“codex”的搜索结果

将反复交办的任务或专门流程整理为Codex技能，组织所需指令、参考资料和辅助脚本，用于创建新技能或改进已有技能的内容。

• 将重复任务整理成技能
• 改进已有技能的指令
• 整理参考资料和辅助脚本

Launch the example Remotion Studio locally and open it in Codex’s built-in browser. The workflow installs dependencies, builds the monorepo, and uses the URL reported by Studio to reach the correct running instance.

中文简介正在准备中。当前显示英语简介。

• Launching the example Remotion Studio
• Opening the local Studio interface in Codex
• Finding the correct Studio URL across working copies

Launch the Remotion documentation site locally and open it in the Codex in-app browser. The workflow installs dependencies, builds the project, starts Docusaurus, and reports the actual preview URL and server status.

中文简介正在准备中。当前显示英语简介。

• Launch the local Remotion documentation site
• Preview documentation changes in Docusaurus
• Open the documentation preview inside Codex

Compose compact, structured prompts for coding, debugging, review, and research with Codex or GPT-5.4. This internal skill defines task scope, completion criteria, output format, verification steps, and evidence requirements using consistent XML tags.

中文简介正在准备中。当前显示英语简介。

• Define implementation scope and completion criteria
• Include verification steps in debugging requests
• Specify evidence requirements for code reviews

Create a local Codex plugin scaffold with its required configuration file and optional folders. Generate or update marketplace entries to define display order, installation availability, and authentication timing before testing or publishing.

中文简介正在准备中。当前显示英语简介。

• Start a new local Codex plugin
• Add optional folders to a plugin
• Register a plugin in a local marketplace

Move supported Claude Code instructions, skills, agents, and MCP tool connection settings into Codex. The workflow inspects sources, previews changes, validates converted files, and reports items that need manual setup or review.

中文简介正在准备中。当前显示英语简介。

• Move project instructions and skills to Codex
• Convert slash commands into Codex skills
• Migrate agents, MCP connections, and supported hooks

Create animated Codex pets from character art, text ideas, or brand cues. Generate nine animation states, assemble a transparent sprite sheet, check appearance and movement, and package the results with a pet configuration file.

中文简介正在准备中。当前显示英语简介。

• Turn character art into an animated Codex pet
• Create a pet in plush, clay, or other non-pixel styles
• Design a mascot from company or brand cues

Switch PUA's narration to an encouragement-first style in Codex CLI through the equivalent of Claude Code's /pua:yes command. The skill preserves verification requirements and requires command or output evidence before reporting completion.

中文简介正在准备中。当前显示英语简介。

• Calling the equivalent of /pua:yes from Codex CLI
• Switching task narration to an encouraging style
• Keeping verification requirements while changing narration

Provides a Codex CLI alias for loading the mama coaching protocol. It switches visible narration to Chinese-mother nagging while retaining verification rules, and preserves unrelated configuration fields whenever it updates the PUA settings file.

中文简介正在准备中。当前显示英语简介。

• Loading mama mode from Codex CLI
• Changing narration while retaining verification rules
• Preserving unrelated settings when updating the configuration

Access the equivalent of Claude Code's /pua:pro command from Codex CLI. The alias invokes the pro protocol for self-improvement, KPI performance measures, and configuration commands, with all processing kept local.

中文简介正在准备中。当前显示英语简介。

• Calling the equivalent of /pua:pro from Codex CLI
• Using the pro protocol for self-improvement and KPI commands
• Managing PUA settings locally

Switch PUA to offline mode from Codex CLI. This alias updates the offline setting and sets feedback frequency to zero while preserving other configuration fields, then reports the mode change.

中文简介正在准备中。当前显示英语简介。

• Switching PUA to offline mode
• Setting feedback frequency to zero
• Calling the offline command from Codex CLI

Put Codex CLI in a technical lead role that writes task prompts and manages P8 execution through the p9 protocol. The agent stays focused on coordination and only implements code when explicitly reassigned.

中文简介正在准备中。当前显示英语简介。

• Assign a technical lead role in Codex CLI
• Write task prompts for P8 execution
• Keep coordination separate from code implementation

Use past local Codex sessions to propose updates to a selected skill and project memory file. Recurring tasks are replayed, changes are checked on separate validation tasks, and proposals are staged for review before adoption.

中文简介正在准备中。当前显示英语简介。

• Turn recurring Codex requests into skill updates
• Consolidate feedback into skills and project memory
• Compare validation scores before applying changes

Pin the current Codex session to a chosen model through Weave Router. This short alias accepts a model ID, runs the included script, and reports the router’s response while allowing the current turn to continue.

