AI model or service
OpenAI agent skills for Claude Code, Codex and other agents.
- skills
- 1,301
- official
- 105
- Type
- AI model or service
- Website
- openai.com
- Official GitHub
- openai
- Reviews
- See OpenAI on Enlisted
OpenAI skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Answer questions about the AI SDK and help build AI-powered features. | vercel-labs/ | 168 | 21 repos | ~1.2k | Automated safety check: Pass | No licence | 5 mo ago |
| 2 | Review completed implementation changes before final verification. | openai/ | 30k | — | ~2k | Automated safety check: Pass | MIT | today |
| 3 | Audit or fix sensitive-data exposure in Python SDK diagnostics, exceptions, logging, and telemetry. | openai/ | 30k | — | ~1k | Automated safety check: Pass | MIT | today |
| 4 | Reference for building on Microsoft Foundry with the azure-ai-projects Python SDK: project clients, versioned agents, evaluations, connections, datasets and indexes. | microsoft/ | 3.1k | 6 repos | ~2.8k | Automated safety check: Pass | MIT | yesterday |
| 5 | Validate changesets in openai-agents-js using LLM judgment against git diffs (including uncommitted local changes). | openai/ | 3.9k | — | ~607 | Automated safety check: Pass | MIT | today |
| 6 | Assess a Python SDK release candidate or release plan against the previous release and recommend ship or block. | openai/ | 30k | — | ~5.4k | Automated safety check: Pass | MIT | today |
| 7 | Generates code that transforms datasets between ML schemas for model training or evaluation. | awslabs/ | 912 | 2 repos | ~3.5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 8 | Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. | trailofbits/ | 512 | 5 repos | ~2.2k | Automated safety check: Notes | CC-BY-SA-4.0 | 2 mo ago |
| 9 | Enable, operate, and extend CAO's MCP Apps surface — the host-rendered fleet dashboard visible inside MCP App hosts (Claude Desktop, ChatGPT, VS Code Copilot, Goose, Postman). | awslabs/ | 1.4k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | today |
| 10 | Prepare a local Python SDK release candidate in a dedicated worktree. | openai/ | 30k | — | ~4.9k | Automated safety check: Pass | MIT | today |
| 11 | Keep pnpm current: preflight the published package and pnpm/action-setup self-installer, update pnpm locally, align packageManager in package.json, and refresh CI pins. | openai/ | 3.9k | — | ~1.1k | Automated safety check: Pass | MIT | today |
| 12 | Designs Azure infrastructure from a natural-language description, or diagrams an existing resource group, then refines the design through conversation and deploys it with Bicep. | github/ | 40k | 1 repo | ~1.9k | Automated safety check: Pass | MIT | today |
| 13 | Assess a JS SDK release candidate or release plan against the previous release and recommend ship or block. | openai/ | 3.9k | — | ~4k | Automated safety check: Pass | MIT | today |
| 14 | Discovers available Azure OpenAI model capacity across regions and projects. | microsoft/ | 255 | 2 repos | ~1.7k | Automated safety check: Pass | MIT | today |
| 15 | A skill your agent uses 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… | JetBrains/ | 363 | 4 repos | ~1.9k | Automated safety check: Pass | Apache-2.0 | 3 mo ago |
| 16 | Run the required final formatting, lint, type, and test checks after eligible SDK changes pass review. | openai/ | 30k | — | ~1.4k | Automated safety check: Pass | MIT | today |
| 17 | Load the official MCP Apps builder skills (create-mcp-app, migrate-oai-app, add-app-to-server, convert-web-app) from github.com/modelcontextprotocol/ext-apps. | awslabs/ | 1.4k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | today |
| 18 | Audit or fix sensitive-data exposure in JS SDK diagnostics, exceptions, logging, and telemetry. | openai/ | 3.9k | — | ~2.2k | Automated safety check: Pass | MIT | today |
| 19 | Transcribe audio files to text with optional diarization and known-speaker hints. | JetBrains/ | 363 | 4 repos | ~776 | Automated safety check: Pass | Apache-2.0 | 3 mo ago |
| 20 | Analyze logs and source from a completed manual examples run. | openai/ | 30k | — | ~1.1k | Automated safety check: Pass | MIT | today |
| 21 | Migrate Python apps from Azure OpenAI Chat Completions to the Responses API. | microsoft/ | 77k | — | ~6k | Automated safety check: Notes | MIT | 18 days ago |
| 22 | Unified Azure OpenAI model deployment skill with intelligent intent-based routing. | microsoft/ | 255 | 1 repo | ~1.8k | Automated safety check: Pass | MIT | today |
| 23 | Optimize a prisma.io page for search engines and AI answer engines. | prisma/ | 1.1k | — | ~2k | Automated safety check: Pass | No licence | today |
| 24 | Carry implementation through an isolated worktree and local handoff. | openai/ | 30k | — | ~2.9k | Automated safety check: Pass | MIT | today |
| 25 | Plan and, after explicit approval, execute runtime-behavior probes for local or live integrations. | openai/ | 3.9k | — | ~4.9k | Automated safety check: Pass | MIT | today |
| 26 | A skill your agent uses 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… | JetBrains/ | 363 | 3 repos | ~2.5k | Automated safety check: Pass | Apache-2.0 | 3 mo ago |
