You can think of a skill as a capability package built for an agent. It usually includes docs, execution rules, scripts, and reference materials, so the agent can complete a specific type of task more reliably instead of figuring everything out from scratch each time.

What can I create after installation?

You can ask your agent to handle text-to-video, image-to-video, reference-based generation, image creation and editing, talking avatars, text-to-speech, voice search, and voice cloning.

What materials do I need?

That depends on what you want to create. For video, you can start from a prompt, an image, or a reference asset. For talking avatars, you usually need a portrait and a script. For voice tasks, a script is often enough, so many workflows can start right away.

Can I pass local images, audio, and video files directly to my agent?

Yes. In this skill workflow, local image, audio, and video files are uploaded automatically when they are passed as parameters, so you do not need to upload them somewhere else first.

Where do I view the generated results?

After generation, the results can be viewed, managed, and edited inside Topview Board. That means you do not just get a file back, you also get a place to organize, preview, and continue editing your assets.

Does it include talking avatars and voice capabilities too?

Yes. Topview Skill does not only handle video generation. It also supports talking avatars, text-to-speech, voice search, and voice cloning, which makes it suitable for explainer videos, spoken content, and multilingual workflows.

Can I control the style of images and videos?

Yes. You can tell your agent the style, pacing, camera feel, or reference materials you want, and the skill will call the right capability to generate results that are closer to your goal.

Do I need to understand scripts and APIs myself?

No. This page is designed around the workflow of sending commands and requests to your agent. You only need to describe what you want, and the agent will call the right skill capability for you.

What kinds of scenarios is this skill good for?

It is suitable for product promo videos, social clips, brand visuals, talking-head explainers, product walkthroughs, voiceovers, and any content workflow where you want outputs and assets managed together inside Topview.

How do I install it into my agent?

Send this prompt to your agent: "Install Topview Skill for me: https://github.com/topviewai/skill.git". Your agent will handle the installation automatically. After that, you can start describing what you want to create.

Topview Skill for OpenClaw

Plug Topview Skill into your AI assistant and unlock video generation, image creation and editing, talking avatars, and voice capabilities in one unified toolkit.

Copy to your agent to installInstall Topview Skill for me: https://github.com/topviewai/skill.git

Quick Start

VideoDemo

ImageDemo

AudioDemo

Install Topview Skill for me:https://github.com/topviewai/skill.git

Installing skill...

GitHub

ClawHub

~/skillsmp |

Install and use it through chat

From installing the Skill and logging into Topview to uploading assets and calling models, everything can be completed step by step inside the conversation.

Install Topview Skill for me: https://github.com/topviewai/skill.git

Installing Topview Skill...

Reading the repository, checking dependencies, and registering callable modules.

Installation complete. Topview Skill is now connected to your agent.

Copy the link below into your browser to sign in. After signing in, the following capabilities will be unlocked.

https://topview.ai/login?QhTnLpVxRkMzBaYsWuCeDfGjNiOpSaReTxUz

Video generation

Generate text-to-video, image-to-video, and marketing clips automatically.

Image generation & editing

Create product images, posters, and retouch marketing assets.

Talking avatar

Generate talking avatars and presenter-style content.

Voice & TTS

Support dubbing, narration, and multilingual voice output.

Logged in

Sign-in successful. Capabilities unlocked.

You can now upload assets and use Topview Skill to generate videos, images, talking avatars, and voice content.

Create a product intro video of the person holding the product in image 2. Key selling points: designed for men's facial cleansing, rich foam, easy to rinse, deeply removes oil and impurities, and leaves skin fresh without tightness. Duration 15s, vertical 9:16.

Analyzing the task and matching generation parameters...

Identifying the product type, refining selling points, and choosing the best model and output spec.

Generation complete. Preview returned.

