Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: Media
5,210 results · page 35 of 174
- View details
card-designSkillMedia
Social media card visual design system: provides color schemes, Chinese font hierarchy, full-bleed layouts, category skeletons, and dead-space/density checks to avoid template-like PPT and cheap AI-generated look. Use when users say things like "the card looks bad, optimize visuals, cover/poster des
Ready to connect★ 1k
- View details
chart-visualizationSkillMedia
Visualizes data as charts. Invoke this skill when the user needs to generate charts such as bar charts, line charts, pie charts, scatter plots, radar charts, Sankey diagrams, mind maps, or flowcharts; it calls the AntV API via the curl tool to generate chart images. Outputs static image URLs (25+ ty
Ready to connect★ 1k
- View details
clipifySkillMedia
Automatically extracts highlight clips from long videos, cutting them into standalone short videos. Supports 16:9→9:16 portrait conversion and word-by-word subtitle burning. Use when the user says "视频切片" (video slicing), "提取精彩片段" (extract highlights), "长视频切短" (cut long video short), "切成短视频" (cut int
Ready to connect★ 1k
- View details
comparison-cardSkillMedia
Comparison image / one-pager: generates A vs B parameter comparison graphics, pros-and-cons comparison tables, and product spec one-pagers. Renders as screenshot-ready visual cards with HTML+CSS, suitable for sharing on platforms like Xiaohongshu/Weibo. Use when the user says "做个对比图" (make a compari
Ready to connect★ 1k
- View details
ecom-details-imageSkillMedia
Generates e-commerce product visual plans: main image concepts, scene images, detail page visual direction, and AI image generation prompts. Use when the user says "商品主图", "详情页视觉", "电商配图方案", "商品场景图", "带货视觉", "产品视觉方向", or "详情页设计". This SKILL provides visual plans + image generation prompts (planning)
Ready to connect★ 1k
- View details
green-screenSkillMedia
Green screen keying / background replacement / compositing: extracts foreground subjects shot against a green screen (or blue screen / specified color) and composites them onto a new background — an image, video, solid color, or a blurred version of the foreground itself. Use when the user says 绿幕,
Ready to connect★ 1k
- View details
image-enhanceSkillMedia
Image enhancement / upscaling / sharpening: high-quality upscaling (Lanczos 2x/4x) + denoising + sharpening + auto contrast/saturation to improve blurry, dark, or noisy images. Use when the user says 图片放大, 图片变清晰, 提高清晰度, 图片增强, 去噪点, 锐化, 图片太糊了, 放大到高清, 提升画质, 优化图片, or 图片调亮调色. Based on shared/scripts/img_
Ready to connect★ 1k
- View details
meme-generatorSkillMedia
Meme / sticker generation: add classic top-and-bottom large text (white with black outline) to an image to make a meme, or add caption bars above/below the image to make a reaction image ("when..." format). Supports both Chinese and English, with automatic line wrapping and adaptive font size. Use w
Ready to connect★ 1k
- View details
skill-bilibili-uploadSkillMedia
Bilibili video publishing: upload videos to Bilibili with support for title/description/category/tags/cover/repost disclaimer/scheduled publishing. Use when the user says "投稿B站" "发B站" "上传到哔哩哔哩" "B站视频发布" "投个稿" "发到bilibili". Wraps the mature biliup CLI, with QR-code login + cookie reuse.
Ready to connect★ 1k
- View details
skill-my-accountSkillMedia
Queries the user's own logged-in identities on Xiaohongshu, Douyin, Kuaishou, Zhihu, and Video Accounts (视频号) in Easel, including followers, likes received, following, and lists of works. When the user asks things like 'which accounts am I logged into', 'who am I', 'my followers/likes', 'what have I
Ready to connect★ 1k
- View details
slideshow-videoSkillMedia
Photo album → video: turns a set of images into a video with Ken Burns slow zoom, transitions between images, background music, and per-image captions, automatically adapting to platform aspect ratios (vertical/square/landscape). Use when the user says 图片转视频 (images to video), 图片做成视频 (make a video f
Ready to connect★ 1k
- View details
subtitle-translateSkillMedia
Subtitle translation / bilingual subtitles: translate existing subtitles (SRT/VTT/ASS) into a target language, producing bilingual (original + translation) or translation-only subtitles, with optional soft-mounting or hard-burning into video. Use when the user says 字幕翻译, 翻译字幕, 双语字幕, 中英字幕, 给视频加翻译, SR
Ready to connect★ 1k
- View details
tts-voiceoverSkillMedia
Text-to-speech voiceover: turn copy/scripts into AI voice narration, voiceovers, or read-aloud audio. **If VOICE_PROVIDER is configured, it defaults to closed-source cloud TTS (CosyVoice2, etc. — expressive, human-like); edge is only a fallback when there is no key** (edge sounds more robotic/AI-lik
Ready to connect★ 1k
- View details
video-chaptersSkillMedia
Video chapters / timestamp table of contents: automatically generates chapter divisions and timestamped tables of contents for medium-to-long videos, for use in Bilibili parts / YouTube chapters / video descriptions, making it easy for viewers to jump around and improving watch-through rates. Use wh
Ready to connect★ 1k
- View details
video-editingSkillMedia
Edit videos with natural language commands: trimming, concatenation, speed changes, jump cuts with silence removal, text overlays, aspect ratio conversion, frame extraction for covers, GIF conversion, compression, and adding BGM/watermarks. Based on ffmpeg. Use when the user says "剪视频", "裁剪视频", "拼接视
Ready to connect★ 1k
- View details
