Total 58,115 skills
Showing 12 of 58115 skills
Implements accessible modals and drawers with focus trap, ESC to close, scroll lock, portal rendering, and ARIA attributes. Includes sample implementations for common use cases like edit forms, confirmations, and detail views. Use when building "modals", "dialogs", "drawers", "sidebars", or "overlays".
Integrates Amazon Location Service APIs for AWS applications. Use this skill when users want to add maps (interactive MapLibre or static images); geocode addresses to coordinates or reverse geocode coordinates to addresses; calculate routes, travel times, or service areas; find places and businesses through text search, nearby search, or autocomplete suggestions; retrieve detailed place information including hours, contacts, and addresses; monitor geographical boundaries with geofences; or track device locations. Covers authentication, SDK integration, and all Amazon Location Service capabilities.
One-click parsing of the actual download URL for WeChat Channels videos. Paste a WeChat Channels sharing link to get the video title, cover image, and HD watermark-free download URL. Trigger words: Use when the user mentions 'parse WeChat Channels', 'WeChat Channels download URL', 'WeChat Channels download', 'WeChat Channels watermark-free download'
Official Notion Model Context Protocol Server for workspace interaction.
Diagnose why AdMob ads are not showing in any Expo/React Native app. Use when the user reports real/test ads not displaying, asks why production ads have NO_FILL, whether the AdMob config/package/unit IDs are correct, how a TEST_ADS flag and UMP consent gate affect ads, or how to debug ads on a real device via adb logcat. Not project-specific — works for any app using react-native-google-mobile-ads.
Creates and maintains concise AGENTS.md and CLAUDE.md project instruction files. Use when asked to create AGENTS.md, update AGENTS.md, maintain agent docs, set up CLAUDE.md, document repository agent conventions, or keep coding-agent instructions minimal and reference-backed.
Postgres best practices maintained by Supabase, for Postgres running anywhere. Load this skill BEFORE writing or changing anything that lives in a Postgres database: creating or altering tables and columns (including choosing column types), schema design, migrations and declarative schema files, RLS policies and the tests that verify them, indexes, triggers, database functions, queues and scheduled jobs (pg_cron, pgmq), vector/semantic search (pgvector), and restoring dumps (pg_restore) or importing data. Also load it when diagnosing slow queries, high CPU, timeouts, EXPLAIN plans, connection exhaustion, locking, bloat, or rows visible to the wrong user or tenant. This is not just a performance guide — schema, migration, security, and SQL authoring tasks need these rules too, even for a one-column change or a single query.
图片版权侵权检测与风险分析。当用户提到版权检测、版权核查、图片侵权检查、图片版权风险、版权相似度搜索、TRO风险分析、权利人查询、版权合规验证、copyright detection, image infringement, copyright risk, TRO risk, copyright lookup, infringement analysis, Ruiguan时触发此技能。即使用户未明确提及"版权"，只要其需求涉及检查图片是否可能侵犯已登记的版权作品，也应触发此技能。
基于智慧芽的专利图片相似度搜索，支持通过图片URL检索实用新型专利。当用户提到实用新型专利图片搜索、实用新型专利侵权检查、实用新型专利搜索、以图搜专利、实用新型专利相似度检测、专利图片匹配、专利形状/图案/色彩匹配、检查产品结构是否侵犯已有实用新型专利、patent image search, utility model patent search, patent reverse image search, utility model patent lookup, PatSnap, patent similarity时触发此技能。即使用户未明确提及"智慧芽"或"专利图片"，只要其需求涉及通过图片查找相似实用新型专利或排查实用新型专利风险，也应触发此技能。本技能仅支持实用新型专利，外观设计专利检索请使用 linkfox-zhihuiya-patent-image-search。
基于 Google 搜索的 AI 概览（AI Overview / AI Mode）抓取，针对一个关键词返回主搜索的 AI 概览要点，适合用最新网页信息做深度调研、技术问答、长尾选品分析、海外消费者偏好分析。仅支持单轮对话，如需追问须由 agent 总结上下文后发起新请求。当用户提到 Google AI、AI Overview、AI Mode、谷歌AI概览、谷歌AI搜索、海外深度调研、长尾选品调研、消费者偏好分析、网页要点总结、Google AI search, AI Overview, AI Mode, deep research, consumer preference analysis 等场景时触发此技能。即使用户未明确提到"Google AI"，只要其需求是"用谷歌搜索 + AI 总结网页要点"，也应触发此技能。
Product Image Generation (Non-apparel Category). Supports single images or image sets: white background main images, scene images, close-up images, selling point layout images, A+ detail page images. Single image of a single type is generated directly; multiple images of multiple types are automatically arranged and planned. Triggered when the user says "create an image set", "create a white background image", "create a scene image", "create a selling point image", "create an A+ image", "create a close-up image". Pure image editing operations go through linkfox-aigc-imagegen.
使用卖家精灵数据在亚马逊上查找和分析竞品，覆盖12个站点，包含销量、BSR、定价、评分和增长趋势等商品指标。当用户提到竞品查询、竞品分析、ASIN反查、竞争商品研究、查找相似商品、市场竞品发现、商品对标、竞品销量估算、分析竞争Listing、competitor analysis, ASIN reverse lookup, competitor sales, competitor research, SellerSprite, market competitor discovery, competitor trends时触发此技能。即使用户未明确提及"卖家精灵"或"竞品查询"，只要其需求涉及通过ASIN、关键词、卖家名称、品牌或品类发现和分析亚马逊竞品，也应触发此技能。