Connect Topview Skill to
the agents you already use

Connect top video and image models to your agent

Video models

Seedance 2.0 Style

Sora 2

Kling 3

Veo 3.1

wan2.7

Vidu Q3

Image models

nanobanana2

nanobanana pro

Seedream 5.0

GPT Image 1.5

Imagen 4

Add the following Topview skills to your AI assistant

AI video generator skill

Text to video

Describe the idea and get a video directly

Image to video

Animate product images, posters, and covers

Reference-based styling

Generate new videos from image, video, or audio references

Built-in asset management

Generated results can be managed and edited in Topview

AI image generator skill

Text to image

Generate visual assets quickly from a description

AI image editing

Change backgrounds, scenes, and details more easily

Generate multiple versions

Create multiple visual directions from one idea

Multiple image models

Switch across 10+ models based on the result you want

AI avatar skill

Start with one photo

Create a presenter-style video without filming

Automatic talking videos

Good for product intros, teaching, and marketing explainers

Subtitle style options

Choose subtitle styles that fit the content when needed

Better for longer explanations

Supports segments up to 120 seconds for continuous delivery

AI voiceovers skill

Text to speech

Turn scripts into natural-sounding speech quickly

Search available voices

Pick a more suitable voice based on your preference

Clone a custom voice

Create your own voice from an audio sample

Useful for video narration

Use it directly for videos, avatars, and spoken content

Claude Skill protocol

Built on the Claude Skill protocol

This skill package follows the Claude Skill protocol structure, so agents can install, read, and execute it in a predictable way. It is a workflow package rather than an executable installer, which means there is no malware or virus risk in normal use.

View VirusTotal virus scan report

How to use it

Install Topview Skill for me: https://github.com/topviewai/skill.git

Step 1: Copy the install command and send it to your agent

Install Topview Skill into your agent first so it can call the relevant capabilities.

🦞

Step 2: Send your creation request to your agent

Send prompts, images, product photos, portraits, or audio-related requests directly to your agent.

🦞

Step 3: Get the result

Your agent will automatically call the right Topview capability to generate video, image, avatar, or audio results for you.

Frequently asked questions

Topview Skill is a skill toolkit that can be installed into OpenClaw or another compatible agent. After installation, you can use natural language to ask the agent to generate videos, images, talking avatars, and voice content.

Topview Skill for OpenClaw

Plug Topview Skill into your AI assistant and unlock video generation, image creation and editing, talking avatars, and voice capabilities in one unified toolkit.

Copy to your agent to installInstall Topview Skill for me: https://github.com/topviewai/skill.git

Quick Start

VideoDemo

ImageDemo

AudioDemo

Install Topview Skill for me:https://github.com/topviewai/skill.git

Installing skill...

Frequently asked questions

Topview Skill for OpenClaw

Install and use it through chat

Connect Topview Skill tothe agents you already use

Connect top video and image models to your agent

Add the following Topview skills to your AI assistant

AI video generator skill

AI image generator skill

AI avatar skill

AI voiceovers skill

Built on the Claude Skill protocol

How to use it

Step 1: Copy the install command and send it to your agent

Step 2: Send your creation request to your agent

Step 3: Get the result

Frequently asked questions

What is a skill?

What is Topview Skill?

What can I create after installation?

What materials do I need?

Can I pass local images, audio, and video files directly to my agent?

Where do I view the generated results?

Does it include talking avatars and voice capabilities too?

Can I control the style of images and videos?

Do I need to understand scripts and APIs myself?

What kinds of scenarios is this skill good for?

How do I install it into my agent?

Topview Skill for OpenClaw

Install and use it through chat

Connect Topview Skill tothe agents you already use

Connect top video and image models to your agent

Add the following Topview skills to your AI assistant

AI video generator skill

AI image generator skill

AI avatar skill

AI voiceovers skill

Built on the Claude Skill protocol

How to use it

Step 1: Copy the install command and send it to your agent

Step 2: Send your creation request to your agent

Step 3: Get the result

Frequently asked questions

What is a skill?

What is Topview Skill?

What can I create after installation?

What materials do I need?

Can I pass local images, audio, and video files directly to my agent?

Where do I view the generated results?

Does it include talking avatars and voice capabilities too?

Can I control the style of images and videos?

Do I need to understand scripts and APIs myself?

What kinds of scenarios is this skill good for?

How do I install it into my agent?

Connect Topview Skill to
the agents you already use

Connect Topview Skill to
the agents you already use