Search
OpenAI · For data scientists
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 49 | A skill your agent uses when certifying mesh-llm KV/cache stability under repeated OpenAI tool-call loops, same-prefix cache reuse, suffix-prefill limits, or native Skippy slot/decode/eviction… | Mesh-LLM/ | 3.5k | — | ~704 | Automated safety check: Pass | Apache-2.0 | today |
| 50 | A skill your agent uses when composing prompts targeting GPT-6 Sol (GPT 디폴트), GPT-6 Astra, GPT-6 Luna, GPT-5.6 Sol (직전 디폴트), legacy GPT-5.5/5.4/5.2 — lean outcome-first 7블록 규칙 + LEGACY 섹션(구 XML 스택)을… | treylom/ | 185 | — | ~334 | Automated safety check: Pass | Unknown | 14 days ago |
| 51 | Continue's prompt caching is opt-in via config and off by default. | OnlyTerp/ | 114 | — | ~977 | Automated safety check: Pass | Unknown | 1 mo ago |
| 52 | Build AI agents with tools, memory, and multi-step reasoning - ChatGPT, Claude, Gemini integration patterns | claude-office-skills/ | 505 | — | ~3.1k | Automated safety check: Pass | MIT | 8 mo ago |
| 53 | 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 |
| 54 | Build a low-latency, Iron Man-inspired tactical voice assistant (F.R.I.D.A.Y.) using Pipecat, Gemini, and OpenAI. | sickn33/ | 47k | 2 repos | ~872 | Automated safety check: Notes | MIT | yesterday |
| 55 | 📝 Prompt Library workflow skill. An agent skill from diegosouzapw/awesome-omni-skills. | diegosouzapw/ | 159 | — | ~3.1k | Automated safety check: Pass | MIT | 3 mo ago |
| 56 | Curated upstream guidance for Longbridge Quant; use when the workflow matches the user goal. | sickn33/ | 47k | 1 repo | ~1.5k | Automated safety check: Pass | MIT | yesterday |
| 57 | 当系统提示需要设计引用格式、信息溯源机制、来源标注系统时调用。适用于文档问答、搜索增强生成(RAG)、代码引用、浏览器辅助等需要让用户追溯信息来源的场景。不适用于纯创作类输出(如故事、诗歌),不适用于无需溯源的常识问答,也不适用于注入防御(虽然两者都涉及内容可信度)。 | kangarooking/ | 208 | — | ~655 | Automated safety check: Pass | MIT | 5 mo ago |
| 58 | 58.Self Answer questions about how 'mi' works, write new tools, or modify the harness. | av/ | 102 | — | ~1.4k | Automated safety check: Pass | No licence | 15 days ago |
| 59 | A skill your agent uses when running, configuring, debugging, or embedding skippy-serving, binary stage transport, OpenAI frontend integration, activation wire dtype settings, stage configs… | Mesh-LLM/ | 3.5k | — | ~380 | Automated safety check: Pass | Apache-2.0 | today |
| 60 | 60.Voice Agents Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. | davila7/ | 33k | 3 repos | ~565 | Automated safety check: Pass | MIT | yesterday |
| 61 | Applies the reasoning style of Ilya Sutskever (deep learning pioneer, co-founder of OpenAI and Safe Superintelligence Inc.) to problems involving AI architecture, scaling laws, alignment, and… | K-Dense-AI/ | 282 | — | ~1.7k | Automated safety check: Pass | MIT | 1 mo ago |
| 62 | Optimize LLM prompt caching hit rate to reduce API costs and improve latency. | affaan-m/ | 276k | — | ~2.5k | Automated safety check: Pass | MIT | yesterday |
| 63 | Vector database implementation for AI/ML applications, semantic search, and RAG systems. | ancoleman/ | 525 | — | ~3.5k | Automated safety check: Pass | MIT | 10 mo ago |
