website-demo-video

website-demo-video is a skill for Claude Code from ABO3SKRALMASAOODI/valmera-mcp. It costs 62 tokens per session (576 once invoked), scanned A, original, MIT.

A workflow for recording a product or website demonstration from a public URL and editing it into a promotional video. It can show browser actions such as clicking, scrolling, hovering, and typing into non-sensitive fields, then add product-video presentation effects.

In plain words
What is it for?
Use it to record a SaaS walkthrough, landing-page promo, launch video, or screen capture in landscape or portrait format, with zooms, cursor focus, captions, or music.
Why use it?
A useful demo needs a short story instead of a recording that clicks through everything. Planning the key flow helps viewers understand the product and the action they should take next.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the valmera plugin — 3 skills, 2 MCP servers shipped together

Good fit Use it to record a SaaS walkthrough, landing-page promo, launch video, or screen capture in landscape or portrait format, with zooms, cursor focus, captions, or music.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/abo3skralmasaoodi/valmera-mcp/website-demo-video
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ABO3SKRALMASAOODI/valmera-mcp --skill website-demo-video
Clone the repo
git clone --depth 1 https://github.com/ABO3SKRALMASAOODI/valmera-mcp

Made for: Claude Code.

Or install valmera, the plugin that ships this one along with the rest of its 3 skills, 2 MCP servers.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for website-demo-video

README.md
[![agentmods](https://agentmods.dev/badge/skills/abo3skralmasaoodi/valmera-mcp/website-demo-video/github.svg)](https://agentmods.dev/skills/abo3skralmasaoodi/valmera-mcp/website-demo-video)
Your own site
<a href="https://agentmods.dev/skills/abo3skralmasaoodi/valmera-mcp/website-demo-video"><img src="https://agentmods.dev/badge/skills/abo3skralmasaoodi/valmera-mcp/website-demo-video/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for website-demo-video

Your own site · 80×15
<a href="https://agentmods.dev/skills/abo3skralmasaoodi/valmera-mcp/website-demo-video"><img src="https://agentmods.dev/badge/skills/abo3skralmasaoodi/valmera-mcp/website-demo-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 576 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00062 $0.00576
Opus 5.5 $0.00025 $0.00230
Sonnet 5.5 $0.00012 $0.00115
Haiku 4.5 $0.00006 $0.00058

Measured 14d ago against content hash 6b2f884e4fa4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

website-demo-video scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/website-demo-video/SKILL.md · 24 lines

How it starts

The opening of the file, as written. The whole thing — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Make a website or product demo video with Valmera

Valmera can drive a real browser through a public website, recording a visible cursor that clicks, scrolls and types. It can then cut the recording like a product video, with zooms that follow each click.

Workflow

  1. Create a project with create_project, or open the user's project.
  2. Plan a short story. Write 4–10 steps that show one clear flow, such as the landing page, then the key feature, then the call to action. A demo that clicks everything shows nothing. Ask the user for the URL and the one thing viewers must understand.
  3. Record. Call record_website_demo with the URL, an orientation (landscape for websites, portrait for social) and the steps. Steps look like {do:'click', text:'Get started'}, {do:'scroll', to:'Pricing'}, {do:'hover', text:'Plans'}, {do:'type', selector:'input[type=email]', text:'[email protected]'} and {do:'wait', seconds:1.5}. It records the public site as a visitor sees it, and never types into password or payment fields. For a simple scrolling capture, use record_website.
  4. Cut it like a product video. Call showcase_demo with the recorded clip. It places the clip and adds zooms that travel between the clicks. For a recording the user uploaded, pass click_times, and use enhance_cursor and add_zoom_path when the pointer is hard to follow.
  5. Add the story layer. Add a title card (add_title_card), short on-screen text for each step (add_text), music (add_music), and a closing call to action.
  6. Render and check. Call render_preview, then wait_for_job, then look_at with rendered=true at each click, so you can confirm the zooms land on the right element.
  7. Export when asked. Call export_final, then wait_for_job, then download_url with kind="final".

Limits

  • Only public pages can be recorded. Desktop apps and logged-in areas can't, so ask the user to upload their own screen recording for those.
  • Editing requires a Valmera subscription (https://valmera.io/subscribe).

Read the full file on GitHub · 24 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 14d ago First seen · 24 lines · 62 tokens per session scan A 6b2f884e4fa4

Subscribe to this mod's changes

website-demo-video is a skill published in the GitHub repository ABO3SKRALMASAOODI/valmera-mcp (0 stars, last pushed 13d ago), licensed MIT. It adds 62 tokens to every session and 576 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-06.