation, unit tests with mocks, or testing code that has external dependencies like database calls, API requests, file I/O, or network operations. Automatically identifies dependencies to mock and creates executable, maintainable test code.

Generates complete modules and components from interface contracts and specifications. Use when Claude needs to build larger software components, implement interfaces, create service layers, or generate complete modules with multiple related classes. Supports Python (with type hints and protocols) and Java (with interfaces and abstract classes). Trigger when users request "implement this interface", "generate a module for", "create a service layer", "build a component that implements", or provide interface definitions that need implementation.

Generate integration tests for multiple interacting components in Python. Use when testing interactions between: (1) Multiple services or APIs (REST/GraphQL endpoints, microservices), (2) Database operations with repositories/ORMs (SQLAlchemy, Django ORM), (3) External services (payment gateways, email services, third-party APIs), (4) Message queues and event-driven systems, (5) Full stack workflows (API + database + business logic). Provides test structure templates, fixtures, test data builders, and patterns for pytest-based integration testing.

Automatically repair buggy code and generate comprehensive tests for Python, Java, and C++ programs. Use when users need to fix logic errors or runtime errors in functions, modules, or repositories. Accepts specifications via natural language descriptions, existing test cases, or input/output examples. Generates corrected code, creates or updates tests to verify correctness and prevent regressions, and produces a detailed report explaining the bug, fix, and testing strategy. Triggers on requests like "fix this bug", "repair this code", "debug this function", or "this code is broken".

Generate abstract Control Flow Graph (CFG) representations of programs showing loops, branches, and function calls for static analysis or verification. Use when users need to: (1) Visualize program control flow structure, (2) Generate CFGs for static analysis tools, (3) Create control flow abstractions for formal verification, (4) Analyze program paths and reachability, (5) Document program structure. Supports both function-level (intraprocedural) and program-level (interprocedural) analysis with multiple output formats (textual, DOT/Graphviz, JSON).

Analyzes and optimizes code for better performance, memory usage, and efficiency. Use when code is slow, memory-intensive, or inefficient. Supports Python and Java optimization including execution speed improvements, memory reduction, database query optimization, and I/O efficiency. Provides before/after examples with detailed explanations of why optimizations work, complexity analysis, and measurable performance improvements.

Execute Juicebox production checklist. Trigger: "juicebox production", "deploy juicebox".

Implement Ideogram rate limiting, backoff, and request queuing patterns. Use when handling rate limit errors, implementing retry logic, or optimizing API request throughput for Ideogram. Trigger with phrases like "ideogram rate limit", "ideogram throttling", "ideogram 429", "ideogram retry", "ideogram backoff", "ideogram queue".

Migrate to Granola from Otter.ai, Fireflies, Fathom, tl;dv, or manual note-taking. Covers data export from source tools, parallel-run strategy, team transition, and historical data preservation. Trigger: "migrate to granola", "switch to granola", "granola from otter", "granola from fireflies", "replace meeting tool with granola".

Audit, upgrade, and maintain Grove test suites. Use when the user asks to "audit the test suite", "find untested examples", "upgrade dependencies", "check suite health", "find dead code", "clean up the test suite", "maintain Grove", "what examples are missing tests", or wants to analyze and improve the overall health of a Grove test suite.

Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.

This skill should be used when the user asks to "create a SwiftUI view", "build an iOS app", "set up an Xcode project", "review Apple platform code", "add a widget", "create a watchOS app", "build for visionOS", "fix SwiftUI layout", or when generating any Swift code targeting Apple platforms (iOS, iPadOS, macOS, tvOS, watchOS, visionOS). Provides modern SwiftUI-first best practices covering UI patterns, app lifecycle, navigation, project structure, and platform-specific guidance. Use together with `swift-development` for Swift language fundamentals. Always generates Swift unless the project explicitly requires Objective-C.