AI model or service
OpenAI agent skills, page 14
OpenAI skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 625 | 625.Economy Mode Shifts Layer 3 model selection to cost-optimized alternatives when economy mode is active. | FritzAndFriends/ | 145 | 2 repos | ~1.3k | Automated safety check: Pass | MIT | 5 mo ago |
| 626 | Generate a concise, shareable code snippet URL for code.franciscomoretti.com. | FranciscoMoretti/ | 1.2k | — | ~178 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 627 | 627.Review Review local code changes for bugs, regressions, missing tests, and pragmatic improvements. | devoxx/ | 684 | — | ~652 | Automated safety check: Pass | MIT | 11 days ago |
| 628 | 628.Vibe Scene Author, repair, render, and inspect VibeFrame scene projects built from STORYBOARD.md and DESIGN.md. | vericontext/ | 175 | — | ~1.8k | Automated safety check: Pass | MIT | 5 days ago |
| 629 | Runs the six-agent CraftBot workflow in this specific repository, turning a design brief and references into versioned Blender Python scripts, renders, a rationale and an archived transcript. | lukapiskorec/ | 154 | — | ~9.1k | Automated safety check: Pass | Unknown | 10 days ago |
| 630 | 630.Vllm Deploy K8s Deploy vLLM to Kubernetes (K8s) with GPU support, health probes, and OpenAI-compatible API endpoint. | vllm-project/ | 102 | — | ~2k | Automated safety check: Pass | Apache-2.0 | 6 mo ago |
| 631 | 631.Brand Guidelines Applies OpenAI's brand colors and typography to any artifact that should match the Codex/OpenAI look-and-feel. | composio-community/ | 17k | — | ~617 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 632 | 632.AI Models Latest AI models reference - Claude, OpenAI, Gemini, Eleven Labs, Replicate | alinaqi/ | 707 | — | ~4.1k | Automated safety check: Pass | MIT | 16 days ago |
| 633 | 633.Mmsp Dev Fixed workflow for developing MMSP itself — adding or updating model support, and changing its pages. | Prism-Shadow/ | 113 | — | ~7.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 634 | 634.Second Opinion Get a second opinion from OpenAI's Codex CLI running locally. | peterkrueck/ | 1.4k | — | ~2.4k | Automated safety check: Warn | MIT | 2 mo ago |
| 635 | Extracts structured data — fields, tables, line items — out of documents into a validated schema using the gaik toolkit, and designs schemas that stay inside provider limits and produce checkable… | GAIK-project/ | 100 | — | ~3.2k | Automated safety check: Pass | MIT | yesterday |
| 636 | Step-by-step guide for adding a new guardrail provider to Agent Kernel. | yaalalabs/ | 192 | — | ~3.5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 637 | LiteLLM-RS Configuration Architecture. An agent skill from majiayu000/litellm-rs. | majiayu000/ | 117 | — | ~3.2k | Automated safety check: Pass | MIT | 2 days ago |
| 638 | 638.CSV Insights Summarize a CSV, compute basic stats, and produce a markdown report + a plot image. | simonw/ | 782 | — | ~154 | Automated safety check: Pass | No licence | 6 days ago |
| 639 | 639.Uipath Functions UiPath Coded Functions — deterministic Python or TypeScript/JavaScript units built with the uip function CLI (new -l py|ts|js, init, serve, run, pack, publish); the functions map in uipath.json… | UiPath/ | 167 | — | ~3.6k | Automated safety check: Notes | MIT | today |
| 640 | 640.Agent Eval Cases Decide which AI agent behaviors are worth an eval case, then write those cases — harness-, framework-, and language-agnostic. | agentailor/ | 132 | — | ~5.3k | Automated safety check: Pass | MIT | 1 mo ago |
