claude-marketplace

Build frontend interfaces with externally randomized style direction. Use when the user asks to build web components, pages, or applications with high design diversity. Produces distinctive, production-grade UI that avoids repetitive AI aesthetics.

Analyzes CLAUDE.md, AGENTS.md, and similar repository context files for effectiveness based on peer-reviewed research. Identifies instructions that hurt agent performance, redundant content, and unnecessary requirements. Use when reviewing a CLAUDE.md, auditing an AGENTS.md, optimizing context files, or when the user says "lint my CLAUDE.md", "review my AGENTS.md", "is my context file good", "optimize my context file", or "check my CLAUDE.md".

Complete reference for Claude Code skill YAML frontmatter fields, their values, and best practices. Use when writing frontmatter for SKILL.md, configuring skill invocation, setting allowed-tools, or deciding on skill metadata fields.

Interactive guide for creating new Claude Code skills from scratch. Use when building a new skill, creating a SKILL.md, designing skill structure, or when the user says "create a skill", "build a skill", "make a new skill", or "help me write a skill".

Common patterns and architectures for building Claude Code skills. Use when deciding how to structure a skill, choosing between skill patterns, designing multi-step workflows, or when the user asks "what kind of skill should I build" or "how should I structure this skill".

Guide for packaging Claude Code skills as distributable plugins. Use when creating a plugin, packaging skills for sharing, setting up a plugin marketplace, or when the user says "make a plugin", "package my skills", "distribute skills", or "create a marketplace".

Reviews and validates existing Claude Code skills for correctness, quality, and best practices. Use when reviewing a skill, auditing SKILL.md files, checking skill quality, or when the user says "review this skill", "validate my skill", "check my SKILL.md", or "is this skill correct".

Diagnoses and fixes common problems with Claude Code skills. Use when a skill is not working, not triggering, triggering too often, instructions are ignored, or when the user says "my skill doesn't work", "skill not loading", "fix my skill", or "debug this skill".

Covers XState v5 event emitter pattern for outward-facing events. Use when emitting events to external handlers via emit() action, subscribing to emitted events with actor.on(), or typing emitted events. Available since XState 5.9.0.

Covers XState v5 Inspect API and developer tools. Use when debugging actor systems, inspecting state transitions, integrating Stately Inspector, or observing actor lifecycle events and microsteps.

Covers XState v5 state persistence and restoration. Use when saving/restoring actor state to localStorage, databases, or other storage, implementing deep persistence of actor hierarchies, or using event sourcing for state replay.

Covers XState v5 integration with SolidJS via @xstate/solid and @xstate/store-solid. Use when connecting XState machines or stores to Solid components, using useActor/useActorRef/fromActorRef hooks, or subscribing to store state as Solid signals.

Covers @xstate/store v3 — lightweight event-driven state management. Use when implementing simple stores with createStore(), atoms, effects, emitting events, selectors, undo/redo, or bridging stores with XState actors via fromStore().

Covers XState v5 actor systems for cross-actor communication. Use when registering actors with systemId, addressing actors globally via system.get(), designing system-wide communication, or managing actor hierarchies beyond parent-child.

Handles asynchronous data fetching in SolidJS using createResource with Suspense integration. Use when fetching data from APIs, managing loading/error states, or implementing optimistic updates in SolidJS.

Creates SolidJS components with correct prop handling, TypeScript types, and lifecycle management. Use when building components, passing props, handling children, or managing component lifecycle with onMount/onCleanup.

Uses SolidJS control flow components for conditional rendering, list rendering, error handling, and suspense. Use when rendering lists, showing/hiding content conditionally, handling errors, or working with async boundaries in SolidJS.

Implements SolidJS reactive patterns using signals, effects, and memos. Use when writing or reviewing SolidJS components, state management, or reactive code. Covers the core mental model: components run once, signals track in reactive scopes, and props must not be destructured.

Manages complex nested state in SolidJS using stores with fine-grained reactivity. Use when working with objects, arrays, nested data structures, or when integrating API responses into reactive state.

Covers XState v5 action types and side-effect patterns. Use when implementing entry/exit actions, assign() for context updates, raise(), sendTo(), enqueueActions(), or deciding where to place effects. Includes type-bound action helpers (v5.22+).

Covers TypeScript patterns for type-safe XState v5 machines. Use when setting up typed machines with setup(), typing context/events/input/output, using type-bound helpers (v5.22+), assertEvent(), or type helpers like ActorRefFrom and SnapshotFrom. Requires TypeScript 5.0+.

Covers XState v5 actor model, actor types, invocation, spawning, and communication. Use when choosing between promise/callback/observable/state-machine actors, implementing invoke vs spawn, designing parent-child communication, or managing actor lifecycle with input/output.

Ready-to-use XState v5 patterns for common scenarios. Use when implementing data fetching with loading/error/retry, form validation, authentication flows, debounce/throttle, retry with backoff, persistence, or CRUD with dynamic actors. Each pattern is a complete machine.

Teaches how to design and model XState v5 state machines from scratch using a systematic process. Use when starting a new state machine, deciding what should be a state vs context, choosing between actions and actors, or structuring events and states for a feature.

Covers XState v5 state types and context management. Use when implementing compound (parent/child) states, parallel states, history states, final states, or managing context with assign(). Includes hierarchy design, context initialization patterns, and state reading.

Covers testing strategies for XState v5 state machines. Use when writing unit tests for machines, testing transitions, mocking with provide(), using the pure transition() function, or testing actors with async operations. Includes patterns for Vitest/Jest.

Covers XState v5 event handling, transition types, and guard patterns. Use when implementing guarded transitions, delayed (after) transitions, eventless (always) transitions, self-transitions, wildcard events, or composable guard logic with and/or/not.