Каталог навыков агентов

コーディング担当エージェント「Codex」を起動します。中上級者のコーディングエージェントとして、コード実装・設計・技術課題解決を担当します。

Provides Codex CLI delegation workflows for complex code generation and development tasks using OpenAI's GPT-5.3-codex m...

Delegate coding tasks to Codex CLI for execution, or discuss implementation approaches with it. CodeX is a cost-effectiv...

Delegate coding to OpenAI Codex CLI (features, PRs).

This skill should be used when the user asks to "run codex", "ask GPT", "GPT review", "codex review", "codex exec", or n...

Run bulk/mechanical work on gpt-5.5 via the Codex CLI.

Orchestrates OpenAI Codex CLI from Claude Code via tmux. Use when delegating implementation tasks to Codex, running /cod...

OpenAI Codex CLI wrapper — three modes. (gstack)

Structured spec-driven workflow for planning and executing software projects with Codex CLI.

Get a second opinion from OpenAI Codex CLI. Use when you want to cross-check your reasoning, validate a plan, or get an...

Should be skipped for codex host.

OpenAI Codex CLIを使用してコードレビュー・分析を実行するスキル。

Multi-AI second opinion via OpenAI Codex CLI. Three modes: Review (pass/fail gate), Challenge (adversarial edge-case fin...

Codex-ready install target for the feature-marker run-through skill workflow. Use from a Codex prompt; the npm package i...

OpenAI Codex CLI 包装器。支持 review、challenge、consult 三种模式： 独立 code review、对抗式挑战、以及带会话连续性的开放咨询。 (gstack)

当用户明确要求直接操作 Codex CLI 作为后台代理（自选 sandbox、codex review、apply、resume 等原生命令，或用 git worktree 并行布置多个 worker）做代码分析、编辑、审查时使用。普通的...

Codex CLI（OpenAI）を使用してコードや文言について相談・レビューを行う。 トリガー: "codex", "codexと相談", "codexに聞いて", "コードレビュー", "レビューして" 使用場面: (1) 文言・メッセ...

Run OpenAI Codex CLI as a subagent for second opinions, code reviews, and questions. Use when you want a different AI mo...

Get a second opinion from OpenAI Codex CLI on a plan or approach. Use when: (1) During planning phase of /x-as-pr or /x-...

Run an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, liveview) on t...

Use this after Codex claims an implementation is done, or when the user wants to verify whether a product, feature, MVP,...

Route ONE bounded, mechanical task to the Codex CLI as a non-Claude executor, under the same review-before-merge gate as...

Use when a solution, paper claim, experiment pipeline, prompt, workflow, or UI needs hostile scenario testing before bei...

Advisory consultation skill for architectural reviews, design decisions, code analysis, and technology evaluation. Codex...

Get a second opinion from OpenAI Codex CLI for plan reviews, code reviews, architecture decisions, and hard problems. Us...

This skill should be used when the user asks for a "GPT second opinion", wants a "cross-model review", needs to "check a...

作为项目经理操作 OpenAI Codex CLI 完全体。包含：知识库维护（自动跟踪 Codex 最新功能）、任务执行（提示词设计→执行→监控→质量检查→迭代→汇报）、配置管理（feature flags/模型/skills/MCP）。通...

Run Codex CLI as an independent coding worker for implementation, investigation, planning, or review, then monitor and v...

Use when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debu...

Run Codex tasks via the ai_cli Task Tool runner.

Delegate coding tasks to Codex AI for implementation, analysis, and alternative solutions. Use when you need a second AI...

Convert Claude Code agent-kit setups into Codex-compatible skills, project instructions, guardrail scripts, command work...

Set up and run Codex custom subagent orchestration for software projects. Use when a user wants a project-local `.codex/...

Команда специализированных агентов для разработки: планирование, архитектура, исправление ошибок, тесты, ревью, документ...

通过 Codex CLI 进行代码审查、算法设计、架构分析和性能优化。适用于复杂技术任务、系统级设计、性能瓶颈分析。触发词：代码审查、review、算法设计、架构分析、性能优化。

Use when working code or generated content feels AI-bloated, noisy, repetitive, over-abstracted, fallback-heavy, generic...

Anthropic Codex API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended think...

Consolidate Codex macOS app automation worktrees and surface actionable changes. Use for morning triage and to review re...

Create Codex threads and send messages into Codex desktop-app (GUI) threads, then wait for and read their replies, so Cl...

Use when Codex needs Fable approval through an ATM/NTM validator pane. Triggers: - codex approval - ask fable - fable pl...

Codex architecture consulting (third brain). Get Codex architecture advice during design phase, forming dual perspective...

Ask OpenAI Codex questions about code to understand implementations, architecture, patterns, and debugging. Use when the...

Deliberative consultation with Codex CLI. Ask, evaluate, critique, iterate until workable agreement.

Run AI-powered tasks using OpenAI Codex CLI. Use when Claude needs to (1) delegate code analysis or generation tasks to...

Use Codex CLI for sandboxed auditing, debugging, and autonomous prototyping

Setup and manage OpenAI Codex CLI authentication including ChatGPT Plus/Pro OAuth, API keys, and multi-account managemen...

