agentleFS
Sign inStart free
ucsandmanucsandman/claude-skills/product-demo/SKILL.md

product-demo

Skill5 starsChanged 2 months agoMITView on GitHub

Use when the user wants a product demo video / screen recording with zooms and cursor / dashboard walkthrough clip for any product (e.g. "/product-demo", "record a demo of the app", "Screen-Studio style demo").

12 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run the capture with --project <product>.

    line 25
  2. Distinctive:

    Read them, set focus {x,y,w,h} centers/sizes in the capture script, re-capture (~20s).

    line 29

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Product Demo

REQUIRED BACKGROUND: marketing-studio skill; also read C:/Projects/animations/docs/playbook/capture.md and C:/Projects/animations/docs/playbook/remotion.md. Work in C:/Projects/animations.

Produces <product>/marketing/assets/<brand>/demo.mp4: real app footage with a timestamp-driven cursor, subject-safe camera framing, and concise captions.

Recipe

  1. Toolchain + brand check per marketing-studio. The product's app must be RUNNING (ask the user to start it; never start their stack yourself).
  2. Capture script: feeders/capture/record-<brand>-demo.mjs. For a new product copy record-noban-demo.mjs: viewport wide enough for the app, deviceScaleFactor: 2, proven ready-locators per view, a step caption per view. Read C:/Projects/animations/docs/playbook/capture.md FIRST — especially: camera focus rects are MEASURED from raw footage frames, never derived from click points, and must end before any app-side clipped edge.
  3. Run the capture with --project <product>; verify capture OK and the product-owned props/public files it writes. Do not stage product footage in the engine.
  4. Measure/tune focus rects: extract raw frames (npx remotion ffmpeg -ss <t> -i <product>/marketing/assets/<brand>/public/<brand>/demo.webm -frames:v 1 f.png), Read them, set focus {x,y,w,h} centers/sizes in the capture script, re-capture (~20s).
  5. Render one proof per view with --public-dir=<product>/marketing/assets/<brand>/public; check that the product action is legible at delivery size, camera framing is safe, and pointer phases match capture.
  6. Render into the product workspace and deliver per marketing-studio. A full desktop recording is raw material, not automatically an authored edit.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free