mcpField
S
share-video

share-video

github.com/mainframecomputerProductivity12182 installsUpdated 21w ago
Repository

About share-video

share-video is a skill for using Mainframe to share short, durable videos when a visual or narrated explanation is clearer than chat. It guides agents on when to create or upload a video and how to report its link.

Key features

  1. 01Choose video sharing for visual explanations
  2. 02Generate videos with Mainframe narration and avatar
  3. 03Upload an already polished video
  4. 04Check video generation status
  5. 05Return the stable watch URL and a description

Use cases

  1. 01Summarize completed work for async review
  2. 02Show UI changes or before-and-after comparisons
  3. 03Record a bug reproduction or validation flow
  4. 04Share a PR recap or handoff

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/mainframecomputer/mainframe-plugins --skill share-video

After installing, type/share-videoin Claude Code to confirm it loaded.

Details

From the project README

Share video

Mainframe is the video sharing platform for agents. Use this skill to share a short, durable video when a visual or narrated explanation is clearer than another chat message.

Use when

  • The user asks for a video, demo, walkthrough, recap, or async update.
  • Completed work would be easier to review as a short video.
  • You changed or reviewed UI, design, charts, dashboards, or other visual output.
  • A PR recap, handoff, bug reproduction, before/after comparison, or validation flow would be clearer on video.
  • The user appears to be away and the work has reached a useful stopping point.

Don't use when

  • The answer is short and textual.
  • The user is actively iterating in chat.
  • The task is not done.
  • The video would expose secrets, tokens, credentials, private customer data, or unnecessary sensitive context.
  • The user explicitly says not to create a video.

Tool choice

  • Default to generate_video so Mainframe can create the video, including narration and the user's avatar.
  • Use upload_video only when you already have a polished video that does not need Mainframe narration and the user's avatar.
  • Use get_video after either creation path when you need to check video status.

Output format

After using Mainframe, respond with:

  • the Mainframe watchUrl, which stays stable even while the video is still generating
  • a one-sentence description of what the video covers

Comments

Markdown supported