@openai

openai-figma-implement-design translates figma designs into production code with visual fidelity by extracting design context, fetching assets, mapping to project conventions, and validating against screenshots. handles both url-based and desktop mcp workflows.

speech generates spoken audio from text via openai's tts models, supporting single clips and batch jobs with configurable voices, delivery styles, and output formats. covers narration, product demos, ivr prompts, and accessibility use cases.

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.

openai-pnpm-upgrade orchestrates pnpm toolchain refresh by updating local binaries, resolving package integrity via npm registry, aligning package.json and github workflows to pinned versions and commit shas without broad regex replacement.

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.

gh-fix-ci inspects failing github actions checks on pull requests, extracts failure logs, drafts a fix plan, and implements changes after user approval using the gh cli and a bundled python script.

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.

openai-transcribe wraps openai's audio model with optional speaker diarization, bundled cli, and environment setup guidance. covers fast text extraction and labeled multi-speaker workflows.

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.

frontend-skill enforces deliberate, image-led interface design through composition-first defaults: full-bleed heroes, restrained palettes, utility-focused copy, and minimal motion. targets landing pages, apps, and dashboards requiring premium visual presence over component density.

screenshot captures desktop, app, window, or region content across macos, linux, and windows. respects user-specified paths, applies tool prioritization, and includes platform-specific helpers with permission preflight for macos.

openai-integration-tests runs a pnpm-based test pipeline against a local verdaccio npm registry, handling sandbox permission escalation, registry lifecycle management, and storage mount integration coverage.

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.

openai-knowledge routes queries to the openai developer docs mcp server when available, falling back to guided setup instructions. covers api schemas, endpoints, and platform features with emphasis on exact documentation retrieval over inference.

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.

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.

security-threat-model produces repository-grounded threat models by extracting system architecture from code, mapping trust boundaries and assets, enumerating realistic attack paths, and recommending prioritized mitigations tied to concrete locations.

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-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.

openai-vercel-deploy handles instant project deployment to vercel with preview-by-default behavior, cli detection, and a fallback script-based method when authentication fails.

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

transcribe converts audio to text via openai's whisper api, supporting optional speaker diarization and language hints. defaults to fast text mode, switches to diarized output on request.

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.

sentry enables read-only production error inspection and health summaries via the official sentry cli, supporting unresolved issue queries, event retrieval, and automatic pii redaction with a 24-hour default window.

openai-notion-research-documentation guides multi-source research by querying notion, synthesizing findings into structured formats (brief, summary, comparison, report), and publishing with citations and source links.

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.

notion-research-documentation aggregates and synthesizes information from multiple notion pages into structured briefs, summaries, or comparisons with citation tracking, using targeted search and templated output formats.

spreadsheet skill handles creation, editing, analysis, and visualization of xlsx/csv/tsv files with formula awareness and optional pre-delivery rendering, but lacks explicit failure recovery and edge case guidance.

imagegen provides image generation and editing for project assets via a built-in tool or fallback cli, supporting diverse output types from mockups to photorealistic renders.

vercel-deploy wraps the vercel cli to ship projects as preview deployments by default, with fallback script support for auth-less scenarios and explicit production promotion.

openai-changeset-validation judges changeset correctness against git diffs using llm reasoning, enforcing semver rules and single-line summaries. runs locally or in ci via pnpm commands and shared validation rules.

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.

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.

codex-cli-runtime wraps the codex-companion task runner for the rescue subagent, enforcing a single forwarding pattern with optional prompt rewriting via gpt-5-4-prompting before delegation.

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.

migrate-to-codex automates bulk migration of claude, mcp, and agent config into codex project and global structures, with explicit autonomy guardrails and ordered task tracking.

figma-generate-design orchestrates full-page screen creation by composing published design system components, variables, and styles rather than drawing primitives from scratch. routes related tasks (code generation, component creation, code connect) to peer skills.

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.

codex-result-handling provides output preservation rules for presenting Codex analysis back to users, emphasizing fidelity to helper verdicts and explicit stopping points before remediation.

winui-app provides scaffolding and environment validation for windows app sdk projects, with conditional flows for setup, bootstrap, design, and troubleshooting work.

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.

figma-use is a mandatory prerequisite skill for executing javascript in figma files via the plugin api. it establishes api rules and references required context but leaves procedural guidance incomplete.

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.

figma-code-connect-components matches figma design components to code implementations via code connect mapping. includes skill boundaries and prerequisites but lacks procedural detail and failure handling.

cloudflare-deploy is a routing index to cloudflare products organized by user intent (compute, storage, ai, networking, security, media). it provides decision trees and product tables but defers actual deployment logic to external references.

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`).

Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for…

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

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

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…

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…

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…

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

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

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)…

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

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

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

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

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

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.

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 read-only queries using the `sentry` command.

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

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.

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`).

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.

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.

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.

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.

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

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

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.

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.

Create the required PR-ready summary block, branch suggestion, title, and draft description for openai-agents-python. Use before the final response whenever the current task changed runtime code, tests, examples, build/test configuration, or docs with behavior impact, regardless of perceived change size and including local-only or uncommitted work. 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.

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).

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.

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.

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 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.

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 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.

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.

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.

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.

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

test-tui — an installable skill for AI agents, published by openai/codex.

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

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…

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…

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