Search
OpenAI · For developers
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 433 | Web data extraction and discovery using the Bright Data JavaScript/TypeScript SDK (@brightdata/sdk). | brightdata/ | 264 | — | ~3k | Automated safety check: Pass | MIT | 4 days ago |
| 434 | Provides research patterns for Foundry Agent Service SDK. An agent skill from microsoft-foundry/foundry-agent-webapp. | microsoft-foundry/ | 127 | — | ~4.7k | Automated safety check: Pass | MIT | 5 mo ago |
| 435 | Produce a 9:16 social-native ad that recreates a ChatGPT mobile chat — user types in the composer with the iOS keyboard visible, taps send, keyboard slides down, header right-cluster swaps… | criptogus/ | 288 | — | ~5k | Automated safety check: Pass | Unknown | 3 days ago |
| 436 | Convert a single provided file into a downloadable Markdown file, representing source images and figures as readable text. | impredicative/ | 157 | — | ~174 | Automated safety check: Pass | LGPL-3.0 | 6 days ago |
| 437 | Audit CC Pocket support candidates against current source and record routine, non-promoting verdicts. | heypandax/ | 143 | — | ~119 | Automated safety check: Pass | MIT | 4 days ago |
| 438 | 438.Nla Create Create a Natural Language Agreement escrow on-chain. An agent skill from internet-court/internet-court-skill. | internet-court/ | 6.6k | 1 repo | ~915 | Automated safety check: Pass | MIT | 1 mo ago |
| 439 | Add support for a newly-released language or image generation model in pydantic-ai (e.g. | pydantic/ | 21k | — | ~10k | Automated safety check: Notes | MIT | today |
| 440 | Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. | davila7/ | 33k | 5 repos | ~2.4k | Automated safety check: Pass | MIT | today |
| 441 | 441.Langfuse Expert in Langfuse - the open-source LLM observability platform. | davila7/ | 33k | 5 repos | ~1.4k | Automated safety check: Pass | MIT | today |
| 442 | Expert in building voice AI applications - from real-time voice agents to voice-enabled apps. | davila7/ | 33k | 5 repos | ~2.1k | Automated safety check: Pass | MIT | today |
| 443 | Patch guide for adding a stable per-task prompt_cache_key to Cline's OpenAI native provider so cached token counts stop reading as zero. | OnlyTerp/ | 114 | — | ~868 | Automated safety check: Pass | Unknown | 1 mo ago |
| 444 | 444.Creator Create, improve, and review AgentUse agent files. An agent skill from agentuse/agentuse. | agentuse/ | 205 | — | ~9.8k | Automated safety check: Pass | Unknown | 4 days ago |
| 445 | 当需要为 AI 定义工具接口、设计调用规范、实现工具发现与编排机制时调用此 skill。典型场景包括:设计 AI agent 的工具集、定义 JSON Schema/XML/TypeScript 格式的工具描述、实现工具权限控制与并行调度、设计子代理委托架构。 | kangarooking/ | 208 | — | ~1.1k | Automated safety check: Pass | MIT | 5 mo ago |
| 446 | 446.Calle Use CALL-E from Codex through the calle CLI. An agent skill from hashgraph-online/awesome-codex-plugins. | hashgraph-online/ | 1.3k | — | ~2.9k | Automated safety check: Pass | MIT | today |
| 447 | 447.Sync Upstream Sync the Switchboard client with a newer official LibreChat server version — a stable release, a release candidate, or a PARTIAL sync up to an untagged upstream commit (e.g. | garfiec/ | 111 | — | ~3.4k | Automated safety check: Notes | MIT | yesterday |
| 448 | Retrieve authoritative OpenAI API and platform documentation when an integration or claim needs current external evidence. | openai/ | 30k | — | ~408 | Automated safety check: Pass | MIT | 3 days ago |
