cutcli-cookbook
Cookbook, JSON templates, AI prompts and docs for cutcli, the CapCut / Jianying (剪映) draft CLI. Generate editable video drafts from code, Cursor, Claude Code or any MCP agent.
Runssource: GitHubhomepageJavaScriptMITcommit d95632886cd3
JavaScript, MIT licensed. The project labels itself: ai agent, ai video, capcut, capcut draft, claude code, cli, cookbook and cursor.
cutcli-cookbook runs. An Argusic agent installed it in 0.5 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
cutcli 1.3.13 installed, cookbook lint suite passes 4/4 checks, VitePress docs build generates the full site, and examples 01 and 03 produce working CapCut drafts with captions. Examples 02, 04, 05 fail only because their CDN-hosted demo assets return 404.
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.
- example 02-image-slideshow-bgm: CDN image asset https://cutcli.com/assets/demo/scene-01.jpg returns HTTP 404
- example 04-easy-by-audio: CDN audio asset https://cutcli.com/assets/demo/bgm-light.mp3 returns HTTP 404
- example 05-keyframe-zoom-in: CDN image asset https://cutcli.com/assets/demo/scene-02.jpg returns HTTP 404
- Install time
- under a minute
- Cold machine to finish
- 2 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- npm run lint exited 0 (8 examples, commands, links, i18n all OK), npm run docs:build completed (VitePress), cutcli --version => 1.3.13, bash examples/01-hello-caption/run.sh created draft 'hello-caption' with duration=5000000µs, bash examples/03-tiktok-keyword-highlight/run.sh created draft with 3 caption segments, cutcli draft list shows 5 real drafts
- Model tokens used
- 21,788
- Exact commit tested
- d95632886cd3
- 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.
21,788 Now I have all the data. Let me collate the final report. **Summary of what happened:** 1. **`npm install`** — 133 packages added, clean 2. **`npm run lint`** — all 4 checks passed (8 examples validated, commands, links, i18n pairs) 3. **`npm run docs:build`** — VitePress built the full docs site (including llms-full.txt) 4. **cutcli installed** — v1.3.13 via `curl -s https://cutcli.com/cli | bash` 5. **Example 01 `hello-caption`** ✅ — 5-second draft with caption created, all CLI commands work 6. **Example 03 `tiktok-keyword-highlight`** ✅ — 6-second draft with 3 caption segments created 7. **Example 04 `easy-by-audio`** ⚠️ — draft created, but CDN audio download 404'd 8. **Examples 02 & 05** ❌ — failed because CDN demo images (`scene-01.jpg`, `scene-02.jpg`) return … All failures are from external CDN assets that the cutcli website hosts — the tool itself and all s…
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.
- Installed in 0.5 minutes, faster than the median of the 67 comparable projects Argusic has measured.
- Recovered from all 3 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
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 68 ai-agent projects Argusic has installed and timed, cutcli-cookbook was the 7th fastest to reach a running state, and 40 of 68 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 0.5 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)
ai-agentai-videocapcutcapcut-draftclaude-codeclicookbookcursorcutcliexamplesjianyingjianying-draftjsonmcpshortvideosubtitletemplatestiktokvideo-automationvideo-editing
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/cutcli-cookbook)Questions
- Does cutcli-cookbook run?
- Yes. cutcli-cookbook runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test cutcli-cookbook?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit d95632886cd3. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test cutcli-cookbook?
- The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does cutcli-cookbook take to install?
- 0.5 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 cutcli-cookbook need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing cutcli-cookbook?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does cutcli-cookbook compare with the alternatives?
- Of the 68 ai-agent projects Argusic has installed and timed, cutcli-cookbook was the 7th fastest to reach a running state, and 40 of 68 reached one at all.
- Where is the evidence for cutcli-cookbook?
- 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.