ghosttypes
- 22 skills
- 0 followers
- 8 hours ago last updated
- ▌ Mypy · ghosttypes bundleProfessional static type checking for Python with mypy (v1.19.1). Use when working with Python type hints, type annotations, or integrating mypy into codebases for: (1) Adding type annotations to Python code, (2) Configuring mypy (mypy.ini, pyproject.toml, setup.cfg), (3) Resolving mypy errors and type checking issues, (4) Using advanced type patterns (Generics, Protocols, TypedDict), (5) Running mypy in CI/CD or development workflows, (6) Creating or working with stub files, (7) Migrating existing codebases to typed Python, or (8) Any mypy-related development task.
- ▌ Pydantic Dev · ghosttypes bundleProfessional Pydantic v2.12 development for data validation, serialization, and type-safe models. Use when working with Pydantic for (1) creating or modifying BaseModel classes, (2) implementing validators and serializers, (3) configuring model behavior, (4) handling JSON schema generation, (5) working with settings management, (6) debugging validation errors, (7) integrating with ORMs or APIs, or (8) any production-grade Python data validation tasks. Includes complete API reference, concept guides, examples, and migration patterns.
- ▌ Github Actions · ghosttypes bundleComprehensive GitHub Actions workflow authoring skill. Enables Claude to write production-grade CI/CD workflows with latest best practices, syntax, and security patterns. Use when creating or modifying GitHub Actions workflows, designing CI/CD pipelines, configuring workflow triggers/events/schedules, implementing security patterns (secrets, OIDC, attestations), creating custom actions, migrating from other CI systems, troubleshooting failed workflows, or any GitHub Actions automation task. Includes complete reference documentation extracted from official GitHub docs with source URLs for verification.
- ▌ Sub Agent Creator · ghosttypes bundleInteractive sub-agent creation skill for Claude Code. Use when user wants to create a custom subagent or mentions needing a specialized agent for specific tasks. This skill guides the entire subagent creation process including identifier design, system prompt generation, skill/context selection, and writing properly formatted agent files to .claude/agents.
- ▌ Jest · ghosttypes bundleComprehensive JavaScript testing with Jest 30.0. Use when writing tests, debugging test failures, setting up Jest in projects, configuring test runners, mocking modules and functions, writing async tests, snapshot testing, framework integration with React or React Native, or any Jest-related task
- ▌ Biome · ghosttypes bundleComprehensive Biome (biomejs.dev) integration for professional TypeScript/JavaScript development. Use for linting, formatting, code quality, and flawless Biome integration into codebases. Covers installation, configuration, migration from ESLint/Prettier, all linter rules, formatter options, CLI usage, editor integration, monorepo setup, and CI/CD integration. Use when working with Biome tooling, configuring biome.json, setting up linting/formatting, migrating projects, debugging Biome issues, or implementing production-ready Biome workflows.
- ▌ Eslint · ghosttypes bundleProfessional-grade ESLint development for JavaScript and TypeScript projects. Use when working with ESLint for (1) configuring ESLint in projects, (2) understanding or fixing ESLint errors and warnings, (3) creating or modifying ESLint rules, (4) integrating ESLint into build systems or editors, (5) migrating ESLint configurations, (6) setting up custom parsers or plugins, (7) troubleshooting ESLint issues, (8) implementing code quality standards, or (9) any task involving ESLint setup, configuration, or usage. Covers all ESLint versions with focus on v9+ flat config format.
- ▌ Vitest · ghosttypes bundleComprehensive Vitest testing framework skill for writing, configuring, and running tests in JavaScript/TypeScript projects. Use when Claude needs to: set up Vitest in a new or existing project (Vite or non-Vite), write or modify tests using Vitest APIs, configure Vitest for specific scenarios (coverage, browser testing, mocking, etc.), migrate from Jest or older Vitest versions, debug test failures or configuration issues, implement advanced testing patterns (workspace, browser mode, snapshots, mocking).
- ▌ NPM To Pnpm · ghosttypes bundleMigrate projects from npm to pnpm including lockfile conversion, workspace setup, CI/CD updates, and troubleshooting. Use when converting a single package from npm to pnpm, migrating npm workspaces or monorepos, updating CI/CD pipelines for pnpm, troubleshooting issues after npm to pnpm migration, or converting package-lock.json to pnpm-lock.yaml.
- ▌ Typescript Best Practices · ghosttypes bundleTypeScript best practices and patterns for writing type-safe, maintainable code. Use when working with TypeScript files, configuring tsconfig, defining interfaces/types, implementing error handling, writing generics, or setting up type-safe communication patterns. Includes patterns for discriminated unions, type guards, utility types, and more.