| 641 | 641.Fkteams fkteams 多智能体协作 AI 助手的完整使用指南。当用户需要启动 fkteams、切换工作模式(团队/深度/讨论/自定义)、 通过命令行或管道执行查询、管理单个智能体(coder/researcher/fkteamshelper/analyst/remote/generalist)、管理会话历史(保存/加载/导出/恢复)、… | wsshow/ | 153 | — | ~2.1k | Automated safety check: Warn | MIT | 1 mo ago |
| 642 | Triage an exported chat history into what to ingest, what to archive and what to delete, with a privacy pass first. | undefined-ui/ | 1k | — | ~527 | Automated safety check: Pass | MIT | yesterday |
| 643 | 643.Ig Human Strip the machine fingerprint out of any draft - em dashes, AI slop words, invisible watermark characters - and score it against a five-check detection panel before it goes out. | Jakeschincariol/ | 760 | — | ~1.3k | Automated safety check: Pass | MIT | 27 days ago |
| 644 | Generate game assets using AI image generation APIs (DALL-E, Replicate, fal.ai) and prepare them for Godot. | jwynia/ | 170 | — | ~3.8k | Automated safety check: Pass | MIT | 7 mo ago |
| 645 | 645.Project Init Initialize and configure the Operator Project Brain. An agent skill from aerovato/operator-memory. | aerovato/ | 414 | — | ~240 | Automated safety check: Pass | BSD-3-Clause | yesterday |
| 646 | 646.Kesekit Guide Ko AI 도구(Claude, ChatGPT, Cursor, Copilot)용 시큐어 코딩 프롬프트와 가이드를 생성합니다. | cdppcorp/ | 360 | — | ~1.3k | Automated safety check: Pass | MIT | 6 mo ago |
| 647 | Rules for adding and editing LobeHub's user-facing strings with react-i18next: flat dot-notation keys, the default locale folder, namespaces and when to run bun run i18n. | lobehub/ | 83k | — | ~885 | Automated safety check: Pass | Unknown | today |
| 648 | Turns footage, audio and a storyboard plan into a finished short video with FFmpeg jump-cuts, subtitle burn-in and a final polish pass. | foryourhealth111-pixel/ | 3.6k | — | ~838 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 649 | 649.Chatgpt Pro Line Use the packaged ChatGPT Pro communication line for blocking AI-to-AI reasoning through the persistent browser session. | angieruiz17/ | 142 | — | ~4.9k | Automated safety check: Warn | MIT | 26 days ago |
| 650 | 650.Qianwenai Wiki 千问AI平台(Qianwen AI Platform / DashScope)官方文档离线知识库,用于检索并回答模型选择、API Key、OpenAI 兼容接口、DashScope SDK、文本与多模态生成、图像/视频/语音、Realtime API、Embedding、Reranking、Function Calling、MCP、批量调用、计费、Token Plan、API/SDK/CLI… | chujianyun/ | 742 | — | ~717 | Automated safety check: Pass | Unknown | yesterday |
| 651 | 651.Deep Research This skill should be used when conducting comprehensive research on any topic using the OpenAI Deep Research API. | glebis/ | 391 | — | ~2.6k | Automated safety check: Notes | MIT | 2 days ago |
| 652 | Convert Claude Code skills to work on OpenAI Codex, Google Gemini CLI, Google Antigravity, and Cursor. | AgriciDaniel/ | 179 | — | ~1.2k | Automated safety check: Pass | MIT | 6 mo ago |
| 653 | 653.Optimize For AI Optimize content for AI search engines — ChatGPT, Perplexity, Claude, Gemini, Google AI Overviews. | galfrevn/ | 237 | — | ~4.3k | Automated safety check: Pass | MIT | 1 mo ago |
| 654 | 654.Prompt Adapt Adapt and convert AI prompts between different models and platforms. | AgriciDaniel/ | 111 | — | ~793 | Automated safety check: Pass | MIT | 6 mo ago |
| 655 | 655.Image Generation Generate images and iteratively edit saved image artifacts. An agent skill from MemTensor/memmy-agent. | MemTensor/ | 2.1k | — | ~727 | Automated safety check: Pass | MIT | today |
| 656 | Initialize or repair a Notion Course Pack workspace, or create a real course from a complete book, course, paper set, transcript set, local files, pasted materials, or authorized Notion pages. | AlphaMao1/ | 130 | — | ~2.9k | Automated safety check: Pass | MIT | 17 days ago |
