Claude Skills

Use when implementation is complete, all tests pass, and you need to integrate the work - validates, updates docs, and creates PR

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

This skill helps you master Customer Relationship Management (CRM) and customer data. Use it to unify customer data, automate marketing and sales, integrate your martech stack, and set strategic goals. Triggers: CRM, customer data, marketing automation, sales automation.

Use PROACTIVELY when searching past Claude Code conversations, analyzing development patterns, or generating activity reports. Automatically processes conversation history from the project, enables RAG-powered semantic search, and generates insight reports with pattern detection. Provides optional dashboard for visualization. Not for real-time analysis or cross-project searches.

Use PROACTIVELY when reviewing CLAUDE.md configurations, onboarding new projects, or before committing memory file changes. Validates against official Anthropic documentation, community best practices, and LLM context optimization research. Detects security violations, anti-patterns, and compliance issues. Not for runtime behavior testing or imported file validation.

Use PROACTIVELY when setting up end-to-end testing, debugging UI issues, creating visual regression suites, or automating browser testing. Uses Playwright with LLM-powered visual analysis, screenshot capture, and fix recommendations. Zero-setup for React, Next.js, Vue, Node.js, and static sites. Not for unit testing, API-only testing, or mobile native apps.

Use PROACTIVELY when working on multiple branches simultaneously or creating parallel Claude Code sessions. Automates git worktree creation with prerequisite checking, development environment initialization, and safe cleanup. Supports single worktree, batch creation, and worktree removal. Not for non-git projects or branch management without worktrees.

Use PROACTIVELY when user needs to create a new GitHub repository or set up a project with best practices. Automates repository creation with four modes - quick public repos (~30s), enterprise-grade with security and CI/CD (~120s), open-source community standards (~90s), and private team collaboration with governance (~90s). Not for existing repo configuration or GitHub Actions workflow debugging.

Test-driven development for Spring Boot using JUnit 5, Mockito, MockMvc, Testcontainers, and JaCoCo. Use when adding features, fixing bugs, or refactoring.

Use when needing to analyze images (screenshots, diagrams, photos), analyze videos (screencasts, recordings), summarize YouTube videos, fetch and analyze web content, or perform web searches with Google. Gemini CLI provides multimodal and web access capabilities Claude lacks natively. Do NOT use for tasks Claude can handle directly (text analysis, code review, file reading of text files).

This agent helps optimize for organic search features like featured snippets, rich snippets, and local packs to improve search engine visibility. Use this skill to improve your website's performance in Google search results.

A comprehensive skill for A/B split test engineering, following Neil Patel's methodology. It covers test prioritization (ICE scoring), statistical significance, sample size, hypothesis formation, variable isolation, multivariate vs. A/B decisions, test documentation, and conversion lift calculation. Use this skill to optimize web pages, ads, and emails for higher conversion rates.

ElevenLabs text-to-speech with mac-style say UX.

当用户提供飞书项目 MCP URL 或请求配置飞书项目 MCP 时触发。自动同时配置到 Claude Code 和 Cursor，简化团队成员的环境设置流程。支持查询项目任务、工作项、需求等。

AI 驱动的代码审查能力，当用户提到代码审查、code review、审查代码、查看代码质量等关键词时自动触发。使用 9 个并行 Agent 进行全维度分析（Bug/质量/安全/性能）。

simple|medium|large (optional, default medium)

Feature key (REQUIRED - e.g., BLOCKS, THEME_DISTRICT)