Use Codex CLI Full Auto for unattended, sandboxed prototyping and refactors.

Run repeated, measured Git experiments toward a numeric target; keep improvements and revert failures. Use for autonomou...

Triage improvement work and run or resume accepted measured loops in a local project. Architecture, documentation, UX, p...

Keep a Codex orchestrator's delegation to an installed delegate skill pending until its registered relay completes, with...

Interactive beginner walkthrough for learning the physical mechanics of VS Code and Codex, including folders, Explorer,...

Adversarial brainstorming. Claude and Codex independently research then debate until Nash equilibrium. For solution expl...

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work — guides completio...

Use when user wants to ask Codex, get GPT's opinion, get a second opinion from OpenAI, compare perspectives, have Codex...

Diagnose GitHub bug reports in openai/codex. Use when given a GitHub issue URL from openai/codex and asked to decide nex...

Delegates coding tasks from Codex to local Claude Code in print mode while preserving Claude's normal runtime customizat...

Interactive REPL workflows with Codex CLI including session management, multimodal conversations, and automated executio...

Use when user wants to ask Codex a question, get a second opinion, or consult with gpt-5.2. Triggers on phrases like "as...

Dual-AI engineering loop orchestrating Claude Code (planning/implementation) and Codex (validation/review). Use when (1)...

Use when driving a gated build loop where Claude orchestrates and Codex CLI implements — Claude plans and judges, Codex...

Integrate OpenAI Codex CLI into Claude Code for AI collaboration, code generation, and automated development. Use when w...

Invoke OpenAI Codex CLI for second-opinion code review, approach validation, and task verification. Use when you need cr...

OpenAI Codex CLI orchestration for AI-assisted development using gpt-5.2-codex model. Capabilities: code generation, ref...

OpenAI Codex CLI fundamentals for code analysis, review, and validation. Use when (1) executing codex commands for code...

Run OpenAI Codex CLI for coding tasks and second-opinion audits. Use when a user asks to run/ask/use Codex, says "codex...

Drive OpenAI's Codex CLI (`codex exec`) as a non-interactive coding sub-agent from inside Claude Code. Load WHENEVER you...

When handing work to the Codex CLI earns its cost, and how to size the run: second-model review, bounded implementation...

Executes tasks using the Codex CLI (`codex`). Automatically determines the least privilege required (Read-Only, Editor,...

Claude Agent, Tool, Workflow creation tool

Single source of truth and librarian for ALL OpenAI Codex CLI documentation. Manages local documentation storage, scrapi...

Load when a non-Codex agent should call OpenAI Codex CLI/Desktop as an external coding lane for implementation, review,...

Use Codex CLI (not MCP) to review uncommitted changes. Codex explores the codebase independently with full disk read acc...

Internal helper contract for calling the codex-companion runtime from Claude Code

Helps you to run a subagent using codex exec

Start and health-check the agent-ebpf-filter Codex Cloud frontend or docs development services without elevated kernel p...

Help the user work with Codex: improve prompts, provide project context, choose available tools and evaluate results. Us...

Automate code review remediation loops with the codex CLI. Requests reviews from codex, classifies findings by severity...

Use when the user asks for code review, PR review, merge readiness, quality/security/maintainability assessment, review...

Code review skill with rubric and templates

Route production coding tasks from Claude Code to the user-level Codex Shell, TypeScript, Python, or Rust workflow throu...

Use for code review and quality feedback from Codex. Triggers on "codex review code", "codex code review", "have codex r...

Delegate tasks to Codex — run prompts, code review, research, pair programming, or any collaboration mode. Use when the...

Background dual-agent collaboration with Codex CLI. Sends tasks to Codex via `codex exec` in the background, captures JS...

【WHEN】当用户命令中明确包含"codex协作"、"codex协同"、"与codex合作"等指令时启用； 【WHEN】当用户要求使用 codex MCP 工具进行代码分析、原型生成、review 等协作开发场景时启用。 【WHEN NOT...

Take over, hand off to, or collaborate with an OpenAI Codex CLI session from Claude Code or another agent. Use when the...

Codex MCP 协作流程专家（协同完成需求→原型→实现→审查），强调批判性思考与只读安全。

Show how many context compactions the current or other terminal-attached Codex sessions have undergone. Use when the use...

Use when the user wants Codex to carry a task through implementation, verification, cleanup, and final evidence instead...

Manages OpenAI Codex CLI configuration including config.toml settings, MCP servers, model profiles, sandbox modes, appro...

Use for multi-perspective analysis with Codex exploring different viewpoints. Triggers on "codex perspectives", "pros an...

Use when the user wants a decision-complete plan before implementation, especially for code, thesis, experiment, documen...

Get a second opinion from OpenAI Codex on documents, specs, or plans. Use for cross-AI consultation on any content, not...

Run Codex CLI inside a Podman container with full internet access but filesystem exposure limited to the repo root + exp...

Generate and load multi-layer project context documentation to reduce AI hallucination. Use before any task on a project...

Invoke Codex CLI as a coworker for implementation, brainstorming, specs, and reviews. Use when you want parallel thinkin...