Individual skill
screen-demo
Turn a screen recording into a polished product demo or tutorial: the view follows the action, dead time is gone, every step is easy to see, and the product looks as good as it is. Use when the person gives a screen recording (or a product to capture) and asks for a demo, walkthrough, tutorial, feature video or how-to (录屏演示, 产品演示, 教程, 操作视频, 功能介绍).
packages/openfilm/skills/screen-demo/SKILL.md
Source commit 623cec4297aa6c134d1426c796e79f5845724433
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Instructions only
- Last checked
- Nov 9, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 5,501
- Repository last updated
- Nov 8, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai-video Repository topic
- claude-code Repository topic
- codex Repository topic
- coding-agents Repository topic
- html Repository topic
- motion-graphics Repository topic
- video-agent Repository topic
- video-editor Repository topic
- education Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 2,206 bytescover.jpgasset · 93,261 bytesopenfilm.jsonasset · 2,800 bytes
Read excerpt
# Screen demo
Make the demo that shows this product at its best and is effortless to follow: the viewer always knows where to look,
sees each step land, never waits, and could do the same in the product today.
## What has to be true
- **The real product.** Its own screens, actions and results, from the person's recording or captured from the live
product; never a redrawn interface or a result that did not happen. Where it must be simpler, crop and zoom into the
real thing.
- **Clear where to look**, at the size it will be watched: the action, its text and its result readable on that
screen, a phone too when the demo is vertical.
- **Nothing private in any frame**: keys, tokens, passwords, emails, names, customer data, notifications, other tabs
and bookmarks are hidden, or that part is recorded again.