@openai

code-change-verification enforces a mandatory verification stack for runtime and test changes in the openai agents python repository, running format, lint, type checking, and tests with fail-fast semantics and platform-specific script entry points.

develop-web-game provides a structured iteration loop for html/js games using playwright-based testing, screenshot validation, and deterministic time control to catch bugs in small increments.

playwright automates browser tasks from the terminal using playwright-cli, covering navigation, form filling, snapshots, screenshots, and data extraction via a wrapper script that works without global installation.

openai-docs routes model selection, api migration, and prompt-upgrade requests to the official openai developer docs mcp server, with fallback to bundled references and domain-restricted web search when remote guidance is unavailable.

security-ownership-map analyzes git history to build people-file graphs, compute bus factor and sensitive-code clusters, and export for neo4j or gephi. flags orphaned sensitive code, ownership drift vs codeowners, and hidden concentration risk in auth/crypto.

security-threat-model produces repository-grounded threat models anchored to code evidence, enumerating trust boundaries, assets, and abuse paths with explicit attacker capabilities and prioritized mitigations.

doc handles read, create, and edit workflows for docx files with optional visual layout validation via pdf conversion. python-docx powers structural edits while fallback text extraction mitigates missing rendering tools.

figma-implement-design converts Figma designs to production code via a seven-step workflow, extracting design tokens and assets, enforcing 1:1 visual parity, and reusing design system components. requires figma mcp connection and handles both url and desktop selection.

guidance for structuring prompts to Codex and GPT-5.4 models using XML blocks, output contracts, and verification loops to improve task clarity and reduce inference drift.

figma enables design-to-code translation via mcp server, fetching context and screenshots to generate production code aligned with project conventions and design tokens.

netlify-deploy automates site deployments via the netlify cli, handling authentication, framework detection, and site linking. supports oauth and api tokens with error recovery for common failure modes.

notion-knowledge-capture converts conversations into structured notion pages (decisions, how-tos, faqs, wiki entries) with proper linking and metadata, requiring notion mcp setup and database selection.

security-best-practices audits code against language and framework specific security guidance, operating in three modes: secure-by-default coding, passive vulnerability detection, and on-demand security reporting with prioritized findings and remediation.

render-deploy guides users through blueprint-based and direct service creation workflows for deploying applications to render. covers git-backed flows, codebase analysis, render.yaml generation, and dashboard deeplinks with mcp tool integration.

openai-docs bridges the implexa graph to openai's developer reference via an mcp server, prioritizing live docs over web search for model selection and api migration guidance.

notion-meeting-intelligence assembles meeting prep materials by querying notion for context, selecting a template type, drafting agendas with links and timebox assignments, then layering in codex research. suitable for organizers building structured pre-reads.

hatch-pet generates codex-compatible animated pet spritesheets from text concepts, brand cues, or reference images, delegating visual generation through the imagegen skill while handling name and description inference.

chatgpt-apps scaffolds MCP-backed ChatGPT applications with docs-first methodology, producing app archetypes, tool plans, server stubs, and widget code paired against a minimum contract.

gh-address-comments fetches github pr review comments via gh cli, presents them to the user for selection, and applies fixes to chosen items after verifying authentication.

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated…

speech — an installable skill for AI agents, published by openai/skills.

Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from…

Capture conversations and decisions into structured Notion pages; use when turning chats/notes into wiki entries, how-tos, decisions, or FAQs with proper…

Research across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or…

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's…

Use when tasks involve creating, editing, analyzing, or formatting spreadsheets (`.xlsx`, `.csv`, `.tsv`) with formula-aware workflows, cached recalculation,…

Use when the task asks for a visually strong landing page, website, app, prototype, demo, or game UI. This skill enforces restrained composition, image-led…

Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or…

Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not…

Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise…

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or…

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft…

Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and…

Manage issues, projects & team workflows in Linear. Use when the user wants to read, create or updates tickets in Linear.

Persistent browser and Electron interaction through `js_repl` for fast iterative UI debugging.

Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger…

Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging)…

Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best…

Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture…

Use when tasks involve reading, creating, or reviewing PDF files where rendering and layout matter; prefer visual checks by rendering pages (Poppler) and use…

macOS-only AppleScript control for the ChatGPT Atlas desktop app. Use only when the user explicitly asks to control Atlas tabs/bookmarks/history on macOS and the "ChatGPT Atlas" app is installed; do not trigger for general browser tasks or non-macOS environments.

Run the Codex Readiness integration test. Use when you need an end-to-end agentic loop with build/test scoring.

Validate changesets in openai-agents-js using LLM judgment against git diffs (including uncommitted local changes). Use when packages/ or .changeset/ are modified, or when verifying PR changeset compliance and bump level.

Help address review/issue comments on the open GitLab MR for the current branch using glab CLI. Use when the user wants help addressing review/issue comments on an open GitLab MR

Run the Codex Readiness unit test report. Use when you need deterministic checks plus in-session LLM evals for AGENTS.md/PLANS.md.

Create a concise plan. Use when a user explicitly asks for a plan related to a coding task.

Turn Notion specs into implementation plans, tasks, and progress tracking; use when implementing PRDs/feature specs and creating Notion plans + tasks from them.

Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).

Create the required PR-ready summary block, branch suggestion, title, and draft description for openai-agents-python. Use in the final handoff after moderate-or-larger changes to runtime code, tests, examples, build/test configuration, or docs with behavior impact; skip only for trivial or conversation-only tasks, repo-meta/doc-only tasks without behavior impact, or when the user explicitly says not to include the PR draft block.

Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.

Generate a Codex Super Bowl merch redemption URL (tokenized) and open it. Use when a user asks to redeem Super Bowl/Codex merch, needs a redemption token, or wants the merch redemption link.

Manage issues, projects & team workflows in Linear. Use when the user wants to read, create or updates tickets in Linear.

Deploy web projects to Netlify using the Netlify CLI (`npx netlify`). Use when the user asks to deploy, host, publish, or link a site/repo on Netlify, including preview and production deploys.

Improve test coverage in the OpenAI Agents Python repository: run `make coverage`, inspect coverage artifacts, identify low-coverage files, propose high-impact tests, and confirm with the user before writing tests.

Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry CLI; perform read-only queries using the `sentry` command.

Perform a release-readiness review by locating the previous release tag from remote tags and auditing the diff (e.g., v1.2.3...<commit>) for breaking changes, regressions, improvement opportunities, and risks before releasing openai-agents-python.

Use when working with the OpenAI API (Responses API) or OpenAI platform features (tools, streaming, Realtime API, auth, models, rate limits, MCP) and you need authoritative, up-to-date documentation (schemas, examples, limits, edge cases). Prefer the OpenAI Developer Documentation MCP server tools when available; otherwise guide the user to enable `openaiDeveloperDocs`.

Prepare meeting materials with Notion context and Codex research; use when gathering context, drafting agendas/pre-reads, and tailoring materials to attendees.

Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed.

Run python examples in auto mode with logging, rerun helpers, and background control.

Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks.

Research across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or reports with citations.

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.

Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions "implement design", "generate code", "implement component", provides Figma URLs, or asks to build components matching Figma specs. For Figma canvas writes via `use_figma`, use `figma-use`.

Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.

Analyze main branch implementation and configuration to find missing, incorrect, or outdated documentation in docs/. Use when asked to audit doc coverage, sync docs with code, or propose doc updates/structure changes. Only update English docs under docs/** and never touch translated docs under docs/ja, docs/ko, or docs/zh. Provide a report and ask for approval before editing docs.

Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

Use when the user asks to generate, remix, poll, list, download, or delete Sora videos via OpenAI’s video API using the bundled CLI (`scripts/sora.py`), including requests like “generate AI video,” “Sora,” “video remix,” “download video/thumbnail/spritesheet,” and batch video generation; requires `OPENAI_API_KEY` and Sora API access.

Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.

Use when tasks involve reading, creating, or reviewing PDF files where rendering and layout matter; prefer visual checks by rendering pages (Poppler) and use Python tools such as `reportlab`, `pdfplumber`, and `pypdf` for generation and extraction.

Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (`scripts/image_gen.py`) and require `OPENAI_API_KEY` for live calls.

Use when tasks involve creating, editing, analyzing, or formatting spreadsheets (`.xlsx`, `.csv`, `.tsv`) using Python (`openpyxl`, `pandas`), especially when formulas, references, and formatting need to be preserved and verified.

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

Guide for testing Codex TUI interactively

Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, and baseline placeholders you can…

Use when working with the OpenAI API (Responses API) or OpenAI platform features (tools, streaming, Realtime API, auth, models, rate limits, MCP) and you need…

vercel-deploy — an installable skill for AI agents, published by openai/skills.

Deploy applications to Render by analyzing codebases, generating render.yaml Blueprints, and providing Dashboard deeplinks. Use when the user wants to deploy,…

yeet — an installable skill for AI agents, published by openai/skills.

Build, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Use when working on Blazor Web…

Turn Notion specs into implementation plans, tasks, and progress tracking; use when implementing PRDs/feature specs and creating Notion plans + tasks from them.

Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry CLI; perform…

security-ownership-map — an installable skill for AI agents, published by openai/skills.

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is…

Migrate supported instruction files, skills, agents, and MCP config into Codex project and global files.

Internal guidance for presenting Codex helper output back to the user

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

Create and edit presentation slide decks (`.pptx`) with PptxGenJS, bundled layout helpers, and render/validation utilities. Use when tasks involve building a…

Create a new blank Figma file. Use when the user wants to create a new Figma design or FigJam file, or when you need a new file before calling use_figma.…

Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user…

Build or update a professional-grade design system in Figma from a codebase. Use when the user wants to create variables/tokens, build component libraries, set…

Connects Figma design components to code components using Code Connect mapping tools. Use when user says "code connect", "connect this component to code", "map…

figma-create-design-system-rules — an installable skill for AI agents, published by openai/skills.

Use this skill alongside figma-use when the task involves translating an application page, view, or multi-section layout into Figma. Triggers: 'write to…

**MANDATORY prerequisite** — you MUST invoke this skill BEFORE every `use_figma` tool call. NEVER call `use_figma` directly without loading this skill first.…

Use when the user asks to generate, edit, extend, poll, list, download, or delete Sora videos, create reusable non-human Sora character references, or run…

Bootstrap, develop, and design modern WinUI 3 desktop applications with C# and the Windows App SDK using official Microsoft guidance, WinUI Gallery patterns,…

Run the integration-tests pipeline that depends on a local npm registry (Verdaccio). Use when asked to execute integration tests or local publish workflows in this repo.

Keep pnpm current: run pnpm self-update/corepack prepare, align packageManager in package.json, and bump pnpm/action-setup + pinned pnpm versions in .github/workflows to the latest release. Use this when refreshing the pnpm toolchain manually or in automation.