Claude Skills

Spawns AI coding agents in isolated git worktrees. Use when the user asks to spawn or launch an agent, delegate a task to a separate agent, work in a separate worktree, or parallelize development across features.

Use when working with Lean 4 (.lean files), writing mathematical proofs, seeing "failed to synthesize instance" errors, managing sorry/axiom elimination, or searching mathlib for lemmas - provides build-first workflow, haveI/letI patterns, compiler-guided repair, and LSP integration

This skill should be used when working on Lean 4 formalization projects to maintain persistent memory of successful proof patterns, failed approaches, project conventions, and user preferences across sessions using MCP memory server integration

This skill should be used when the user asks to "review code", "find dead code", "check for duplication", "simplify the codebase", "find refactoring opportunities", "do code cleanup", "check naming consistency", "analyze test organization", "run codebase health check", "review my PR", "refactor this code", "extract method", "rename variable", or "consolidate duplicates". Routes to specialized analysis agents or refactoring workflow based on the type of request.

Socratic thinking partner for decisions, debugging mental models, and working through uncertainty. This skill should be used when the user says "I'm stuck", "should I", "can't decide", "not sure if", "is this the right approach", "what do you think about", "help me think through", "review my plan", "am I missing something", "what am I assuming", "let me think", "brainstorm", "help me figure out", "sanity check", "does this make sense", or expresses uncertainty about a decision, design, or direction. Activates dialectical reasoning to surface assumptions, challenge positions, and find the right question to ask.

Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project memory optimization".

Generate and edit images using the Gemini API (Nano Banana Pro). Use this skill when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples: websites, landing pages, dashboards, React components, Astro components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

myfy web routing with FastAPI-like decorators. Use when working with WebModule, @route decorators, path parameters, query parameters, request bodies, AuthModule for authentication, RateLimitModule for rate limiting, or error handling.

myfy module protocol, lifecycle phases, and extension patterns. Use when creating new modules, working with configure/extend/finalize methods, module dependencies, or using WebModule, DataModule, FrontendModule, TasksModule, UserModule, CliModule, AuthModule, or RateLimitModule.

myfy DataModule for database access with async SQLAlchemy. Use when working with DataModule, AsyncSession, database connections, connection pooling, migrations, or SQLAlchemy models.

myfy TasksModule for background job processing with SQL-based queue. Use when working with TasksModule, @task decorator, background jobs, task workers, TaskContext, task retries, or async task dispatch.

Core myfy patterns and conventions for building applications. Use when working with myfy.core, Application, WebModule, DataModule, FrontendModule, TasksModule, UserModule, CliModule, AuthModule, RateLimitModule, or @route decorators.

myfy CliModule for custom CLI commands with DI injection. Use when working with CliModule, @cli.command decorator, command groups, CLI arguments, CLI options, or myfy app commands.

myfy dependency injection with scopes (SINGLETON, REQUEST, TASK). Use when working with @provider decorator, DI container, scopes, injection patterns, or understanding how WebModule, DataModule, FrontendModule, TasksModule, UserModule, CliModule, AuthModule, and RateLimitModule use dependency injection.

myfy UserModule for authentication with email/password, OAuth, sessions, and JWT. Use when working with UserModule, BaseUser, OAuth providers, login, registration, password reset, email verification, or user authentication.

Use when Playwright scripts fail, tests are flaky, selectors stop working, or timeouts occur - provides systematic debugging approach for browser automation issues

Use when writing or reviewing tests - covers test philosophy, condition-based waiting, mocking strategy, and test isolation

Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes

Use when writing tests for serialization, validation, normalization, or pure functions - provides property catalog, pattern detection, and library reference for property-based testing

Use when beginning any design process - orchestrates gathering context, clarifying requirements, brainstorming solutions, and documenting validated designs to create implementation-ready design documents

Use when creating or developing anything, before writing code or implementation plans - refines rough ideas into fully-formed designs through structured Socratic questioning, alternative exploration, and incremental validation

Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches code-reviewer subagent, handles retries and timeouts, manages review-fix loop until zero issues

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions