Development

Best practices for writing clear, actionable error messages in code.

When css being written or edited.

Provides coding style rules for Python and PowerShell. Apply when writing, editing, reviewing, or debugging code.

My personal best practices for writing clear and effective code comments.

Generate coding-aider plans as created by the IntelliJ coding-aider plugin. Use when user explicitly asks for a "coding-aider plan", "aider plan", or needs structured development planning with checklist tracking and file context management.

Spawn and control external coding agents (Claude Code, Codex, OpenCode, Pi) for delegating tasks. Use when (1) user asks to run another coding agent, (2) delegating subtasks to a different AI tool, (3) running multiple agents in parallel on separate issues, (4) spawning an agent in an isolated environment or worktree, (5) user mentions "codex", "opencode", "pi agent", or running "another claude".

Garante padrões de código HTML limpo, semântico e consistente. Use quando criar ou modificar arquivos HTML, estruturar páginas, ou o usuário mencionar HTML, tags, atributos, ou estrutura de código.

Validate architecture/plan quality via claude-delegator (Plan Reviewer expert). Use after writing context.md for complex feature/refactor work.

Validate integration impact and regression risks via claude-delegator (Code Reviewer expert). Use for complex tasks or API integration.

Leverage OpenAI Codex/GPT models for autonomous code implementation. Triggers: "codex", "use gpt", "gpt-5", "gpt-5.2", "let openai", "full-auto", "用codex", "让gpt实现".

Codex CLI用のスキル作成ガイド。YAML frontmatter、ディレクトリ構造、ベストプラクティスを解説。Use when creating new Codex skills, updating existing skills, or learning about Codex skill development.

Lisp machine self-modification patterns via MCP Tasks and Narya bridge types

Search the web using OpenAI Codex CLI to find current documentation, best practices, solutions, and technical information. Use when the user needs to research libraries, find API documentation, troubleshoot errors, or learn about new technologies. Requires Codex CLI installed.

Architect-level guidance, workflows, and scripts for building agentic coding systems with OpenAI Codex. Use for Codex SDK (@openai/codex-sdk) threads + streaming JSONL events; Codex CLI automation (codex exec, output schema, JSONL, resume); MCP server usage (codex mcp-server) and dynamic tool integration; multi-agent orchestration with OpenAI Agents SDK (handoffs, gating, tracing); durable state, caching, and memory using SQLite; safe-by-default sandbox/approval patterns and execpolicy rules.

Run code in Codex fully isolated sandbox - network disabled, CWD only, Seatbelt/Docker isolation

Review implementation quality and regression risks via claude-delegator (Code Reviewer expert). Use after implementation for complex tasks, refactors, or API changes.

Review implementation quality and regression risks via claude-delegator (Code Reviewer expert). Use after implementation for complex tasks, refactors, or API changes.

Use when the user asks how to structure Codex skills (folders, SKILL.md, supporting files), wants plugin-dev-like organization, or needs conventions for templates/scripts bundled with a skill.

- **Name:** codex-law-enforcement - **Category:** Governance & IRP - **Version:** 1.0.0

Use Codex CLI in full-auto mode to fix issues iteratively until tests pass. Autonomous debugging and test-fixing loop with sandbox safety.

Invoke OpenAI Codex CLI with the correct configuration for autonomous code generation. Use when you need Codex to generate or regenerate code files, implement features, or execute multi-step coding tasks.

Codex CLI를 sub-agent로 활용하여 실제 구현 작업을 수행합니다. Claude가 작업을 분석/분해하고, Codex가 코드 작성/수정/리팩토링을 담당합니다. "Codex로 구현", "구현해줘", "코드 작성해줘", "병렬 구현" 요청 시 활성화됩니다.

Execute development tasks using OpenAI Codex CLI for code generation, refactoring, feature implementation, and bug fixes. Use when the user asks to create code, add features, refactor, fix bugs, or generate tests. Requires Codex CLI installed.

Consult Codex for architectural decisions. Use when: (1) introducing patterns not in codebase, (2) 3+ design options exist, (3) performance-critical implementation, (4) major refactoring. Get risk assessment before coding.