中文简介正在准备中。当前显示英语简介。

• Pinning a Codex session to a chosen model
• Using a short alias for force-model
• Checking the router’s response after pinning a model

Check whether Codex is using Weave Router or its default provider. This skill runs a status command and summarizes the result in one line without changing any configuration.

中文简介正在准备中。当前显示英语简介。

• Checking whether Codex uses Weave Router
• Checking whether the default provider is active
• Reviewing routing status without changing settings

SUPERSEDED by /claudex-loop (formerly /crucible; adds a Phase 0 research/recon pass + rebuilt interview) — prefer that skill unless you explicitly want this one. Two-act plan hardening. ACT 1 (you ↔ Claude) — Claude interviews you relentlessly about a plan or design, one question at a time, recommending an answer for each and exploring the codebase when it can answer itself, until every branch of the decision tree is resolved. ACT 2 (Claude ↔ Codex) — Claude writes the locked plan to PLAN.md and OpenAI Codex adversarially reviews it in a read-only sandbox (VERDICT:APPROVED/REVISE), Claude revises and re-submits to the SAME Codex session until APPROVED or a MAX_ROUNDS cap, then you sign off before any code. Use when the user says "/grill-me-codex", "grill me then have codex review", "grill me and stress-test the plan", "interview me about this plan then get a second model on it", or is about to build something high-stakes (auth, schema, concurrency, migrations, payments) and wants both alignment AND a cross-model sanity check before implementation. Builds on Matt Pocock's grill-me (MIT). For the docs-aware variant use /grill-with-docs-codex; if you already have a plan and want only the Codex review use /codex-review. NOT for reviewing already-written code (use /codex:review) and NOT for trivial changes.

中文简介正在准备中。当前显示原文说明。

Delegate a coding task to the OpenAI Codex CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Codex — phrasings like "have Codex do X", "delegate this to Codex", "run it through Codex", or "use Codex to implement/fix/refactor" — or to run a queue of coding tasks through Codex while staying the reviewer. Prefer it over a one-shot Codex forwarder (such as the codex-rescue agent) when the user will review the diff and commit it themselves. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.

中文简介正在准备中。当前显示原文说明。

Run an automated codex⇄Claude debate to consensus — no round cap, no deadlock exit. Two explicit subcommands. `review` (also the bare/back-compat default) — codex (reviewer) critiques the current diff and a Claude subagent (author) fixes/disputes, looping until they agree. `answer` — Claude and codex each answer a freeform prompt in parallel, then cross-check until they agree, and a unified answer is returned. Use when the user types `/codex-debate`, asks to "have codex review this", "run the codex debate", "review this PR with codex", "argue this with codex until you agree", or passes a question to "have Claude and codex debate/answer until they agree".

中文简介正在准备中。当前显示原文说明。

Provides Codex CLI delegation workflows for complex code generation and development tasks using OpenAI's GPT-5.3-codex models, including English prompt formulation, execution flags, sandbox modes, and safe result handling. Use when the user explicitly asks to use Codex for complex programming tasks such as code generation, refactoring, or architectural analysis. Triggers on "use codex", "delegate to codex", "run codex cli", "ask codex", "codex exec", "codex review".

中文简介正在准备中。当前显示原文说明。

将功能开发、大规模代码重构和拉取请求审查交给Codex、Claude Code或OpenCode在后台执行，并处理独立检出目录、进度监控及完成或失败通知。

• 将功能开发交给后台代理
• 在独立工作目录中进行大规模重构
• 请编码代理审查拉取请求

通过OpenAI Codex CLI完成现有项目的功能开发、代码重构和拉取请求审查。也涵盖长时间任务的进度检查，以及使用独立Git工作目录并行修复多个问题的步骤。

• 为现有项目添加功能
• 重构认证模块
• 审查拉取请求

Review estimated spending, token usage, and cache hit ratios across Claude Code, Codex, and Grok using local logs. Filter by time, project, or provider, while keeping currencies separate and identifying models without pricing.

中文简介正在准备中。当前显示英语简介。

• Reviewing estimated spending for the past seven days
• Comparing usage across providers and models
• Checking costs for a specific project or time range

Update Codex's pinned V8 and rusty_v8 versions, synchronize build settings and checksums, and validate a release candidate. If validation fails, investigate upstream changes and adjust the affected build files to restore a working build.

中文简介正在准备中。当前显示英语简介。

• Update Codex's pinned V8 and rusty_v8 versions
• Update prebuilt artifacts and checksums
• Validate a V8 release candidate

Find and install Codex skills from a curated catalog or a GitHub path. Check which skills are already installed, explore experimental options, and add skills from private repositories when credentials are available.

中文简介正在准备中。当前显示英语简介。

• Browse available skills and check installed ones
• Install a skill by name from the curated catalog
• Add a skill from a private GitHub repository