Who it is forA video editor or reviewer who has a finished poem video and wants a repeatable check before posting it.
The problemA browser preview can look fine while the final encoded MP4 has black frames, broken transitions, or a wrong audio track.
The outcomeA QA folder with ffprobe.json, blackdetect.log, silencedetect.log, volumedetect.log, frames at 10, 25, 50, 75, and 90 percent plus the last frame, and a contact sheet of the encoded video.
What you need first
- An agent that supports SKILL.md, such as Codex or Claude Code
- Codex built-in ImageGen for the still images
- Docker with the gemini-flow-suite container from the HBG Gemini Flow Suite runtime, with the one-time authorization done by you
- The classical poem text and the scene plan you want to use
Steps
- Clone the repo with
git clone https://github.com/Mr-funny/hbg-classical-poem-silk-video.git. - Run
skill/classical-poem-silk-video/scripts/final_media_qa.sh final.mp4 qa/finalon the finished MP4. (inferred, check the README) - Open the contact sheet and the logs in qa/final and note any frame with a problem.
- If you want to check specific moments, write a tab-separated file with timestamps and labels, then run
skill/classical-poem-silk-video/scripts/final_media_qa.sh final.mp4 qa/final qa-timestamps.tsv. (inferred, check the README)
Prompt for your agent
Use the final_media_qa.sh script from https://github.com/Mr-funny/hbg-classical-poem-silk-video on <path to final.mp4> and write the output to qa/final. Report any black detection, silence detection, or spec mismatch in the logs and the ffprobe.json. Verify that the frames at 10, 25, 50, 75, 90 percent and the last frame are all present in the output folder.
Caveat. The QA script checks the encoded file only, so it does not judge whether the painting or calligraphy looks right, which still needs a human look.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page