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
5,215 results · page 110 of 174
- View details
cad-skillSkillMedia
Generate interior design planning artifacts, 2D SVG floorplans, BOM outputs, analysis boards, and renovation image sets from structured requirements. Use for staged interior-design work that moves through plan, 2D drafting, BOM, and image outputs.
Ready to connect★ 96
- View details
car-model-generationSkillMedia
A professional skill for generating 3D car model images, using the Gemini API to create high-quality car showcase images and Doubao AI for quality analysis and optimization. Use cases: automotive brand promotional videos, car model showcases, and car advertising material generation. Keywords: car mo
Ready to connect★ 96
- View details
codex-collabSkillMedia
Use when the user asks to invoke, delegate to, or collaborate with Codex on any task. Also use PROACTIVELY when an independent, non-Claude perspective from Codex would add value — second opinions on code, plans, architecture, or design decisions.
Ready to connect★ 96
- View details
collectSkillMedia
Download YouTube videos and extract frames using yt-dlp and ffmpeg for YOLO training data. Use when you need to gather frames from a video URL.
Ready to connect★ 96
- View details
design-craftSkillMedia
Constraint + process skill for UI that reads "designed", not "AI-generated". Mandatory two-pass process (token plan grounded in the subject's world + ONE signature element, then self-critique) whose output is the project's root DESIGN.md — the design contract re-read on every UI generation. Navigati
Ready to connect★ 96
- View details
film-masterSkillMedia
Turns scripts or scene descriptions into professional, continuous, executable film storyboards, then hands them to the current image generation route.
Ready to connect★ 96
- View details
flow-skillSkillMedia
Generate, edit, validate, and bundle draw.io or diagrams.net diagrams in XML form. Use for new diagrams, local XML edits, shape-library diagrams, truncated XML continuation, and local image export.
Ready to connect★ 96
- View details
geography-video-effectsSkillMedia
Turn geography, culture, and history scripts into credible, readable, spatially grounded maps and cinematic visuals.
Ready to connect★ 96
- View details
internet-ad-directorSkillMedia
Internet Ad Director — consultant and executor in one. Given a product/brand, creative brief, target market, and ad platform, it first produces a viral ad creative strategy (viral element matching + director style recommendation + short-video structure), then after user confirmation implements it st
Ready to connect★ 96
- View details
jimeng-cliSkillMedia
Use when an agent needs Dreamina（即梦） login, sessions, task history, Seedream 5.0 Pro, or Seedance 2.5 image/video generation through the dreamina CLI.
Ready to connect★ 96
- View details
lark-vc-agentSkillMedia
Feishu video conferencing: lets the bot join/leave an ongoing meeting on behalf of the current user and read real-time events during the meeting (participants joining and leaving, speaking, chat, screen sharing, etc.). 1. Use +meeting-join / +meeting-leave when the user provides a 9-digit meeting ID
Ready to connect★ 96
- View details
lark-whiteboardSkillMedia
Lark Whiteboard: query and edit whiteboards in Lark cloud docs. Supports exporting whiteboards as preview images, exporting the raw node structure, and updating whiteboard content using DSL (converted to OpenAPI format), PlantUML, or Mermaid. Use this skill when the user needs to view whiteboard con
Ready to connect★ 96
- View details
modern-jetpack-composeSkillMedia
Guides writing, reviewing, and reasoning about modern Android UI code using Jetpack Compose. Covers best practices for state management, side effects, recomposition, navigation, Material 3 design, accessibility, and performance. Use when reading, writing, or reviewing any Jetpack Compose project.
Ready to connect★ 96
- View details
omni-mg-animationSkillMedia
Create paid motion-graphics videos in Kunpeng with MiniMax H3, Omni, or Seedance Mini. Use for MG animation, app showcase MG, talking-head graphic overlays, text-to-video MG explainers, and editor/canvas workflows that may spend credits.
Ready to connect★ 96
- View details
promo-briefSkillMedia
Creative brief for product promo videos. Input a product description or GitHub link; it automatically fetches product info, distills core selling points, and recommends visual style and narrative structure. Triggered when the user mentions "宣传片", "promo", "产品视频", "做个视频介绍", or "项目宣传".