- ▌ Get Time · ghosttypes bundleGet the current local time in various formats. Use when the user asks for the current time, what time it is, the date, or needs timestamp information. Works across claude.ai web, Claude Desktop, and Claude Code environments.
- ▌ MCP Setup · ghosttypesSet up MCP (Model Context Protocol) servers in Claude Code workspaces for testing. Use this skill when a user provides a local file path to an MCP server, a GitHub repository URL containing an MCP server, or asks to configure/install/set up an MCP server for testing. Handles creating .mcp.json configuration, cloning repositories, and guiding users through the setup process.
- ▌ Claudius Maximus · ghosttypes bundleSet up autonomous Claude Code loops (Ralph Wiggum pattern). Use when the user wants to run Claude continuously on a task until complete. Triggered by phrases like: run in a loop, autonomous agent, AFK coding, keep going until done, Ralph Wiggum loop, Claudius loop.
- ▌ MCP Test Harness · ghosttypes bundleBuild fully automated integration test suites for MCP (Model Context Protocol) servers using STDIO transport. Use when creating pytest tests for Python/FastMCP servers, Vitest tests for TypeScript servers, or using MCP Inspector CLI for universal testing. Triggers include "test my MCP server", "create MCP tests", "automated MCP testing", "integration tests for MCP", or any request to verify MCP server functionality with real data validation.
- ▌ Fastmcp V3 Migration · ghosttypes bundleProduction-ready migration from FastMCP v2.x to v3.0. Use when upgrading MCP servers built on FastMCP to v3, migrating legacy FastMCP code, converting v2 patterns to v3 architecture (providers/transforms), or when user mentions FastMCP upgrade, migration, or v3. Covers breaking changes, deprecated patterns, new v3 features (providers, transforms, versioning, authorization), and testing strategies. Ensures zero-regression migrations with user confirmation checkpoints.
- ▌ Claude Code Hooks · ghosttypes bundleInteractive skill for setting up Claude Code hooks in any workspace. Use when users want to configure hooks for Claude Code, create automation around tool execution, add notifications, format code automatically, protect files, validate commands, log operations, or customize Claude Code behavior. Triggers include "set up hooks", "create hook", "configure Claude Code", "add PreToolUse hook", "PostToolUse automation", "notification hook", "protect files from editing", or any request to automate Claude Code's behavior through hooks.
- ▌ Pytest · ghosttypes bundleComprehensive pytest testing framework skill for Python. Use when working with pytest tests, fixtures, parametrization, markers, assertions, configuration, plugins, or test discovery. Covers pytest 9.x with full API reference, how-to guides, best practices, and examples for writing, running, and debugging Python tests.
- ▌ Ruff Dev · ghosttypes bundleProfessional-grade Python development with Ruff (v0.14.10) - an extremely fast Python linter and formatter. Use when working with Python codebases for (1) linting and fixing code quality issues, (2) formatting Python code, (3) configuring Ruff settings, (4) understanding and resolving specific rule violations, (5) integrating Ruff into projects or editors, (6) migrating from other tools (Black, Flake8, isort, etc.), or (7) any Ruff-related development tasks. Includes complete documentation for 937+ lint rules, formatter settings, configuration options, and editor integrations.
- ▌ Best Practices · ghosttypes bundleUniversal software engineering best practices for any language or project. Use when programming, refactoring code, designing systems, reviewing code, or ensuring production-ready quality. Covers fundamental principles (SOLID, DRY, KISS, YAGNI), architectural patterns (SoC, SSOT, LoD, CQS, DbC), and operational reliability (ETC, PoLP, CoC, Idempotency). Apply when building new features, cleaning up codebases, improving maintainability, or ensuring code follows industry standards.
- ▌ Project Bootstrap · ghosttypes bundleBootstrap Claude Code setup for greenfield (new) or brownfield (existing) projects. Automatically detects project type, copies relevant skills from your skill library, and creates engineer agents with best practices skills. Use when starting work on a new project or wanting to upgrade an existing project's Claude Code setup with skills and agents.
- ▌ Home Assistant Dev · ghosttypes bundleComprehensive Home Assistant custom integration development skill. Use when developing Home Assistant integrations, custom components, or plugins. Covers entity platforms, config flows, data management, quality requirements, testing, and HACS publishing. Includes complete reference documentation for all 47+ entity types, integration quality scale requirements, and step-by-step publishing guides.
- ▌ Python Best Practices · ghosttypes bundleProduction-ready Python DOs and DON'Ts for engineers. Covers code quality, type hints, error handling, async patterns, testing, security, performance, logging, and data validation. Use when writing Python code that needs to be production-ready, reviewing Python code, refactoring legacy Python, or answering questions about Python best practices. Targets Python 3.12+.