Search
OpenAI · For developers
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 481 | LiteLLM-RS Routing Architecture. An agent skill from majiayu000/litellm-rs. | majiayu000/ | 118 | — | ~1.9k | Automated safety check: Pass | MIT | today |
| 482 | 482.Dev Auth Bypass Authenticate a browser against a local ChatJS app without OAuth. | FranciscoMoretti/ | 1.2k | — | ~141 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 483 | 483.Agents Build voice AI agents with ElevenLabs. An agent skill from elevenlabs/skills. | elevenlabs/ | 482 | — | ~6.5k | Automated safety check: Pass | MIT | 2 days ago |
| 484 | Deploy vLLM using Docker (pre-built images or build-from-source) with NVIDIA GPU support and run the OpenAI-compatible server. | vllm-project/ | 102 | — | ~2.5k | Automated safety check: Notes | Apache-2.0 | 6 mo ago |
| 485 | Perform language and framework specific security best-practice reviews and suggest improvements. | trailofbits/ | 513 | 9 repos | ~2.2k | Automated safety check: Notes | CC-BY-SA-4.0 | 2 mo ago |
| 486 | 486.Chatgpt CLI Drives ChatGPT from the terminal via cli-web-chatgpt — ask questions, generate and download images, list and view conversations, browse models, and manage OpenAI SSO auth. | ItamarZand88/ | 231 | — | ~781 | Automated safety check: Pass | MIT | 10 days ago |
| 487 | 487.Oracle Oracle second-model review: bundle prompts/files, debug, refactor, design. | steipete/ | 7.3k | 1 repo | ~2.1k | Automated safety check: Notes | MIT | yesterday |
| 488 | Wires Grok speech-to-speech into an app's own microphone and audio playback over a realtime WebSocket, replacing an STT-LLM-TTS cascade or OpenAI Realtime. | cursor/ | 11k | — | ~1.7k | Automated safety check: Pass | No licence | today |
| 489 | Azure OpenAI SDK for .NET. An agent skill from microsoft/skills. | microsoft/ | 3.1k | 5 repos | ~3.4k | Automated safety check: Pass | MIT | 2 days ago |
| 490 | Azure AI Voice Live SDK for .NET. An agent skill from microsoft/skills. | microsoft/ | 3.1k | 5 repos | ~2.3k | Automated safety check: Pass | MIT | 2 days ago |
| 491 | 491.Image Prompting A skill your agent uses when generating or editing images via blockrunimage — especially with GPT Image 2, Nano Banana, or Grok Imagine for posters, UI mockups, marketing assets, product shots, or… | BlockRunAI/ | 391 | — | ~3.6k | Automated safety check: Pass | MIT | 3 days ago |
| 492 | 492.Surf Control Chrome browser via CLI for testing, automation, and debugging. | w-winter/ | 139 | — | ~7.6k | Automated safety check: Warn | MIT | today |
| 493 | 493.Gpt Pro Create a self-contained GPT Pro or external-review prompt with full repo context, current state, evidence, and pointed review questions because the reviewer has no local file access. | udecode/ | 17k | — | ~1.7k | Automated safety check: Pass | Unknown | yesterday |
| 494 | Audit and rewrite your LinkedIn profile to attract the right people. | BrianRWagner/ | 441 | — | ~3.8k | Automated safety check: Pass | No licence | 6 mo ago |
| 495 | 495.Python AI Build and troubleshoot Python AI applications involving model APIs, local LLMs, retrieval, tools, agents, prompts, evaluation, or AI dependencies. | ChrisTitusTech/ | 147 | — | ~601 | Automated safety check: Pass | No licence | 5 days ago |
| 496 | Continue's prompt caching is opt-in via config and off by default. | OnlyTerp/ | 114 | — | ~977 | Automated safety check: Pass | Unknown | 1 mo ago |
| 497 | Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. | github/ | 40k | 2 repos | ~4.6k | Automated safety check: Pass | MIT | 2 days ago |
| 498 | Answer questions about Tlon, Urbit, Tlon Messenger, Tlonbot, and OpenClaw — what they are, how they work, and how to use them. | tloncorp/ | 107 | — | ~11k | Automated safety check: Pass | MIT | yesterday |
| 499 | 499.Agent Delegation 当系统提示词需要设计多代理协作架构、子代理专业化分工、代理间上下文隔离与传递机制、任务生命周期管理时调用此 Skill。适用于 AI Agent 平台、多工具编排系统、代码审查流水线、跨应用协作场景等。不适用于:单代理系统(无委派需求)、简单工具调用(无子代理概念)、纯 API 编排(无 AI 决策)。当需求聚焦于"单代理内的对话路由"而非"多代理间的任务分配"时,应该用… | kangarooking/ | 208 | — | ~897 | Automated safety check: Pass | MIT | 5 mo ago |
| 500 | 500.Memcode Use the enabled Memcode MCP connection to explicitly save approved facts and recall relevant memories across DeepChat conversations. | ThinkInAIXYZ/ | 6.4k | — | ~453 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 501 | 501.Glmv Prompt Gen Analyze images/videos and generate professional prompts for text-to-image and text-to-video AI tools (Midjourney, Stable Diffusion, DALL-E, Sora, Runway, Kling, Pika). | zai-org/ | 476 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | 5 mo ago |
| 502 | LiteLLM-RS Streaming Architecture. An agent skill from majiayu000/litellm-rs. | majiayu000/ | 118 | — | ~2.1k | Automated safety check: Pass | MIT | today |
| 503 | 503.Review Docs Review and fix ChatJS Blume documentation and MDX files. An agent skill from FranciscoMoretti/chat-js. | FranciscoMoretti/ | 1.2k | — | ~201 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 504 | A skill your agent uses when building any FrontMCP server component other than a tool (for tools, use create-tool). | agentfront/ | 146 | — | ~10k | Automated safety check: Pass | Apache-2.0 | today |