| 657 | Produce a square cover art image for a given podcast episode title, with vibrant, creative artwork and no text or people by default. | impredicative/ | 157 | — | ~372 | Automated safety check: Pass | LGPL-3.0 | 5 days ago |
| 658 | 658.Save Skill Helps users permanently set up the OpenTax skill on their AI platform so they don't have to load it every time. | filedcom/ | 111 | — | ~724 | Automated safety check: Pass | AGPL-3.0 | today |
| 659 | Generates diagrams, flowcharts and conceptual illustrations with OpenAI's gpt-image models, while leaving data plots and result figures to real plotting code. | RealSeaberry/ | 257 | — | ~1.9k | Automated safety check: Notes | MIT | 1 mo ago |
| 660 | Produces a personalized, broadcast-style fan-cam video from one photo of a person, using the genmedia CLI to generate a stadium frame and then animate it. | fal-ai-community/ | 251 | — | ~3.2k | Automated safety check: Pass | No licence | 12 days ago |
| 661 | 661.Test Afm Binary Test a pre-built afm binary at any path — runs pre-flight safety checks, then any combination of unit tests, assertions, smart analysis, promptfoo evals, batch validation, OpenAI compat, GPU… | scouzi1966/ | 346 | — | ~3.8k | Automated safety check: Pass | MIT | yesterday |
| 662 | 662.Rank Geo AI search optimization audit. An agent skill from Houseofmvps/claude-rank. | Houseofmvps/ | 147 | — | ~671 | Automated safety check: Pass | MIT | 3 mo ago |
| 663 | 663.Openai Agents Build AI applications with OpenAI Agents SDK - text agents, voice agents, multi-agent handoffs, tools with Zod schemas, guardrails, and streaming. | coco-research/ | 513 | — | ~3.3k | Automated safety check: Pass | MIT | yesterday |
| 664 | 664.Keirouter Image Generate images via KeiRouter /v1/images/generations using OpenAI DALL-E / Gemini Imagen / FLUX / MiniMax / Stability AI / Fal.ai models. | mydisha/ | 147 | — | ~691 | Automated safety check: Pass | MIT | 1 mo ago |
| 665 | 665.Git Commit Generate well-formatted git commit messages following conventional commit standards | ThinkInAIXYZ/ | 6.4k | — | ~406 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 666 | Adds one optional external Codex critique that tries to break a council's decision draft, sent to OpenAI only after you consent. | affaan-m/ | 276k | — | ~1.5k | Automated safety check: Pass | MIT | yesterday |
| 667 | 667.Image Gen Generate or edit images via Google Gemini (nano-banana-pro) or OpenAI gpt-image-2. | nicknisi/ | 114 | — | ~502 | Automated safety check: Pass | MIT | 2 mo ago |
| 668 | Prompt-crafting guide for gpt-image-2.5: which image tool to call, which model to pick, and how to write prompts, edit with references and refine over turns. | code-yeongyu/ | 474 | — | ~2.3k | Automated safety check: Pass | MIT | today |
| 669 | 审查代码改动(review diff / PR)时使用——按固定清单过正确性、边界、错误处理和测试盲区,避免只看顺眼不顺眼。 | 7-e1even/ | 285 | — | ~176 | Automated safety check: Pass | MIT | 1 mo ago |
| 670 | Run the Kiln pre-release smoke test suite plus the standard CI checks (checks.sh), diagnose every prerelease test that broke (and why), and write a clean readable report with recommended actions. | Kiln-AI/ | 5.2k | — | ~7.8k | Automated safety check: Notes | Unknown | yesterday |
| 671 | SEO, AEO (Answer Engine Optimization), and GEO strategy for search engines and AI visibility. | manojbajaj95/ | 105 | — | ~4k | Automated safety check: Pass | MIT | 22 days ago |
| 672 | 当需要在基础身份之上叠加可切换的人格风格层时调用此 skill。典型场景包括:为同一产品提供多种人格选项(如 GPT-5.1 的 friendly/professional/quirky 模式)、设计人格切换机制、防止人格泄露到用户内容中。 | kangarooking/ | 208 | — | ~1k | Automated safety check: Pass | MIT | 5 mo ago |