Essential command-line tools and system utilities.
Intelligence-first code analysis for bugs, architecture, performance, and security. Use proactively when investigating code issues, tracing dependencies, or understanding system behavior. MUST query project-intel.mjs before reading files.
Automatically release a new version. Detects current version, analyzes recent changes, suggests version bump (patch/minor/major), and executes release. Trigger when user says "请发版本", "release", "发版", "bump version".
Comprehensive QA engineer that designs test strategies, writes test cases, identifies edge cases, and validates implementations. Use when writing tests, reviewing test coverage, planning QA strategy, identifying edge cases, or validating feature implementations. Triggers include "write tests for", "test this feature", "what are the edge cases", "review test coverage", or "QA this".
Testing expert with comprehensive knowledge of test structure, mocking strategies, async testing, coverage analysis, and cross-framework debugging. Use PROACTIVELY for test reliability, flaky test debugging, framework migration, and testing architecture decisions. Covers Jest, Vitest, Playwright, and Testing Library.
Use when creating GitHub Actions workflows for CI/CD - testing, building, publishing npm packages, and automating repository tasks
git commit, push, PR作成を一括実行。新機能実装完了後やレビュー対応完了後に使用。メインエージェントのコンテキスト節約のため、定型的なPR作成フローをこのSkillに委譲する。
Guide for reviewing GitHub Actions for security vulnerabilities.
Automates test quality assessment, identifies vanity tests, and guides systematic improvement of test suites. Use when reviewing test suites, identifying shallow tests, enforcing behavioral test standards, or when the user mentions test quality, vanity tests, or test effectiveness.
Automates Git commit creation with Conventional Commits. Use when user wants to commit changes. (project)
Documentation check checkpoint for conductor gates. Analyzes code changes to determine if documentation needs updating. Returns structured result with pass/fail status and documentation suggestions.
Orchestrate Terraform and OpenTofu at scale using Terragrunt, Terramate, or Atmos. Use when managing multiple environments, implementing DRY configurations, handling cross-stack dependencies, deploying to many accounts, managing tool versions with TEnv, or establishing infrastructure platform patterns.
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.
Comprehensive performance benchmarking, regression detection, automated testing, and performance validation. Use for CI/CD quality gates, baseline comparisons, and systematic performance testing.
Patterns for testing local web applications using Playwright. Use when verifying frontend functionality, debugging UI behavior, capturing screenshots, or testing dynamic web apps. Provides decision tree for choosing approach, reconnaissance-then-action pattern, and multi-server testing.
Multi-repository git synchronization patterns for batch operations
Build reusable Terraform and OpenTofu modules and provider configurations for multi-cloud infrastructure, Kubernetes, CI/CD, databases, networking, security, observability, and virtualization. Use when creating infrastructure modules, generating module documentation with terraform-docs, standardizing provisioning, migrating from Terraform to OpenTofu, or implementing IaC patterns across 40+ providers.
Expert knowledge on CLI testing with auth bypass, automated endpoint testing, and the 3 bypass methods (headers, environment, test headers). Use this skill when user asks about "test endpoint", "cli testing", "auth bypass", "curl", "automated testing", "local development", or "testing without clerk".
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.
Develop custom Gitea Actions (composite or Docker-based). Use when creating reusable actions for Gitea, building action.yml files, packaging actions for distribution, or porting GitHub Actions to Gitea.
코드 품질 검증 스킬. Use when (1) 커밋 전 검증, (2) 린트/빌드/테스트 실행, (3) PR 전 품질 확인.
