OpenAI

查阅官方资料，提供附有来源的Codex设置、价格及OpenAI API与产品使用说明，也可用于模型选型、迁移规划、提示词调整和问题排查。

• 确认Codex设置并排查问题
• 比较模型的费用、速度和质量
• 规划模型迁移和提示词调整

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

以只读方式检查代码变更、相关测试及调用位置，找出变更新引入且需要修复的缺陷，并附上依据、严重程度和准确的文件位置。

• 检查尚未提交的代码变更
• 在合并前检查变更
• 查找特定提交引入的缺陷

生成照片风格图像、插画和产品效果图，也可替换现有图像的背景、移除多余物体或制作透明背景，并根据参考图探索不同方案。

• 制作网站主视觉图
• 预览产品或包装的成品效果
• 移除多余物体或替换背景

查看可添加到Codex的技能及其安装状态，并从精选列表或指定GitHub位置安装。支持实验性技能、具备凭据的私有仓库，以及一次安装多个技能。

• 查看可用技能及安装状态
• 从精选列表安装技能
• 添加私有GitHub仓库中的技能

Review OpenAI Cookbook documentation and notebook prose for technical accuracy, readable wording, consistent terminology, and publication metadata. Make focused edits, preserve notebook code and outputs, and report unresolved issues with validation results.

中文简介正在准备中。当前显示英语简介。

• Review documentation before merging a pull request
• Polish notebook Markdown cells
• Check publication metadata and author records

Review invoices, expense receipts, and service contracts against accounts-payable policy before human approval. Recalculate invoice totals, flag missing documentation and risky contract terms, and produce a JSON report with findings and a review decision.

中文简介正在准备中。当前显示英语简介。

• Recalculate invoice totals and report exact differences
• Check receipts and documented purchase approvals
• Flag changed bank details or payment instructions

Set up a realtime evaluation folder with a suitable shared harness, the framework that runs evaluations. Prepare prompts, tool definitions, realistic starter data, and a README, then validate the setup with evaluation and test runs.

中文简介正在准备中。当前显示英语简介。

• Start a single-turn text-to-speech evaluation
• Set up evaluations using saved audio
• Build multi-turn simulations with mock tools

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

Present results returned by a Codex helper while preserving findings, severity, file references, and uncertainty. This internal guidance also covers reporting edited files, failed runs, and setup requirements, with user confirmation before fixing review findings.

中文简介正在准备中。当前显示英语简介。

• Present review findings in order of severity
• Keep observed evidence separate from inferences
• Report files changed by Codex

Forward tasks from Claude Code's rescue subagent to Codex through a helper script. This internal skill handles model and effort options, fresh or resumed runs, and write access, then returns the helper's output unchanged.

中文简介正在准备中。当前显示英语简介。

• Hand off diagnosis or implementation work to Codex
• Resume a previous Codex request
• Start a fresh Codex run

Compare local case files with insurer policies to prepare a concise prior authorization packet, covering approval requirements, referrals, missing information, and a checklist for staff reviewing the case and communicating with the patient.

中文简介正在准备中。当前显示英语简介。

• Check prior authorization requirements for a case
• Review referral status and imaging policies
• List missing information for human review

Run final checks on reviewed SDK changes, covering code formatting, linting for code issues, type checking, and tests. Confirm completion only after every required check succeeds, with wrappers for macOS, Linux, and Windows.

中文简介正在准备中。当前显示英语简介。

• Verify runtime code changes after review
• Run final checks after test or build configuration changes
• Rerun required checks after fixing a failure

Find and retrieve official OpenAI documentation to answer API integration questions with source evidence. Check endpoint definitions, parameters, and documented limits, and receive setup guidance when the documentation connection is unavailable.

中文简介正在准备中。当前显示英语简介。

• Verify specifications before integrating an OpenAI API
• Check endpoint parameters and schemas
• Support technical explanations with official documentation

Compare SDK implementation with English documentation to find missing features, incorrect defaults, and outdated behavior descriptions. Report evidence and suggested locations, or make requested updates while keeping navigation consistent and following the repository’s documentation checks.

中文简介正在准备中。当前显示英语简介。

• Auditing documentation for a specific SDK feature
• Updating English docs after implementation changes
• Correcting outdated settings and default values

Prepare a Python SDK release candidate in a separate working directory, check version metadata and public API compatibility, and produce one local commit with a review report for the release handoff.

中文简介正在准备中。当前显示英语简介。

• Prepare a manual Python SDK release candidate
• Check release versions and public API compatibility
• Prepare a release pull request handoff

Capture a local static HTML page from the terminal using Playwright and Chromium. The supplied commands install the browser, set a 2048 × 1152 viewport, and save screenshots without starting a web server.

中文简介正在准备中。当前显示英语简介。

• Capturing a local static HTML page
• Saving screenshots at a specified viewport size
• Keeping first and second captures as separate files

Assess GitHub issues and pull requests by checking demonstrated user needs, existing alternatives, compatibility, and maintenance costs. Produce an evidence-based maintainer recommendation through code and document inspection, without running tests or examples.

中文简介正在准备中。当前显示英语简介。

• Deciding whether a pull request merits merging
• Checking whether existing features already solve an issue
• Comparing competing fixes for the same problem

Review logs and source files from a completed manual example run. Check that results are current and complete, verify intended behavior beyond successful exit codes, and distinguish product defects from environment or credential problems.

中文简介正在准备中。当前显示英语简介。

• Review results after a manual example run
• Verify behavior in examples that exited successfully
• Separate product failures from environment problems

Plan and, after explicit approval, run controlled checks of software behavior. Compare baseline and failure cases, repeat sensitive measurements, and report observed results with execution context, comparison conditions, and the status of temporary evidence files.

中文简介正在准备中。当前显示英语简介。

• Investigating a suspected runtime regression
• Checking retries, interruptions, and concurrent operations
• Comparing latency or cost under matched conditions

Measure Python SDK test coverage, the code exercised by tests, and identify meaningful gaps in user-visible behavior. Report proposed scenarios or add authorized tests, then verify the changes and report remaining gaps alongside coverage results.

中文简介正在准备中。当前显示英语简介。

• Auditing Python SDK test coverage
• Investigating a decline in coverage metrics
• Finding untested error and cancellation paths

Compare a Python SDK release plan or candidate with the previous release to assess compatibility, versioning, and proven regressions. Produce a ship-or-block recommendation, documentation handoff, and key changes for minor releases.

中文简介正在准备中。当前显示英语简介。

• Plan the next patch or minor SDK release
• Assess whether a release candidate can ship
• Check compatibility and migration paths

Audit Python SDK logs, exceptions, and telemetry for sensitive data exposure. Trace values to their sources, fix confirmed leaks, and test that redaction hides sensitive information while preserving the caller's expected behavior.

中文简介正在准备中。当前显示英语简介。

• Audit logs and exceptions for sensitive data exposure
• Fix leaks involving model or tool data
• Test redaction and caller behavior

Review completed code changes against the original requirements, choosing review depth by behavioral risk. Coordinate independent reviewers, resolve actionable findings, and verify that the delivered changes match the content actually reviewed.

中文简介正在准备中。当前显示英语简介。

• Review completed changes before final verification
• Choose review depth based on behavioral risk
• Re-review fixes after actionable findings