Use when user asks to leverage codex, gpt-5, or gpt-5.1 to implement something (usually implement a plan or feature designed by Claude).
Run a minimal Codex CLI smoke test (opt-in, uses real tokens). Not part of the normal test suite.
Запускает Codex в режиме Triple Solution Finder: находит OBVIOUS (простой/проверенный), NON-OBVIOUS (неожиданный), и BEST (оптимальный) вариант решения любой задачи.
Use when one milestone is too large for a single spec or plan and needs several brainstorm-and-plan rounds before it ships — a long, multistage effort spanning sessions where the…
Check the current status of Codex collaboration. Use when user says codex status, check codex, or collaboration status.
Canonical Codex stop workflow. Use /sidekick:codex-stop to deactivate delegation and return to direct host behavior.
Use after major visual changes to Codex Studio when a screenshot or local URL is available. Judges whether the rendered page reads as a senior 3D design portfolio or a generic…
Use for Codex Studio GSAP, ScrollTrigger, SplitText, Lenis, animation, preloader, custom cursor, hover, reduced-motion, case-view reveal, and motion bug work.
Use before publishing, committing, pushing, or opening a PR for any Codex Studio code change. Replaces the former Claude /ship command with Codex-native review plus `npm run…
Launch Codex CLI as an isolated subagent for bounded coding, review, or verification tasks.
Choose Codex subagent roles and dispatch strategy. Use immediately before spawning only when the user explicitly requests subagents, delegation, parallel agents, or parent-model…
Coordinate bounded agent work when delegation helps; define ownership, authority, handoffs, and integration.
Spawnt N parallele Codex-Agents via tmux, orchestriert von Claude Opus 4.6. Jeder Agent laeuft in eigener Worktree mit konfigurierbarem Modell und Prompt.
Codex CLIワーカーエージェントを起動してタスクを実行する。 Claude CodeがオーケストレーターとしてCodexを呼び出すハイブリッド構成。 トリガー: 「Codexで実行」「Codexに任せて」「並列でCodex」「高速に処理」
Run in-session task loops via the codex-taskloop-plugin MCP server and stop hook.
Use for deep multi-step investigation and analysis with Codex. Triggers on "codex deep analysis", "investigate with codex", "codex thorough investigation", "have codex think…
Use when watching, monitoring, following, or supervising one or more live Codex tasks or threads by ID, including cursor-based transitions, completion or attention gates, claim…
Use to surface Codex features the user is not using but should, tuned to the friction they describe. Trigger when the user says "what can Codex do", "is there a better way", "I…
Use for Codex work with clear excess-cost risk: broad or unpredictable logs and diffs, browser/UI loops, subagents, repeated compaction, or explicit usage audits.
Execute and manage Codex CLI tools including file operations, shell commands, web search, and automation patterns.
Запускает Codex в режиме Brian Tracy Strategic Clarity: находит A1-приоритет, frog-задачу, что исключить. Для кода, проекта, backlog, застревания в ступоре.
Use when the user asks about Codex token usage, model/reasoning efficiency, usage dashboards, CSV exports, or per-session/per-turn Codex usage stats from local logs.
Use built-in Codex coordination, retrieval, and utility tools effectively during live sessions. Trigger when work benefits from maintaining a step plan, asking the user 1-3 short…
Create and personalize a new local Codex Vault when the user asks for a persistent Markdown second brain or a new memory vault. Do not use for modifying an existing vault.
Configure and troubleshoot OpenAI Codex in VS Code and VS Code-compatible IDEs. Use when adding Codex project instructions, installing standards for the Codex VS Code extension,…
Recover pasted screenshot images in Windows Codex Desktop when the message says a C:\Users\...\Temp\codex-clipboard-*.png file could not be read.
Route implementation tasks to OpenAI Codex in a sandboxed container for autonomous code churn
Run deterministic multi-step agent workflows in Codex — fan-out, parallel, schema-validated structured output — via the codex-workflow MCP orchestrator (run_workflow), with native…
Review recent agent work, memory summaries, rollout notes, repeated failures, and workflow friction to decide which lessons should become durable skills, instructions, helper…
Run OpenAI Codex CLI as a subagent for second opinions, code reviews, and questions. Use when you want a different AI model's perspective.
Zero Data Retention mode for sensitive/proprietary code - no code stored on OpenAI servers
Use when Codex, Hermes, OpenClaw, Claude Code, Cowork, or another AI agent needs to plan, review, implement, audit, or improve email work focused on repo-aware email impl — from…
OpenAI Codex CLI configuration guide for Claude. Use when users ask about: codex config, ~/.codex/config.toml, codex sandbox policies, codex approval modes, creating codex skills,…
Summarize support tickets, chats, and customer threads into issue, impact, status, owner, and next response.
Run a Codex-native planning and implementation loop with docs/plans progress tracking, MEMORY.md failure memory, per-task git worktrees, and iterative verification until tasks…
Use the CodexPet pixel companion asset pack in local app, web, desktop-pet, or UI work. Trigger when the user asks for CodexPet, a pet character, a companion mascot, or…
Use when planning repo work with evidence-backed comprehension, autopsy, ontology, ledger continuity, QA audit, and gated handoff.
Codicilli: nachtraegliche letztwillige Verfuegungen im roemischen Recht. Skill behandelt die ad-hoc-Form ihre Bindung an ein bestehendes Testament und die Bedeutung für L — from…
Codicilli: nachtraegliche letztwillige Verfuegungen im roemischen Recht. Skill behandelt die ad-hoc-Form ihre Bindung an ein bestehendes Testament und die Bedeutung für L — from…
Scans a repo for disciplines that exist only in prose, convention, or agent memory but are NOT enforced by executable code, then codifies each into the right surface — a script, a…
Skills para desenvolvimento de software, debug, APIs, automações no-code e uso avançado de ferramentas de IA para desenvolvimento.
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…
1. 创建网页需要先根据拿到的数据设计数据库结构，需要调用工具在数据库中建立结构。…
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control. — from majiayu000/claude-skill-registry
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control. — from ndesv21/awesome-openclaw-skills-1
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control. — from kalibr-ai/skills
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control. — from kalibr-ai/skills
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control. — from majiayu000/claude-skill-registry
Construction d'agents de coding autonomes capables de lire, écrire et modifier du code. Se déclenche avec "coding agent", "agent de code", "agent développeur", "Devin", " — from…
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control. — from majiayu000/claude-skill-registry
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control. — from majiayu000/claude-skill-registry
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control. — from majiayu000/claude-skill-registry
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control. — from user/repo.git
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control. — from majiayu000/claude-skill-registry
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control. — from kalibr-ai/skills
Plan, assign, review, and verify coding-agent work with tight scope control and clear acceptance criteria.
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control. — from majiayu000/claude-skill-registry
Direct and supervise a coding agent (Claude Code, Cursor, Antigravity) so it ships correct, verified work.
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…