全部能力

在执行任何涉及 Supabase 的任务时使用。触发条件：Supabase 产品（Database、Auth、Edge Functions、Realtime、Storage、Vectors、Cron、Queues）；客户端…

在创建新技能、编辑现有技能或在部署前验证技能是否正常工作时使用

当用户希望使用模板和数据大规模创建 SEO 驱动的页面时使用。当用户提及“programmatic SEO”、“template pages”、“pages… ”时也可使用。

使用 Firebase CLI 为 Firebase 提供基础设置、身份验证和项目管理工作流。在检查 Firebase CLI 版本（必须使用 'npx -y firebase-tools@latest --version'）、初始化 Firebase 环境、进行身份验证、设置活动项目，或设置 `google-services.json` 或 `GoogleService-Info.plist` 文件时使用。

关于使用 Sentry CLI 从命令行与 Sentry 交互的指南。当用户询问查看 issues、events、projects、organizations 等内容时使用。

设置 Convex 认证、身份映射和访问控制。用于登录和认证。

通过 Microsoft Graph 预配 Microsoft Entra Agent Identity Blueprint、BlueprintPrincipals 以及每个实例的 Agent Identity，并配置 OAuth 2.0 token…

引导用户完成协作撰写文档的结构化工作流。当用户需要编写文档、提案、技术规范、决策……时使用。

发现并列出网站上的所有 URL，支持可选的搜索过滤。当用户希望在海量网站中查找特定页面、列出所有 URL、查看网站结构、查找某内容在域名中的具体位置，或者提到“映射网站”、“查找……的 URL”、“……有哪些页面”或“列出所有页面”时，请使用此技能。当用户明确知道所在网站但不知道具体页面时，此技能必不可少。

使用基于令牌的身份验证在 Vercel 上部署和管理项目。适用于使用访问令牌而非交互式登录操作 Vercel CLI 的场景——……

此技能提供了通过 REST 调用与 Notion API 交互的全面指南。每当用户要求与 Notion 交互时，均应使用此技能，包括读取、创建、更新或删除页面、数据库、块、注释或任何其他 Notion 内容。该技能涵盖了身份验证、所有可用端点、分页、错误处理和最佳实践。

在任何已抓取的页面上控制并交互实时浏览器会话——点击按钮、填写表单、导航流程，并使用自然语言提示或代码提取数据。当用户需要进行超越简单抓取的网页交互时使用：登录网站、提交表单、点击分页、处理无限滚动、导航多步骤结账或向导流程，或者当常规抓取因内容隐藏在 JavaScript 交互之后而失败时使用。也可用于通过配置文件进行需身份验证的抓取。触发词包括“interact”、“click”、“fill out the form”、“log in to”、“sign in”、“submit”、“paginated”、“next page”、“infinite scroll”、“interact with the page”、“navigate to”、“open a session”或“scrape failed”。

获取 Firecrawl 凭据并在项目中配置 SDK。适用于应用程序需要 `FIRECRAWL_API_KEY`、需要将 Firecrawl 添加到 `.env`、当……

web-search — 一项面向 AI 智能体的可安装技能，由 inference-sh-skills/skills 发布。

agent-browser — 一项面向 AI 智能体的可安装技能，由 inference-sh-skills/skills 发布。

通过 inference.sh CLI 自动化 Twitter/X，实现发帖、互动和用户管理。应用：x/post-tweet、x/post-create（含媒体）、x/post-like，…

Generate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model catalog: FLUX 2 (Klein 9B/4B, Pro, Dev, Flash, Turbo, Max), Google Nano Banana 2 / Pro, OpenAI GPT Image 2, ByteDance Seedream 5 / 4-5 / 4-0 and Dreamina 4-0, Alibaba Qwen Image and Z-Image Turbo, Wan 2-7. Covers both text-to-image (t2i) and image-to-image / edit (i2i) endpoints — the skill picks the right model for the user's actual intent (typography precision, photoreal portraits, sub-second iteration, multi-reference brand styling, open-weights workflow) and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "generate image", "make a picture", "text to image", "AI image", "make an image of …", "image to image", "i2i", or any explicit ask to create or restyle an image.

Extend or continue an existing video clip on RunComfy via the `runcomfy` CLI. Routes to Google Veo 3-1's `extend-video` and `fast/extend-video` endpoints — pick the source video plus a prompt describing what should happen next, and the model produces a clip that continues the original with consistent motion, lighting, and subject identity. Use when the user has a short Veo clip and wants it longer, or wants a chained narrative built shot-by-shot from a single seed clip. Triggers on "extend video", "continue video", "longer video", "video extend", "make this clip longer", "Veo extend", "chain video shots", "video continuation", or any explicit ask to take an existing video and add more frames after it.

Region edits across video frames on RunComfy via the `runcomfy` CLI — remove an object that appears across many frames, clean up wires or watermarks, replace a region with matching motion. Routes across Wan 2-7 edit-video (default, prompt-driven region edits with spatial language), Lucy Edit Restyle (identity-stable region-aware restyle), and Seedream 4-0 edit-sequential (when treating the clip as a frame stack). Picks the right route based on whether the change is prose-driven, identity-locked, or needs frame-by-frame still inpaint chained into a video. Triggers on "video inpaint", "video inpainting", "remove from video", "mask region in video", "clean up video", "remove object from clip", "video patch", "frame-by-frame edit", "remove watermark from video", "remove passing person", or any explicit ask to edit a region across video frames.

Mask-driven image inpainting on RunComfy via the `runcomfy` CLI. Routes to Tongyi MAI Z-Image Turbo Inpainting (the dedicated inpainting endpoint with mask, strength, and control-scale) and to identity-preserving edit models (Nano Banana 2 Edit, GPT Image 2 Edit, FLUX Kontext Pro) when a mask isn't available and the region must be described instead. Use for object removal, watermark removal, region replacement, blemish cleanup, and any controlled local edit where a binary mask defines the target area. Triggers on "inpaint", "inpainting", "image inpaint", "remove from image", "fill region", "mask-driven edit", "remove watermark", "remove object", "patch the photo", "fill the hole", or any explicit ask to edit a specific masked region of a still.