| 449 | Guides LLM fine-tuning with LoRA and QLoRA through Hugging Face PEFT, from dataset validation and training checks to adapter merging, quantization and deployment. | Jeffallan/ | 12k | — | ~1.7k | Automated safety check: Pass | MIT | 8 days ago |
| 450 | 450.RAG Architect Designs retrieval-augmented generation systems: document chunking, embeddings, vector store setup, hybrid search, reranking and retrieval evaluation, with checks at each step. | Jeffallan/ | 12k | — | ~2k | Automated safety check: Pass | MIT | 8 days ago |
| 451 | 451.Login Start the official Cursor SDK login flow. An agent skill from greenpolo/cc-multi-cli-plugin. | greenpolo/ | 188 | — | ~189 | Automated safety check: Notes | Apache-2.0 | 6 days ago |
| 452 | 452.Add Model Add a new LLM model to apps/sim/providers/models.ts with specs verified against the provider's live API docs (no hallucination) | simstudioai/ | 30k | — | ~4k | Automated safety check: Pass | Apache-2.0 | today |
| 453 | Use only when a developer explicitly asks to clean, prune, tidy, or organize DeepChat SDD documentation after implementation and validation. | ThinkInAIXYZ/ | 6.4k | — | ~788 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 454 | Migrate ANY cortextOS agent from the claude-code runtime to the live codex-app-server runtime. | grandamenium/ | 101 | — | ~12k | Automated safety check: Warn | MIT | 18 days ago |
| 455 | 455.Prime Agent A skill your agent uses when learning, configuring, or troubleshooting Prime Agent (PrimeIntellect-ai/prime-agent), including installation, providers, custom OpenAI-compatible models, local… | wcygan/ | 194 | — | ~1.8k | Automated safety check: Pass | No licence | yesterday |
| 456 | LiteLLM-RS provider system in two tiers - data-driven OpenAI-compatible catalog entries auto-routed through OpenAILikeProvider, plus code-based provider modules implementing the LLMProvider trait… | majiayu000/ | 118 | — | ~4.9k | Automated safety check: Pass | MIT | today |
| 457 | 457.Voxclaw Give your agent a voice. An agent skill from malpern/VoxClaw. | malpern/ | 208 | — | ~1.9k | Automated safety check: Pass | No licence | 2 mo ago |
| 458 | 458.Codex Delegate coding to OpenAI Codex CLI (features, PRs). An agent skill from NousResearch/hermes-agent. | NousResearch/ | 253k | 1 repo | ~1.5k | Automated safety check: Pass | MIT | today |
| 459 | 459.Smoke Test Create a Mastra project using create-mastra and smoke test the studio in Chrome using Chrome MCP server | mastra-ai/ | 29k | — | ~3.3k | Automated safety check: Notes | Unknown | today |
| 460 | 460.Codex CLI Bridge Bridge between Claude Code and OpenAI Codex CLI - generates AGENTS.md from CLAUDE.md, provides Codex CLI execution helpers, and enables seamless interoperability between both tools | alirezarezvani/ | 882 | — | ~2.2k | Automated safety check: Pass | MIT | 11 mo ago |
| 461 | EdgeOne Makers platform development router — the single entry point for building, storing data, and deploying on Tencent EdgeOne Makers. | TencentEdgeOne/ | 1.9k | 1 repo | ~646 | Automated safety check: Pass | MIT | 3 days ago |
| 462 | Assess a GitHub issue or PR for demonstrated need, supported alternatives, correctness, and maintainer action. | openai/ | 30k | — | ~8.9k | Automated safety check: Pass | MIT | 3 days ago |
| 463 | Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. | davila7/ | 33k | 4 repos | ~1.7k | Automated safety check: Pass | MIT | today |
| 464 | Adds an MCP server to NanoClaw so its container agent can list and prompt local models served by the Atomic Chat desktop app. | nanocoai/ | 31k | — | ~2.6k | Automated safety check: Notes | MIT | yesterday |
