Skill permission analysis, one-time authorization, analyze skill permissions, batch authorization

Safe Rust refactoring with LSP analysis. Triggers on: /refactor, rename symbol, move function, extract, 重构, 重命名, 提取函数, 安全重构

CRITICAL: Use for concurrency/async. Triggers: E0277 Send Sync, cannot be sent between threads, thread, spawn, channel, mpsc, Mutex, RwLock, Atomic, async, await, Future, tokio, deadlock, race...

Professional technical SEO audit that analyzes crawlability, Core Web Vitals, site architecture, mobile readiness, security, structured data, and AI crawler configuration. Use when auditing...

Every resource must have clear ownership and lifetime. Use when reviewing resource management, subscriptions, or cleanup code.

Use when building .NET 10 or C# 14 applications; when using minimal APIs, modular monolith patterns, or feature folders; when implementing HTTP resilience, Options pattern, Channels, or...

OpenTelemetry observability - use for distributed tracing, metrics, instrumentation, Sentry integration, and monitoring

Safely merge GitHub pull requests using comprehensive pre-merge validation. Use this skill when the user asks to merge a PR, complete a PR workflow, or check if a PR is ready to merge. Validates...

Next.js performance optimization and best practices. Use when writing Next.js code (App Router or Pages Router); implementing Server Components, Server Actions, or API routes; optimizing RSC...

Orchestrate RED-GREEN-REFACTOR TDD phases. Use when starting TDD, managing phase transitions, or maintaining TDD discipline across a development session.

>

Redis data structures and commands including strings, lists, hashes, sets, sorted sets, streams, and transactions for high-performance caching and real-time applications.

Create responsive layouts using CSS Grid, Flexbox, media queries, and mobile-first design. Use when building adaptive interfaces that work across all devices.

以資深架構師思維執行開發，強調測試先行、深度上下文分析與防禦性編程，確保代碼的高質量與可維護性。

Guides agents through using the Jujutsu (jj) version control system. Activate when the user mentions jj, jujutsu, or when working in a repository with a .jj directory. Teaches proper workflow for...

Execute beads autonomously within a track. Handles bead-to-bead context persistence via Agent Mail, uses preferred tools from AGENTS.md, and reports progress to orchestrator.

Orchestrate lawyer agents to review code for compliance with codebase laws. Spawns counsel in parallel to produce a unified legal brief.

Infrastructure as Code using Terraform with modular components, state management, and multi-cloud deployments. Use for provisioning and managing cloud resources.

Comprehensive guide for using Claude Agent SDK to build AI agents that can read files, execute commands, edit code, and perform complex workflows. Use when (1) Building autonomous AI agents with...

This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.