CI/CD

Use when completing implementation, before escalating to human review, or when human checkpoint is reached - performs AI-assisted code review covering security, AI-specific issues, logic errors, and architecture to ensure humans see fresh analysis

Use when someone needs a rapid overview of all 12 animation principles in under 5 minutes

Post-deployment validation and health check scripts for validating HTTP endpoints, APIs, MCP servers, SSL/TLS certificates, and performance metrics. Use when deploying applications, validating deployments, testing endpoints, checking SSL certificates, running performance tests, or when user mentions health checks, deployment validation, endpoint testing, performance testing, or uptime monitoring.

Use when creating prompts for Claude or other LLMs, need help structuring prompts effectively, want to improve prompt quality, or need templates for simple or complex prompting tasks. Provides Anthropic's official 10-component framework, best practices for Claude 4.x models, and ready-to-use templates.

Safe deployment of Polymarket trading bot with regression tests and active trade protection

Execute surgical code refactors using single, named refactoring patterns with test verification. Use only when user explicitly requests to refactor code or perform a specific refactoring pattern. Analyzes complexity, establishes test baseline, previews changes with quality checks, executes refactoring, and verifies tests still pass.

实现关注点分离，确保不同职责模块化和边界清晰。当需要架构分层设计、模块职责划分、横切关注点处理时使用。覆盖层次分离、功能分离、横切关注点三大维度，提供分离检查清单和耦合问题的诊断修复方法。

Create detailed implementation plans through interactive research and iteration. Use this skill when needing to plan a feature, refactor, or bug fix before implementation. The skill orchestrates research agents (codebase-locator, codebase-analyzer, codebase-pattern-finder) to understand the codebase, then works collaboratively with the user to produce comprehensive technical specifications with phased implementation steps and success criteria.

Manage Temporal workflows: server lifecycle, worker processes, workflow execution, monitoring, and troubleshooting for Python SDK with temporal server start-dev.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Use when building, deploying, or setting up notebooks. Covers Makefile targets (make build, make data, make etl), GitHub Actions workflows, CI/CD, and creating new notebook repositories.

This skill should be used when the user asks about "ActiveRecord", "database queries", "query optimization", "N+1 queries", "eager loading", "associations", "migrations", "database indexes", "SQL performance", "ActiveRecord callbacks", "scopes", or needs guidance on efficient database access patterns in Rails 7+.

Design a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features

Use ONLY when user explicitly requests updating Node.js and pnpm versions - systematically updates package managers in all locations (frontend, backend, CI/CD) and verifies versions against official sources. Never use proactively.

19-agent team structure, decision trees for agent selection, Haiku vs Sonnet model selection, and agent collaboration principles. Use when deciding which sub-agent to invoke, understanding team responsibilities, or learning multi-agent orchestration.

Search and retrieve information from indexed PDF documentation including IC datasheets, FPGA manuals, and technical specifications. Use this when the user asks about hardware specifications, pin configurations, register details, timing diagrams, or any technical information that might be in datasheets or technical documentation.

Clean Code principles adapted for C#/.NET including naming, variables, functions, SOLID, error handling, and async patterns. Use when: (1) reviewing C# code, (2) refactoring for clarity, (3) writing new code, (4) code review feedback.

Write self-documenting code with minimal, evergreen comments that explain why, not what. Use this skill when deciding whether to add comments or when reviewing existing comments. When writing docstrings, inline comments, or documentation blocks. When avoiding comments that describe recent changes, temporary fixes, or obvious code behavior.

Guide for MUSUBIX SDD (Specification-Driven Development) workflow. Use this when asked to develop features using MUSUBIX methodology, create requirements, designs, or implement code following the 9 constitutional articles.

Build and deploy this Next.js application with PostgreSQL database. Use when building, deploying, setting up database, or preparing the project for production.