| 505 | 505.Image Generation Generate images from text prompts (and optionally edit/remix input images). | letta-ai/ | 3.6k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | today |
| 506 | 506.Codex A skill your agent uses when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. | davila7/ | 33k | 3 repos | ~1.3k | Automated safety check: Pass | MIT | today |
| 507 | 507.Codex Subagent Launch OpenAI Codex CLI as a subagent (ChatGPT subscription auth, no API key). | davidondrej/ | 4.1k | — | ~1k | Automated safety check: Pass | MIT | yesterday |
| 508 | A skill your agent uses 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… | trailofbits/ | 513 | — | ~2k | Automated safety check: Notes | CC-BY-SA-4.0 | 2 mo ago |
| 509 | 509.Codexbar AI service usage/quota via CodexBar CLI: Codex/OpenAI, Claude, Kimi and other provider limits, credits, reset times. | steipete/ | 7.3k | — | ~700 | Automated safety check: Pass | MIT | yesterday |
| 510 | Tools are how AI agents interact with the world. An agent skill from omer-metin/skills-for-antigravity. | omer-metin/ | 163 | — | ~705 | Automated safety check: Pass | Apache-2.0 | 8 mo ago |
| 511 | 511.Ito Inference Inspect the availability of model serving on a completed Itô compute booking and, when the canonical backend becomes available, hand off an explicitly confirmed serving manifest. | affaan-m/ | 277k | 1 repo | ~1.5k | Automated safety check: Pass | MIT | today |
| 512 | 512.Lesson Make a narrated lesson video about lpm from the real desktop app, recorded on a pristine data directory. | gug007/ | 152 | — | ~1.2k | Automated safety check: Pass | MIT | today |
| 513 | Transcribe audio files to text via POST /audio/transcriptions. | veniceai/ | 144 | — | ~1.7k | Automated safety check: Pass | MIT | 5 days ago |
| 514 | Use the user's already signed-in official ChatGPT website account, especially GPT-5.5 Pro / ChatGPT Pro, to perform product research, market research, competitor research, second-opinion analysis… | mcncarl/ | 4.4k | — | ~3.4k | Automated safety check: Pass | Unknown | 7 days ago |
| 515 | Continue's Gemini provider doesn't use the cachedContents API at all. | OnlyTerp/ | 114 | — | ~1.1k | Automated safety check: Pass | Unknown | 1 mo ago |
| 516 | 516.Voice Agents Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. | sickn33/ | 47k | 2 repos | ~1k | Automated safety check: Pass | MIT | yesterday |
| 517 | 517.Delegate Sol Delegate a bounded task from a Codex session to GPT-5.6 Sol in the same Herdr workspace, then wait for and collect the result. | instructa/ | 139 | — | ~1.2k | Automated safety check: Pass | No licence | 13 days ago |
| 518 | 518.Model Selection Per-agent model selection with 4-layer hierarchy and fallback chains | bradygaster/ | 3.3k | — | ~2k | Automated safety check: Warn | MIT | yesterday |
| 519 | Transcribe audio and video from URLs (YouTube, direct media links) using WhisperKit locally. | nicepkg/ | 285 | — | ~1.5k | Automated safety check: Pass | MIT | 8 mo ago |
| 520 | 520.Xrk LLM 当你需要配置/新增/排查 LLM 提供商(OpenAI/Azure/Gemini/Anthropic/Ollama/各类兼容网关)时使用;确保 YAML/Schema/代码一致。 | xrkseek/ | 138 | — | ~304 | Automated safety check: Pass | MIT | 10 days ago |
| 521 | Build, test, and debug Hermes Agent RL environments for Atropos training. | Tommy-yw/ | 546 | — | ~3.3k | Automated safety check: Pass | MIT | 4 mo ago |
| 522 | Guide the agent to recall, remember, and route durable learning into Memory, Skills, Scheduled Tasks, or Tape. | ThinkInAIXYZ/ | 6.4k | — | ~849 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 523 | Integrates local AI capabilities into applications using Embeddable Lemonade. | amd/ | 408 | — | ~6k | Automated safety check: Pass | MIT | 2 days ago |
| 524 | 524.Refine Improve a prompt using official OpenAI or Claude guidance. An agent skill from automagik-dev/genie. | automagik-dev/ | 346 | — | ~1.3k | Automated safety check: Pass | MIT | yesterday |
| 525 | 525.Generate Idea Generate and rank research ideas given a broad direction. An agent skill from GRIND-Lab-Core/night_owl_research_agent. | GRIND-Lab-Core/ | 106 | — | ~3.2k | Automated safety check: Warn | No licence | 5 mo ago |
| 526 | 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). | trailofbits/ | 513 | 6 repos | ~474 | Automated safety check: Notes | CC-BY-SA-4.0 | 2 mo ago |
| 527 | Get RED metrics + service maps + frontend RUM + AI/LLM monitoring out of Grafana Cloud — Application Observability (tracesspanmetrics from OTel traces, p50/p95/p99 latency, exemplar-to-trace… | grafana/ | 282 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | 3 days ago |
| 528 | 528.Agentica SDK Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration | parcadei/ | 3.9k | 1 repo | ~2.8k | Automated safety check: Notes | MIT | 8 mo ago |