ai-promo-video-maker
一句话让 AI 帮你做产品宣传片！把产品名或网址告诉 Cursor、Claude Code、Codex 等 AI 编程工具，它会自己调研产品、画出多种风格样图让你挑选、截取 4K 真实页面、按音乐节拍卡点剪辑、生成 AI 旁白并逐句转写校验、自动审图，最后交付一支 4K 商业宣传视频和可在线播放的网页版。App、网站、SaaS、开源项目、课程、AI 模型都能做，你只需确认需求、试听配乐。不用学剪辑软件，也不用花钱找外包。基于 Remotion + ElevenLabs，可直接克隆使用，也能一键安装为 Agent Skill。
Runssource: GitHubPythonMITcommit 279ba5178c3c
Python, MIT licensed. The project labels itself: agent skills, ai agent, ai video, ai video generator, aigc, claude code, claude skills and codex.
ai-promo-video-maker runs. An Argusic agent installed it in 9 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Template project installs, fonts subset correctly, stills render, 1080p preview video renders cleanly, web player builds; lint passes; all doctor checks pass except optional ElevenLabs key.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- No CJK fonts on Linux container3 minutes
- @tailwindcss/oxide v4 has no x86_64-glibc binary (only musl), breaks Remotion bundling2 minutes
- Python deps not installed in system python (externally-managed-environment)1 minute
- Remotion concurrency set to 12 on 4-core container
- Missing public/audio/mix.wav blocks render
- Install time
- 9 minutes
- Cold machine to finish
- 10 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- npm run lint → exit 0; npm run render:preview → 1920×1080 h264, 12.05s, 360/360 frames; ffmpeg -v error -i out/preview.mp4 -f null - → no errors; npm run web:build → builds out/web; doctor.py → all essentials OK; check_video.py → video OK (loudness only fails on placeholder audio); node scripts/stills.mjs --scenes → all 6 scene stills rendered
- Model tokens used
- 124,341
- Exact commit tested
- 279ba5178c3c
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
exec /bin/sh -lc 'echo "--- All checks complete ---"' in /work/repo succeeded in 0ms: --- All checks complete --- Here is my verified result for the full mission. Install time was ~9 minutes. The `@tailwindcss/oxide` v4 binary only ships musl bindings, so it can… All essential checks pass: `doctor.py` reports all items OK, `npm run lint` exits 0, still frames r… tokens used 124,341 Here is my verified result for the full mission. Install time was ~9 minutes. The `@tailwindcss/oxide` v4 binary only ships musl bindings, so it can… All essential checks pass: `doctor.py` reports all items OK, `npm run lint` exits 0, still frames r…
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 5 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Took 9 minutes to install, slower than the median of the 77 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 78 agent-skills projects Argusic has installed and timed, ai-promo-video-maker was the 59th fastest to reach a running state, and 56 of 78 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 9 minutes after the clone.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
agent-skillsai-agentai-videoai-video-generatoraigcclaude-codeclaude-skillscodexcursorelevenlabsffmpegmarketingmotion-graphicsplaywrightproduct-videopromo-videoreactremotiontext-to-speechvideo-generation
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/ai-promo-video-maker)Questions
- Does ai-promo-video-maker run?
- Yes. ai-promo-video-maker runs. Argusic installed and launched it on a clean machine in 9 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test ai-promo-video-maker?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 279ba5178c3c. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test ai-promo-video-maker?
- The run that produced this verdict cost $0.19: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does ai-promo-video-maker take to install?
- 9 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does ai-promo-video-maker need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing ai-promo-video-maker?
- 5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does ai-promo-video-maker compare with the alternatives?
- Of the 78 agent-skills projects Argusic has installed and timed, ai-promo-video-maker was the 59th fastest to reach a running state, and 56 of 78 reached one at all.
- Where is the evidence for ai-promo-video-maker?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.