LLM 與 Agent

Use when relay fragment composition, data masking, colocation, and container patterns for React applications.

Use when modifying, removing, or refactoring code that lacks test coverage. Emphasizes the danger of untested changes and the RGR workflow to add characterization tests before modifications.

Use when creating temporary files, drafts, experiments, or any content that should not be committed to version control. Ensures proper placement in .claude/.scratch with gitignore configuration.

Use when configuring interactive controls and args for Storybook stories. Helps create dynamic, explorable component demonstrations with proper type constraints.

Use when scala collections including immutable/mutable variants, List, Vector, Set, Map operations, collection transformations, lazy evaluation with views, parallel collections, and custom collection builders for efficient data processing.

Use when nim's metaprogramming including macros, templates, compile-time evaluation, AST manipulation, code generation, DSL creation, and leveraging compile-time computation for performance and abstraction in systems programming.

Use when configuring Fnox providers for encryption and secret storage. Covers age encryption, cloud providers (AWS, Azure, GCP), and password managers.

Orchestrator for WebView UI mockup workflow - delegates design iteration to ui-design-agent and implementation scaffolding to ui-finalization-agent. Use when user mentions UI design, mockup, WebView interface, or requests 'design UI for [plugin]'.

Use when advanced Pytest features including markers, custom assertions, hooks, and coverage configuration.

Validates and configures all dependencies required for the Plugin Freedom System. This is a STANDALONE skill that runs BEFORE plugin workflows begin. It checks for Python, build tools, CMake, JUCE, and pluginval, optionally installing missing dependencies with user approval. Configuration is saved to .claude/system-config.json for use by other skills. Use when user mentions setup, installation, dependencies, missing tools, or when SessionStart hook detects configuration issues.

Orchestrates Stage 0 research and planning for JUCE plugins - creates architecture.md and plan.md contracts through subagent delegation. Use when creative brief exists and plugin needs DSP architecture specification, complexity assessment, or implementation planning. Invoke via /plan command, natural language (plan architecture, research DSP), or as first implementation step.

Use when gleam-Erlang interoperability including calling Erlang code from Gleam, using Erlang libraries, external functions, working with Erlang types, NIFs, and leveraging the BEAM ecosystem from Gleam applications.

Use when managing agent context, memory, and conversation state in Claude AI agents using the Agent SDK.

Use when working with Claude Code CLI, plugins, hooks, MCP servers, skills, configuration, or any Claude Code feature - provides comprehensive official documentation for all aspects of Claude Code

Use when advanced Jest features including custom matchers, parameterized tests with test.each, coverage configuration, and performance optimization.

Use when creating or configuring Claude AI agents using the Agent SDK. Covers agent initialization, configuration, and basic setup patterns.

This skill should be used when the user wants to add components (commands, agents, skills, hooks, or MCP servers) to the Component Reference section of the website.

Use when jest testing patterns including unit tests, mocks, spies, snapshots, and assertion techniques for comprehensive test coverage.

Use when nim-C interoperability including calling C from Nim, wrapping C libraries, importc/exportc pragmas, header generation, FFI patterns, and building high-performance systems code integrating Nim with existing C codebases.

Use when integrating tools, permissions, and MCP servers with Claude AI agents using the Agent SDK.