video-highlightsSkillMedia
Highlight clipping for long videos / stream recordings: find highlight segments in a long video and cut them into multiple standalone short videos, with optional conversion to vertical 9:16 plus subtitles. Two methods for finding moments — audio energy peaks (where emotions surge / cheering / loudne
Ready to connect★ 1k
- View details
video-intro-outroSkillMedia
Video intro / outro: generates intro cards and outro cards with title, subtitle, logo, and follow prompts, and appends them to the main video (hard cut or fade transition). Use when the user says 片头、片尾、加片头片尾、开场卡片、结尾卡片、标题卡、关注引导页、订阅引导、视频开头加标题、结尾加点赞关注、intro、outro、片头动画. Deterministic ffmpeg wrapper base
Ready to connect★ 1k
- View details
video-reframeSkillMedia
Intelligently converts video aspect ratios, supporting 9:16/16:9/1:1, blurred background fill, focus cropping, and face-centered cropping. Use when the user says things like "convert between landscape and portrait", "change to 9:16", "make it vertical", "remove black bars", "adapt to platform sizes"
Ready to connect★ 1k
- View details
video-scriptSkillMedia
Generates video scripts covering all durations, from short videos (7-60 seconds) to medium-long videos (1-30 minutes). Short videos: Hook variant scoring, second-by-second timing, subtitle copy, cover design. Medium-long videos: retention optimization, pacing break points, forward hooks, chapter str
Ready to connect★ 1k
- View details
video-strategySkillMedia
Video production strategy and tool selection: comparison of AI video generation models, video script structure design, and production workflow planning, covering product demos, explainers, and social media short videos. Use when the user says "视频怎么做", "视频选型", "用什么工具做视频", "视频制作流程", "视频策略", or "视频系列规划
Ready to connect★ 1k
- View details
voice-cloneSkillMedia
Upload your own voice samples to clone a personalized voice, then use it to synthesize spoken narration, voiceovers, or product-promotion audio. Use when the user says things like “声音克隆、克隆/复刻我的声音、用我的声音配音、定制专属音色”. Requires the user to provide their own cloud provider credentials. For public, ready-ma
Ready to connect★ 1k
- View details
audioaccessorykitSkillMedia
Support automatic audio switching for paired third-party Bluetooth headphones or earbuds with AudioAccessoryKit. Use when a companion app registers an audio accessory, an app extension reports worn/removed placement or connected source-device changes, or AccessoryControlDevice capabilities and error
Ready to connect★ 1k
- View details
avkitSkillMedia
Create media playback experiences using AVKit. Use when adding video players with AVPlayerViewController, enabling Picture-in-Picture, routing media with AirPlay, using SwiftUI VideoPlayer views, configuring transport controls, displaying subtitles and closed captions, or integrating AVFoundation pl
Ready to connect★ 1k
- View details
carplaySkillMedia
Build CarPlay-enabled apps using the CarPlay framework. Use when creating navigation, audio, communication, EV charging, parking, or food ordering apps for the car display, working with CPTemplateApplicationScene, CPInterfaceController template hierarchies, CPListTemplate, CPMapTemplate, CPNowPlayin
Ready to connect★ 1k
- View details
natural-languageSkillMedia
Tokenize, tag, and analyze natural language text using Apple's NaturalLanguage framework and translate between languages with the Translation framework. Use when adding language identification, sentiment analysis, named entity recognition, part-of-speech tagging, text embeddings, or in-app translati
Ready to connect★ 1k
- View details
photokitSkillMedia
Implement, review, or improve photo picking, camera capture, and media handling in iOS apps using PhotoKit and AVFoundation. Use when working with PhotosPicker, PHPickerViewController, camera capture sessions (AVCaptureSession), photo library access, image loading and display, video recording, or me
Ready to connect★ 1k
- View details
acmmm-related-workSkillMedia
Use when building or auditing the related-work section of an ACM MM (ACM Multimedia) paper — covering the multimedia literature spread across vision, audio/speech, language, HCI/QoE, and systems, handling arXiv-speed concurrency, keeping citations double-blind, and verifying that cited "ACM MM paper
Ready to connect★ 1k
- View details
acmmm-supplementarySkillMedia
Use when organizing the ACM MM (ACM Multimedia) supplementary material due after the paper deadline — deciding what belongs in the 6-8 page body versus the supplement, packaging video/audio/interactive demos that render on a reviewer's machine, keeping all assets anonymous for double-blind tracks, a
Ready to connect★ 1k
- View details
acmmm-writing-styleSkillMedia
Use when revising an ACM MM (ACM Multimedia) paper for house style — putting the cross-modal contribution on the first page, framing media (figures, video, audio) as evidence rather than decoration, making the fusion the visible claim, and compressing the argument into a 6-8 page ACM sigconf body wi
Ready to connect★ 1k
- View details
aeja-theory-modelSkillMedia
Use when an American Economic Journal: Applied Economics (AEJ: Applied) manuscript needs a model to interpret, discipline, or structure its empirical estimates — not to lead the paper. Calibrates how much theory belongs in an empirical-first journal and where it goes; it does not design the identifi
Ready to connect★ 1k
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
53,585 of the 54,017 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.