| 465 | Installs Codex as an agent provider for NanoClaw groups, with streaming, MCP tools, server-side history and vault-only credentials, next to or instead of Claude. | nanocoai/ | 31k | — | ~2.3k | Automated safety check: Notes | MIT | yesterday |
| 466 | Installs OpenCode as an optional NanoClaw agent runtime, reaching OpenRouter, OpenAI, Google, DeepSeek and others through OpenCode's own configuration. | nanocoai/ | 31k | — | ~5k | Automated safety check: Notes | MIT | yesterday |
| 467 | Generate a single photoreal or designed image with OpenAI gpt-image via fal.ai. | gooseworks-ai/ | 1.2k | 1 repo | ~2.4k | Automated safety check: Pass | MIT | yesterday |
| 468 | Generates onboarding code snippets for Phoenix tracing integrations and wires them into the project onboarding UI. | Arize-ai/ | 12k | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 469 | 469.Antseed Connect Connect coding agents, AI SDKs, and LLM tools to the AntSeed buyer proxy. | internet-court/ | 6.6k | 1 repo | ~20k | Automated safety check: Notes | GPL-3.0 | 1 mo ago |
| 470 | 470.Open Notebook Organizes research with the self-hosted Open Notebook alternative to NotebookLM. | K-Dense-AI/ | 48k | 1 repo | ~2.8k | Automated safety check: Pass | MIT | 6 days ago |
| 471 | Prepare a local PR title, description, and branch suggestion when requested or after eligible implementation work. | openai/ | 3.9k | — | ~1.8k | Automated safety check: Warn | MIT | yesterday |
| 472 | AI Engineering from Scratch 中文版中的 MCPA(Model Context Protocol Associate)AI 原生导师与入门流程。学习者需要备考 MCPA、继续认证路线、 交互式学习下一课、运行并验证实践实验、参加诊断或全真模拟、根据薄弱领域 补弱时使用。适用于 Claude Code、Codex、ChatGPT、Cursor 或其他 agent。 | fancyboi999/ | 1.2k | — | ~1.4k | Automated safety check: Pass | MIT | 2 days ago |
| 473 | Build AI applications using Azure AI Projects SDK for JavaScript (@azure/ai-projects). | microsoft/ | 3.1k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | 2 days ago |
| 474 | A skill your agent uses 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… | trailofbits/ | 513 | 9 repos | ~669 | Automated safety check: Notes | CC-BY-SA-4.0 | 2 mo ago |
| 475 | 475.Codex CLI Drive OpenAI's Codex CLI (codex exec) as a non-interactive coding sub-agent from inside Claude Code. | kortix-ai/ | 20k | — | ~1.6k | Automated safety check: Pass | Unknown | today |
| 476 | 476.Page Agent Embed alibaba/page-agent into your own web application — a pure-JavaScript in-page GUI agent that ships as a single <script tag or npm package and lets end-users of your site drive the UI with… | Tommy-yw/ | 546 | 3 repos | ~2.3k | Automated safety check: Notes | MIT | 4 mo ago |
| 477 | 477.Feishu Tools Use the Feishu/Lark plugin MCP tools for Feishu documents, spreadsheets, knowledge content, and other matching workspace operations. | ThinkInAIXYZ/ | 6.4k | — | ~652 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 478 | Start, validate, debug, and stop an AReno OpenAI-compatible serving endpoint. | inclusionAI/ | 323 | — | ~409 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 479 | 479.Gpt Image Skill Generate or edit images using OpenAI GPT Image API (gpt-image-2, gpt-image-1, etc). | feiskyer/ | 1.7k | — | ~1.4k | Automated safety check: Pass | MIT | 14 days ago |
| 480 | 面向 GPT-5.5 等强模型和熟练用户的轻量 AI Agent Harness / checkpoint-driven coding skill。默认用户已经把任务切到基本可执行的最小混沌单元;模型自行分解、探索与推进,人类通过最终目标、最小 spec、复述、checkpoint、证据验证与回写来低干扰控盘。 | openyida/ | 221 | — | ~1.5k | Automated safety check: Pass | MIT | yesterday |