Skill Claude CodeCodex
A backend coding guide covering web APIs, databases, error handling, logging, and endpoint tests. Backend code runs on servers and handles data and application operations.
Skill Claude CodeCodex
A debugging workflow that reproduces a problem with a failing test, collects evidence, finds the underlying cause, applies a fix, and runs regression checks. Regression checks verify that the fix does not break behavior that already worked.
Skill Claude CodeCodex
A front-end coding guide for building components, styles, state handling, API calls, design-system integrations, and browser-based end-to-end tests. A design system is a project's shared set of visual rules and reusable interface parts.
Skill Claude CodeCodex
A coding workflow for checking requirements, understanding existing code, designing module boundaries, writing tests first, implementing changes, and reviewing risks. TDD means writing a failing test, making it pass, then improving the code.
Skill Claude CodeCodex
A checklist for mechanically reviewing code after implementation. It checks module boundaries, dependency cycles, requirement links, lint and type errors, security issues, and repeated or dead code.
Skill Claude CodeCodex
Generates production-grade Playwright automation scripts and E2E tests in TypeScript, JavaScript, Python, Java, or C#. Supports local execution and TestMu AI cloud across 3000+ browser/OS combinations and real mobile devices. Use when the user asks to write Playwright tests, automate browsers, run cross-browser tests…
Skill Claude CodeCodex
A guide for creating or changing agent configuration files. An agent is a configured software worker with a role, instructions, tools, limits, and status.
Skill Claude CodeCodex
A set of rules for creating or changing frontend visual themes through configuration. It covers colors, interface components, effects, backgrounds, naming, accessibility, and how preset themes are registered.
Skill Claude CodeCodex
A development guide for creating or changing built-in tools. It explains test-driven development (TDD), where tests are written before the code, along with naming, file paths, and required class methods.
Skill Claude CodeCodex
A process guide for creating and managing container tasks: larger, ongoing jobs such as building an app, game, or novel. It covers task planning, workspaces, progress checks, task chains, resources, failures, and completion.
Skill Claude CodeCodex
A planning skill for game projects. It helps structure a game design document, which describes the game's vision, mechanics, levels, systems, numbers, target platform, audience, and business model.
Skill Claude CodeCodex
A planning guide for fiction projects, including the story world, characters, plot outline, chapter structure, platform style, and publishing goals.
Skill Claude CodeCodex
A guide for planning research or investigation projects. It covers the research goal, decision to support, research questions, scope, methods, evidence quality, and report structure.
Skill Claude CodeCodex
A software planning guide for deciding how a project should be structured and built. It covers architecture, technology choices, modules, interfaces, requirements, and testing.
Skill Claude CodeCodex
A guide and script for turning task files and project documents into one self-contained HTML page. The page shows task status, dependencies, and how acceptance criteria (ACs) link back to tasks.
Skill Claude CodeCodex
A set of scripts that supports end-to-end testing, which checks a complete workflow across its connected parts. The scripts capture selected log messages, compare database snapshots, and record and verify notifications or other side effects.
Skill Claude CodeCodex
A set of scripts for managing information about tools and their execution records. It can clear stored execution data, collect tool details into a configuration file, and check that tool definitions match that configuration.
Agent
The execution engine for an AI agent built with LangGraph, a framework for connecting model decisions, tool calls, and state into a workflow. It accepts a user message, agent configuration, and registered tools, then returns a result or streamed events.