| 27 | A skill your agent uses when adding, debugging, or modifying LLMObs plugins for an LLM library in dd-trace-js. | DataDog/ | 836 | — | ~1.4k | Automated safety check: Pass | Unknown | today |
| 28 | Choose supported scope and compatibility boundaries for SDK behavior changes; revisit when feedback changes the design. | openai/ | 30k | — | ~3.7k | Automated safety check: Pass | MIT | today |
| 29 | Wires up an Airbyte connector for use in a PydanticAI, Claude SDK, or other agent. | airbytehq/ | 135 | — | ~1.7k | Automated safety check: Notes | Unknown | yesterday |
| 30 | A skill your agent uses when the task involves reading, creating, or editing .docx documents, especially when formatting or layout fidelity matters; prefer python-docx plus the bundled… | trailofbits/ | 512 | 5 repos | ~786 | Automated safety check: Notes | CC-BY-SA-4.0 | 2 mo ago |
| 31 | Create, extend, package, and troubleshoot Codex and ChatGPT plugins using OpenAI MCP Extensions. | callstackincubator/ | 138 | — | ~1.9k | Automated safety check: Pass | No licence | today |
| 32 | Shift Python apps dem from Azure OpenAI Chat Completions go Responses API. | microsoft/ | 77k | — | ~6k | Automated safety check: Notes | MIT | 18 days ago |
| 33 | Statically audits GitHub Actions workflows that run AI coding agents, tracing attacker-controlled input to agent prompts and flagging unsafe sandbox, trigger and allowlist settings. | trailofbits/ | 7.4k | 6 repos | ~5.4k | Automated safety check: Notes | CC-BY-SA-4.0 | 5 days ago |
| 34 | Builds a complete agent with multiple Airbyte connectors using PydanticAI or Claude SDK. | airbytehq/ | 135 | — | ~1.7k | Automated safety check: Notes | Unknown | yesterday |
| 35 | Guides building an MCP app: an MCP server that also serves interactive UI widgets such as forms, pickers and confirm dialogs, rendered inline in chat hosts like Claude and ChatGPT. | anthropics/ | 37k | — | ~4.7k | Automated safety check: Pass | Apache-2.0 | today |
| 36 | Run the required final install, build, type, lint, test, and format checks after eligible SDK changes pass review. | openai/ | 3.9k | — | ~1.1k | Automated safety check: Pass | MIT | today |
| 37 | A skill your agent uses when the agent 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… | trailofbits/ | 512 | — | ~2.3k | Automated safety check: Notes | CC-BY-SA-4.0 | 2 mo ago |
| 38 | Build, test, and deploy code-based Teams apps using the M365 Agents Toolkit CLI. | microsoft/ | 1k | — | ~1.8k | Automated safety check: Notes | Unknown | today |
| 39 | Measure Python SDK coverage or address measured coverage gaps. | openai/ | 30k | — | ~687 | Automated safety check: Pass | MIT | today |
| 40 | Analyze logs and source from a completed repository example run. | openai/ | 3.9k | — | ~1.1k | Automated safety check: Pass | MIT | today |
| 41 | A skill your agent uses 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… | trailofbits/ | 512 | — | ~1k | Automated safety check: Notes | CC-BY-SA-4.0 | 2 mo ago |
| 42 | Build MCP servers for Copilot Chat using the OpenAI Apps SDK or MCP Apps SDK widget rendering support (any language). | microsoft/ | 1k | — | ~6.1k | Automated safety check: Notes | Unknown | today |
| 43 | Migrate Python OpenAI Agents SDK applications to Pydantic AI and, when warranted, Pydantic AI Harness. | pydantic/ | 20k | — | ~1.8k | Automated safety check: Pass | MIT | today |
| 44 | Audit or update English SDK documentation against the requested implementation scope. | openai/ | 30k | — | ~1.3k | Automated safety check: Pass | MIT | today |
| 45 | Retrieve authoritative OpenAI API and platform documentation when an integration or claim needs current external evidence. | openai/ | 30k | 1 repo | ~408 | Automated safety check: Pass | MIT | today |
| 46 | INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. | langchain-ai/ | 1.3k | 1 repo | ~3.9k | Automated safety check: Pass | MIT | yesterday |
| 47 | A skill your agent uses when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via playwright-cli… | trailofbits/ | 512 | — | ~945 | Automated safety check: Notes | CC-BY-SA-4.0 | 2 mo ago |
| 48 | Prepare the required local PR title, description, and branch suggestion after eligible implementation work is complete. | openai/ | 30k | — | ~1.8k | Automated safety check: Warn | MIT | today |
Questions, answered from the data.
What is the best OpenAI skill?
AI SDK (official) from vercel-labs/ai-facts ranks first of the 1,301 OpenAI skills listed here, with the highest score: its repository has 168 GitHub stars, 21 other GitHub owners carry a copy, its SKILL.md loads about 1.2k tokens and it passes the automated safety check with no findings. Next come Implementation Final Review and Sensitive Logging Audit.
Is there an official OpenAI skill?
105 of the 1,301 OpenAI skills are official, published by the vendor's own GitHub organization: AI SDK, Implementation Final Review, Sensitive Logging Audit, Azure AI Projects Python SDK, Changeset Validation and 100 more.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.