Skip to main content
skill CX Codex

ketchup-video — Claude Code skill: video recap instead of text

ketchup-video — a skill for Claude Code, Codex, Cursor and other platforms that shows what happened in your project as a short subtitled video with slides instead of a text summary.

MIT 5,300 installs ★ 4,730 updated 2026-10-24

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add backnotprop/pstack --skill ketchup-video -a claude-code
Open on GitHub

What ketchup-video does

Works like the built-in /ketchup command but renders a landscape video instead of text and visuals. The agent gathers slides from screenshots, recordings, diffs and real results of the work. Each slide makes one point: how a system is laid out, a PR stack with each PR's state, a before-and-after fix, or options side by side. Text stays minimal: a label on the thing it names, a subtitle in a strip below the video.

The video draws only from facts — no invented numbers, no screenshots you never took. If rendering fails, the agent says so in one line and returns only the action items. Video rendering is the one exception to the read-only rule; writes outside the repo are allowed for this. Subtitles scale to slide length — more words mean longer hold time, at least one second per three words.

What it helps with

  • turn a long project update into a single watchable video
  • show a PR stack with the state of each pull request visually
  • compare solution options side by side on one slide
  • understand which tasks are done and which are still waiting

Example prompts for the agent

  • Run /ketchup-video to see a video of what happened since your last message
  • After a few attempts, use /ketchup-video to render a final video report
  • Paste screenshots and diffs in chat, then run /ketchup-video for a video summary

How to install ketchup-video

1Skills CLI (Vercel)

npx skills add backnotprop/pstack --skill ketchup-video -a claude-code

2Manually: put the files in place

~/.claude/skills/ketchup-video/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/ketchup-video/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about ketchup-video

How do I install ketchup-video in Claude Code?

Run npx skills add backnotprop/pstack --skill ketchup-video -a claude-code, then open ~/.claude/skills/ketchup-video/SKILL.md in your editor.

What does ketchup-video do?

It builds a video from screenshots, diffs and work output to show what happened, replacing a text recap. Each slide shows one change, all slides connect visually, and text is minimal.

Does ketchup-video work on platforms other than Claude Code?

Yes, the skill runs on Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode. Installation command varies by platform.

Source text

SKILL.md · MIT
---
name: ketchup-video
description: "Catch the user up like /ketchup, with a short subtitled video of slides for what happened and the waiting calls as text under it. Use for /ketchup-video."
disable-model-invocation: true
---

# Ketchup video

Follow [`/ketchup`](../ketchup/SKILL.md), but show what happened in a short subtitled video instead of its summary and visuals. Its window starts at the last message the user wrote before `/ketchup-video`, not before any earlier `/ketchup`. Writing and rendering the video, outside the repo, is the one exception to its read-only rule. The reply is ketchup's opening sentence, the embedded video, one line naming any work left that you can do yourself, and the action items. When the video shows a call's options, call each option by the name the video gives it. If the render fails, say so in one line and give only the calls.

## Slides

Use the screenshots, recordings, diffs, and data the work produced, not the chat's prose about them. Before you draw, write the one sentence the user should leave with and one line per slide. Drop each slide that does not change what the user knows. Use at most 10 slides, and fewer is better. Neither note goes in the reply.

Each slide makes one point. Build the slides on one picture and change it from slide to slide, rather than cut to an unrelated one. A color or shape means the same thing on every slide. Show the work in pictures, such as how a system works, a PR stack with each PR's state, a before and after of a fix, or options side by side. Point at what changed with arrows, highlights, and motion. A slide is never a bullet list, a status list, a table, or boxes with nothing connecting them.

Keep text to the minimum. Put each label on the thing it names, in plain words a person would say, not tags like "Tests: pass". Never caption what a picture shows, and never give a fact twice, across slides or in the text under them.

Show what came of each thing the user asked for, and whether it is done, still running, failed, or not checked. Never show something done that still waits on the user. Show any bug found and fixed on the way. If a visible change has no screenshot, say so on its slide and name what changed on screen. Draw only from facts you have. Never invent a number, and never draw a screen you did not capture.

## Subtitles

Give each slide one short subtitle line, about ten words, that says its point the way you would tell the user, from only what that slide shows. Say what the picture means rather than read out its labels. Put the subtitle in a strip below the slide, the same height on every slide and empty except for the subtitle, so it never covers the slide. Set it small, but readable when the video plays at chat size.

## Render

Render one silent landscape video, such as an mp4, with motion between slides. Every frame is the slide itself, edge to edge, above its subtitle strip. Make the frames from the slides, never by recording a screen, and burn each subtitle into its slide's frames so it stays on screen for the slide's whole hold. The hold is the time a slide is fully on screen, not counting the motion into or out of it. Hold each slide long enough to read the words it adds, at least one second for each three words. A slide adds its subtitle and each word that was not on the slide before it, including a label it changes. The first slide adds all its words. Words inside a screenshot do not count.

Before you embed the video, check the rendered file. Look at one frame from each slide at chat size, and check that its subtitle is readable and covers nothing. Measure each hold by matching the file's frames to the slide, not with a still-frame detector, which counts the faint ends of a fade as still. Count the words each slide adds against its measured hold. Fix any slide you cannot read in that time, render again, and check again.

© backnotprop · MIT · backnotprop/pstack

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set46

The whole set →
principle-explain-the-number principle-explain-the-number is a Claude Code skill that checks what a measured number actually captures and what limits it. It covers speedups, regressions, throughput, latency, and eval results. CX Codex +1 9,200installs benchmark-checklist benchmark-checklist — a skill that makes the agent answer seven questions with evidence from a run before it reports a speedup or a regression. CX Codex +1 9,100installs poteto-help poteto-help is a Claude Code skill that guides users through the pstack framework, playbooks, and commands. It answers workflow questions and formats prompts without spending run tokens. CX Codex +1 8,800installs ketchup ketchup summarizes chat updates since your last message in plain words and visual diagrams, highlighting decisions that need your approval. CX Codex +1 7,900installs sharpen sharpen is a Claude Code skill that deepens a task and rewrites the prompt without expanding its scope. Runs when invoking /sharpen. CX Codex +1 7,300installs create-formal-verification-skill The create-formal-verification-skill skill selects code for formal verification and creates a project-local guide for checking it again after changes. Use it when tests leave important invariants or event orderings uncovered. CX Codex +1 6,200installs maintain-formal-verification-skill maintain-formal-verification-skill is a Claude Code skill that updates formal checks to match code changes, reruns them, and classifies failures after merges or refactors. CX Codex +1 6,100installs statechart This skill verifies TLA+ models of stateful systems (purchase flows, protocols, services) with TLC and draws them as Mermaid statecharts. The report traces the shortest path to each state that breaks a rule. CX Codex +1 5,500installs

Project sponsors

Companies that keep this analytics open