開發

Build OpenCode plugins, agents, hooks, and tools. Use when creating, reviewing, or debugging OpenCode extensions. Covers plugin architecture, agent configuration, lifecycle hooks, custom tools, and distribution. Invoke PROACTIVELY when user mentions OpenCode plugins, agents, hooks, or wants to extend OpenCode functionality.

Validates project after initialization. Checks static files, endpoints, CSS, health.Use when: after rust-project-init, before TDD loop.Triggers: "validate project", "check project", "verify init".

Builds full-stack applications with Payload CMS, the Next.js-native headless CMS. Use when creating content-driven apps with TypeScript, code-first configuration, and full control over your backend.

Review React hook usage for React 19 compliance and best practices

Use when generating PDFs from markdown with Pandoc - covers differences from Python-Markdown, blank line rules, fix scripts for labels/anchors/metadata, and visual testing workflow

This skill should be used for thorough AI review via Codex CLI (gpt-5.2-max). Triggers include architectural decisions, blocking issues, final review before done, or when consult-light escalates due to low confidence.

Create CrewAI workflows as NestJS applications under apps/crewai/. FUTURE: Same pattern as LangGraph - NestJS app, same webhook pattern as n8n, receive same parameters, wrap as API agents. CRITICAL: Status webhook URL must read from environment variables.

Fast code generation agent optimized for speed and iteration

Enforce comprehensive deployment verification after deploying code, scripts, or configurations. Use after any deployment, build, or installation operation. Prevents deployment verification failures (FP-9).

Swift code style conventions for clean, readable code. Use when writing Swift code to ensure consistent formatting, naming, organization, and idiomatic patterns.

Conversion rate optimization (CRO) patterns for Next.js applications including CTA design, landing page layouts, trust signals, form optimization, pricing tables, and A/B testing. Use when building landing pages, optimizing CTAs, adding social proof, or improving conversion funnels.

Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive discovery, and optimization for signal-to-noise ratio.

MoAI-ADK's foundational principles - TRUST 5, SPEC-First TDD, delegation patterns, token optimization, progressive disclosure, modular architecture, agent catalog, command reference, and execution rules for building AI-powered development workflows

Deploy the resume app to Cloudflare Pages using the documented build and wrangler steps. Use when deploying, troubleshooting deploys, or updating Pages-related CI configuration.

Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates

Solved issues, common errors, and debugging techniques for LMS. Use this skill when debugging issues, understanding error codes, fixing RLS problems, or troubleshooting environment variable issues.

Zustand state management for React Native. Use when implementing client-side state.

Use when capturing screenshots, automating browser interactions, or scraping web content. Covers Playwright Python API for page navigation, screenshots, element selection, form filling, and waiting strategies.

SwiftUIを使ったiOSアプリのUI実装を支援するスキル。View +

Comprehensive code review specialist providing security analysis, performance optimization, maintainability assessment, and best practice recommendations across multiple programming languages