Ready to connect★ 95
- View details
promo-editorSkillMedia
Uses HyperFrames to stitch all assets together by storyboard timecodes, add text layers, animations, and transitions, and render a complete promotional video MP4. This is the core rendering engine of the entire pipeline. Triggered automatically once assets are confirmed.
Ready to connect★ 95
- View details
promo-music-makerSkillMedia
Generates BGM plans and music generation prompts that closely match the pacing of product promo visuals. Reads brief, storyboard, EDL, DESIGN, or the final cut, and outputs music style, BPM, emotional curve, beat-sync table, Mureka/Skywork Music Maker English prompt, negative prompt, and editing sug
Ready to connect★ 95
- View details
promo-storyboardSkillMedia
Shot-by-shot storyboard script for promotional videos. Based on the creative brief, generates a 7-dimension visual description and detailed HyperFrames prompt for each Shot; it is key to the quality of the entire video. Automatically triggered after the user confirms the brief.
Ready to connect★ 95
- View details
promo-workflowSkillMedia
Master control workflow for product promo video production. Chains 6 skills together, executing stage by stage with pauses for confirmation. A fully automated pipeline from a product URL to a finished MP4 with BGM. Triggered when the user mentions "做个宣传片", "promo", "产品视频", or "项目介绍视频".
Ready to connect★ 95
- View details
runninghubSkillMedia
Generate supported images, videos, audio, and 3D models via RunningHub API and run RunningHub AI Applications by webappId.
Ready to connect★ 96
- View details
scene-image-anchorSkillMedia
Internal consistency rules shared across all storyboard image generation workflows, establishing visual anchors based on real assets and environment groups.
Ready to connect★ 96
- View details
storyboard-sketchSkillMedia
Cinematic shot-replication storyboard generator. Core workflow: original film keyframes → line-art sketches → sketch + character reference → cinematic storyboard final images.
Ready to connect★ 96
- View details
vibe-orchestratorSkillMedia
Master workflow controller for Lovable-style development. Creates working UI immediately from ANY prompt - no questions asked, no choices given. Resumes or materializes .toh/plan.md, generates the design identity (root DESIGN.md) first, then spawns specialist sub-agents from plan task lines (ui-buil
Ready to connect★ 96
- View details
video-copy-analyzerSkillMedia
All-in-one video copywriting analysis tool. Downloads online videos (Bilibili/YouTube/Douyin, etc.), transcribes Chinese speech with FunASR Nano, automatically corrects the transcript, and performs three-dimensional comprehensive analysis (TextContent/Viral/Brainstorming). Use cases: when users need
Ready to connect★ 96
- View details
video-style-replicationSkillMedia
Uses Kimi for shot-by-shot analysis to extract the narrative, cinematography, pacing, and visual grammar of a reference video, then adapts them to the user's own content and assets.
Ready to connect★ 96
- View details
yolodexSkillMedia
Train a custom YOLO object detection model from any YouTube gameplay video. Provide a video URL and target classes, and this skill handles the entire pipeline autonomously — frame extraction, AI-powered labeling, data augmentation, training, and evaluation with iterative improvement.
Ready to connect★ 96
- View details
catia-v5-production-operatorSkillMedia
Operate CATIA V5 through daiemon12/catia-v5-mcp-server under a conservative production execution contract. Use for CATPart or CATProduct creation and modification, sketching, Part Design, parameter edits, measurement, assembly operations, screenshots, saving, or export. Requires serialized CATIA cal
Ready to connect★ 95
- View details
skf-brief-skillSkillMedia
Design a skill scope through guided discovery. Use when the user requests to "create a skill brief" or "brief a skill".
Ready to connect★ 95
- View details
macos-controlSkillMedia
Control macOS GUI applications via mouse automation, keyboard input, screenshots, image recognition, and AppleScript execution. Use when you need to interact with macOS app UIs, take screenshots, click buttons, type text, scroll, drag, or locate images on screen.
Ready to connect★ 94
- View details
receiving-code-reviewSkillMedia
Processes code review feedback by classifying each finding, reproducing or validating it against the real contract, applying the smallest in-scope fix, and re-running focused proof. Use after comments arrive on a diff, pull request, design, or implementation. Not for requesting a first review or deb
Ready to connect★ 94
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.
53,788 of the 54,220 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.