| 64 | Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates. | getsentry/ | 1k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 65 | 65.AI Image Gen 通用 AI 生图:文生图 / 图生图 / 图像变体。当用户说 AI 生图、AI 画图、文生图、图生图、生成图片、生成配图、图像生成、AI 出图、AI 作图、换图、改图、图像编辑、给我画一张、生成一张图 时使用。支持 OpenAI 兼容 API 与 apimart 异步 API,用户自备 API key。 | ZJU-REAL/ | 3.4k | — | ~787 | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 66 | Agente que simula Ilya Sutskever — co-fundador da OpenAI, ex-Chief Scientist, fundador da SSI. | sickn33/ | 47k | 2 repos | ~447 | Automated safety check: Pass | MIT | 2 days ago |
| 67 | Evolve prompts/regex/SQL/code with Imbue's evolution loop. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 2 repos | ~2.1k | Automated safety check: Warn | MIT | 3 days ago |
| 68 | Integrate RouterBase as an OpenAI-compatible model gateway for routing GPT, Claude, Gemini, media, audio, and embedding requests. | sickn33/ | 47k | 1 repo | ~1.8k | Automated safety check: Pass | MIT-0 | 2 days ago |
| 69 | A skill your agent uses when a user provides ChatGPT web AI-search keywords, repeat count, target entity, entity type, OpenCLI profile, and crawl interval preference, then needs repeated crawls… | yaojingang/ | 871 | — | ~456 | Automated safety check: Pass | MIT | 10 days ago |
| 70 | Grade or filter workflow HDF5 episodes with an OpenAI-compatible vision model. | NVIDIA/ | 3.6k | 1 repo | ~1.5k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 71 | Run the corpus benchmark — booster locally, optional Gemini/Sonnet/Opus baselines — and persist a verifiable measured-vs-claimed table | ruvnet/ | 74k | — | ~745 | Automated safety check: Notes | MIT | yesterday |
| 72 | Connect a ChatGPT or Claude account and sync its conversation history into the brain automatically. | garrytan/ | 31k | — | ~2.8k | Automated safety check: Pass | MIT | yesterday |
| 73 | 当系统提示词需要定义 AI 如何分类用户意图、路由到不同处理流程、决定澄清策略和自主度级别时调用此 Skill。适用于多任务型 AI 助手、客服机器人、编程工具、研究助手等需要结构化对话管理的场景。不适用于:纯问答型系统(无任务执行)、单轮交互(无对话状态)、简单的 prompt 模板(无路由逻辑)。当需求仅涉及"输出什么格式"而非"如何决定输出什么"时,应该用… | kangarooking/ | 208 | — | ~788 | Automated safety check: Pass | MIT | 5 mo ago |
| 74 | Knowledge base from "Spinning Up in Deep RL" by Joshua Achiam (OpenAI, MIT-licensed). | alirezarezvani/ | 28k | — | ~2.8k | Automated safety check: Pass | MIT | 1 mo ago |
| 75 | Tests/benchmarks a third-party LLM endpoint (OpenAI- or Anthropic-compatible): availability, fidelity, speed, concurrency, protocol compliance, quality regression. | daymade/ | 1.4k | — | ~4.7k | Automated safety check: Pass | MIT | yesterday |
| 76 | Generate and improve prompts using best practices for OpenAI GPT-5 and other LLMs. | jamesrochabrun/ | 216 | — | ~4.2k | Automated safety check: Pass | MIT | 9 mo ago |
| 77 | Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc. | aiskillstore/ | 433 | 3 repos | ~3.9k | Automated safety check: Pass | No licence | yesterday |
| 78 | 78.Geo Crawlers AI crawler access analysis. | sickn33/ | 47k | 1 repo | ~4.8k | Automated safety check: Notes | MIT | 2 days ago |
| 79 | Save the current conversation as a trajectory JSON file in OpenAI chat completion format for analysis and fine-tuning | AgentToolkit/ | 123 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 80 | 80.Memory Setup Enable and configure Moltbot/Clawdbot memory search for persistent context. | sundial-org/ | 663 | 1 repo | ~1k | Automated safety check: Pass | No licence | 7 mo ago |
