Explore skills

Claude Code Skills

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Reduces token waste by eliminating verbose pleasantries, fluff, and unnecessary meta-commentary. Activates when the user mentions reducing token usage, being more concise, avoiding fluff, cutting废话, or optimizing response length. Use this skill to minimize overhead in responses. Delivers maximally succinct, no-surplus-word answers without repeating user input, prefacing actions, or adding unreques

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

在需要对任意 SKILL 做资深质量评审、客观评分、交付把关、引入前审查、安全边界检查、故障复盘或修正复评时使用。适用于判断 SKILL 是否可被正确触发、按步骤执行、稳定产出、可验收、可维护、可复用，并输出证据化评分、问题优先级、修正方案、最终判定和复评闭环。

Use when you have a spec or requirements for a multi-step task, before touching code

配置和管理 Claude Code 底部常驻 HUD 状态栏。显示 CPU、内存、磁盘、温度、天气、Git 分支、时间、中文语录。支持彩色显示、自定义内容。关键词：hud、状态栏、statusline、底部显示、系统监控、语录、天气、彩色。

Use when executing implementation plans with independent tasks in the current session

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes