“codex”的搜索结果

Find current official documentation for OpenAI products and APIs, then get concise guidance with source citations. Use it to check implementation approaches, model capabilities, and limits, with code examples grounded in the documentation.

中文简介正在准备中。当前显示英语简介。

• Check how to implement features with Responses API
• Look up Codex usage
• Explore how to build ChatGPT apps with Apps SDK

Compare a feature implemented in Qwen Code with Codex or Claude Code under the same scenario. Capture communication and terminal records, inspect tool definitions and outputs, and guide fixes toward matching observable behavior.

中文简介正在准备中。当前显示英语简介。

• Checking a reproduced feature against its reference agent
• Comparing tool definitions and required arguments
• Investigating differences in terminal output

Review board memos and strategy briefs with available Claude, Codex, and Gemini models. Compare concerns, supporting arguments, and votes, then turn disagreements into questions to resolve before committing to a major business decision.

中文简介正在准备中。当前显示英语简介。

• Reviewing fundraising terms before signing
• Checking the reasoning behind a major strategic pivot
• Examining an acquisition memo before a decision

Create or update Codex skills that package specialized knowledge, repeatable workflows, and tool instructions. The guide covers concrete use cases, folder structure, reusable resources, starter generation, and basic validation of names and required metadata.

中文简介正在准备中。当前显示英语简介。

• Turning recurring work into a reusable skill
• Packaging company knowledge and API instructions
• Reorganizing an existing skill and its reference files

Evaluate changes to OpenSEO skills by running fresh Codex sessions against a local backend. Compare saved reports using weighted criteria, then inspect tool logs to understand failures and check whether revised instructions improve output.

中文简介正在准备中。当前显示英语简介。

• Comparing report quality before and after skill edits
• Checking revised instructions across different websites
• Scoring SEO audit reports against defined criteria

Connects supported AI clients, including Claude Code and Codex, to OpenWork through MCP, a protocol for accessing external tools. It guides account sign-in and verifies that tools for finding and running organization capabilities are available.

中文简介正在准备中。当前显示英语简介。

• Connecting an AI client to OpenWork organization resources
• Signing in and verifying available MCP tools
• Switching organizations or troubleshooting authentication

Delegate development tasks to external coding agents such as Codex and Claude Code through command-line tools. Choose local or container execution, check setup, provide a self-contained task brief, and inspect important changes afterward.

中文简介正在准备中。当前显示英语简介。

• Delegating project work to a local coding agent
• Running a coding agent inside an Agent Zero container
• Checking CLI setup before assigning a task

Improve research code, results, and paper drafts through repeated review by a second Codex agent. The workflow implements fixes, checks them again, and records assessments and unresolved issues across up to four rounds.

中文简介正在准备中。当前显示英语简介。

• Improve research before submitting a paper
• Repeat fixes and reviews of experimental results
• Track unresolved concerns across review rounds

Turn method notes or figure descriptions into academic architecture and concept illustrations. Claude plans and reviews the layout, while a local Codex bridge generates images, with refinement rounds and final PNG, LaTeX snippet, and review records.

中文简介正在准备中。当前显示英语简介。

• Illustrating a model architecture for a paper
• Turning method notes into a workflow diagram
• Creating concept or comparison figures

Use Codex to send emails, create issues, post messages, and update data in connected apps through Composio CLI, a terminal tool. It supports services including Gmail, Slack, GitHub, and Notion.

中文简介正在准备中。当前显示英语简介。

• Send emails through Gmail
• Create GitHub issues
• Post updates to Slack

Create or update Codex skills that package specialized knowledge, repeatable workflows, and tool instructions. The guide covers concrete use cases, folder structure, reusable resources, starter generation, and basic validation of names and required metadata.

中文简介正在准备中。当前显示英语简介。

• Turning recurring work into a reusable skill
• Packaging company knowledge and API instructions
• Reorganizing an existing skill and its reference files

Create or review SECURITY.md guidance so Codex Security understands what to examine, which protections must hold, and what is excluded. Compare existing policies with repository evidence and preview proposed changes before writing.

中文简介正在准备中。当前显示英语简介。

• Define security review scope for a repository
• Document required security protections
• Check whether existing guidance matches the code

Guide changes to RDD reviewer integrations through a shared Go contract, a common set of processing rules. Define adapter boundaries, validate result handling, and check that runtime migrations preserve existing review outcomes.

中文简介正在准备中。当前显示英语简介。

• Moving reviewer invocation into a shared Go contract
• Checking that adapters only invoke reviewers and return raw output
• Verifying review outcomes during a runtime migration

Evaluate a local Codex plugin to understand its scores and identify what to fix first. Review stronger and weaker skills, prepare benchmark runs, compare saved results across versions, and produce a readable report.

中文简介正在准备中。当前显示英语简介。

• Review an entire plugin before comparing versions
• Understand scores and prioritize fixes
• Compare strengths and weaknesses across included skills

Improve an evaluated Codex skill by turning plugin-eval findings into prioritized changes. Refine activation descriptions, shorten SKILL.md, move lengthy details into supporting files, fix structural issues, and compare evaluation results before and after the rewrite.

中文简介正在准备中。当前显示英语简介。

• Prioritizing fixes after a skill evaluation
• Shortening SKILL.md and reducing token use
• Clarifying when a skill should activate

Run repeated, independent security audits of a repository or selected directory with Codex Security. It combines validated findings into a report that records the reviewed scope, exclusions, and any incomplete coverage.

中文简介正在准备中。当前显示英语简介。

• Run repeated security audits across a repository
• Audit a specific directory
• Combine validated findings from independent scans

Build remote MCP servers, which let AI agents call external tools, on Cloudflare Workers. This skill covers server code, tool definitions, OAuth authentication, local testing, deployment, and connecting a Codex client.

中文简介正在准备中。当前显示英语简介。

• Building a remote MCP server
• Adding OAuth authentication to MCP tools
• Exposing external APIs as tools for AI agents

View and interact with an iOS Simulator inside the Codex browser. Display SwiftUI previews from importable Swift packages, see source edits update the running preview, and capture screenshots to document the visible results.

中文简介正在准备中。当前显示英语简介。

• Viewing and interacting with an iOS app in the browser
• Checking SwiftUI previews outside Xcode Canvas
• Iterating on package previews with hot reload

Audit Claude, Codex, or Pi configuration, instruction conflicts, hooks, and MCP connections to external tools. It also checks safeguards for maintaining AI-assisted projects and returns prioritized findings with evidence and concrete corrective or diagnostic steps.

中文简介正在准备中。当前显示英语简介。

• Investigate agent settings or instructions that seem ineffective
• Audit hooks, MCP connections, and permission boundaries
• Check verification gaps and stale project guidance

Guides migration of historical SWE-Marathon agent configurations to the shared Codex runtime. It preserves native tasks, verification rules, and scoring while outlining environment checks and restrictions on retired execution methods.

中文简介正在准备中。当前显示英语简介。

• Migrating historical SWE-Marathon agent configurations
• Preserving task and scoring rules during migration
• Checking the native environment before a full run

Check whether an Ouroboros update is available and upgrade after the user chooses to proceed. The native updater preserves the installation manager, environment, and optional dependencies, then provides restart guidance for the host integrations.

中文简介正在准备中。当前显示英语简介。

• Checking for an available Ouroboros update
• Upgrading while preserving the installation configuration
• Refreshing both Claude Code and Codex integrations

Review a project’s past Codex sessions, saved memory, and existing skills to identify recurring workflows. Receive prioritized recommendations for updating incomplete skills or creating distinct new ones, grounded in actual project history.

中文简介正在准备中。当前显示英语简介。

• Choosing which project skills to create next
• Finding outdated or incomplete skill instructions
• Turning recurring checks into reusable skill candidates

Create or update Codex skills that package specialized knowledge, repeatable workflows, and tool instructions. The guide covers concrete use cases, folder structure, reusable resources, starter generation, and basic validation of names and required metadata.

中文简介正在准备中。当前显示英语简介。

• Turning recurring work into a reusable skill
• Packaging company knowledge and API instructions
• Reorganizing an existing skill and its reference files

Diagnose whether a Codex Desktop update changed codexhost Composer/CDP bindings, private Renderer DOM or React state, Host bridges, routing, the Codex usage submission gate, or injected UI. Use after an installed Codex update or when compatibility regresses and the affected surface is unknown.

中文简介正在准备中。当前显示原文说明。