| 81 | Web research API with OpenAI-compatible chat completions and async tasks | gooseworks-ai/ | 1.2k | 1 repo | ~3k | Automated safety check: Pass | MIT | 2 days ago |
| 82 | Integrate and route AI model requests through RouterBase. An agent skill from davepoon/buildwithclaude. | davepoon/ | 3.6k | — | ~1.1k | Automated safety check: Pass | MIT | 2 days ago |
| 83 | A skill your agent uses when benchmarking browsing-skills actions, comparing a maintained site skill against a no-skill browser agent, measuring OpenAI API token usage, wall time, API calls… | browsing-skills/ | 117 | — | ~596 | Automated safety check: Pass | MIT | 4 mo ago |
| 84 | Generate or edit raster images through an OpenAI-compatible image API. | hashgraph-online/ | 1.3k | — | ~852 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 85 | Migrate an application to or from Cohere with a provider adapter, parallel embedding index, quality evaluation, canary traffic, and rollback. | jeremylongshore/ | 2.8k | — | ~1.1k | Automated safety check: Pass | MIT | yesterday |
| 86 | Encapsulate Together AI SDK v2 behind a typed adapter with catalog-resolved models, bounded retries, streaming normalization, usage capture, and OpenAI-compatible migration seams. | jeremylongshore/ | 2.8k | — | ~1k | Automated safety check: Pass | MIT | yesterday |
| 87 | Use Venice's Alpha POST /responses endpoint - an OpenAI-compatible, stateless Responses API with typed output blocks (reasoning, message, functioncall, websearchcall). | veniceai/ | 144 | — | ~3.7k | Automated safety check: Pass | MIT | 5 days ago |
| 88 | Adding provider-backed LLM text generation to an Effect-based Golem agent with effect/unstable/ai and an Effect AI provider. | golemcloud/ | 1.5k | — | ~3.3k | Automated safety check: Pass | Unknown | yesterday |
| 89 | Check whether a website's robots.txt allows the AI crawlers that decide visibility in ChatGPT Search, Perplexity, Claude, Gemini, and Microsoft Copilot. | davepoon/ | 3.6k | — | ~1.5k | Automated safety check: Pass | MIT | 2 days ago |
| 90 | 添加和配置第三方 API 中转站供应商到 OpenClaw。当用户需要添加新的 API 供应商、配置中转站、设置自定义模型端点时使用此技能。支持 Anthropic 兼容和 OpenAI 兼容的 API 格式。 | aAAaqwq/ | 105 | 1 repo | ~1.8k | Automated safety check: Pass | MIT | 2 days ago |
| 91 | 91.Openai Check OpenAI API access and list the models your key can use. | Anil-matcha/ | 1.3k | — | ~395 | Automated safety check: Pass | MIT | 5 days ago |
| 92 | Local TensorZero documentation reference (latest). An agent skill from olorehq/olore. | olorehq/ | 104 | — | ~1.6k | Automated safety check: Pass | MIT | yesterday |
| 93 | 93.Venice Chat Call POST /chat/completions on Venice. An agent skill from veniceai/skills. | veniceai/ | 144 | — | ~5.9k | Automated safety check: Pass | MIT | 5 days ago |
| 94 | Analyze images and multi-frame sequences using OpenAI GPT vision models | benchflow-ai/ | 1.8k | — | ~5k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 95 | 95.Vision See and understand images when you (the current model) have no native vision. | aiskillstore/ | 433 | — | ~1.1k | Automated safety check: Pass | No licence | yesterday |
| 96 | Route text-labeling requests across LDA topic modeling, sklearn baselines, pretrained transformer models, and OpenAI-compatible LLM labeling. | Drchronx/ | 139 | — | ~1.1k | Automated safety check: Pass | Unknown | 4 mo ago |