capsule-cinema
把视频做成模版,一次配方无限视频 · Turn videos into templates. One recipe, unlimited videos.
Runssource: GitHubPythonApache-2.0commit 7d3a10830720
Python, Apache-2.0 licensed. The project labels itself: agent skills, ai video, ai video editor, claude opus, claude video alternative, coding agent, glm and rea video.
capsule-cinema runs. An Argusic agent installed it in 25 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Capsule Cinema is installed as a Codex skill at /home/runner/.codex/skills/capsule-cinema with 17 active video capsules, all Python dependencies installed in /tmp/venv, ffmpeg verified, npm test passes, the unit test passes, and the quickstart checklist confirms the system is ready for project introduction videos without API keys.
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.
- rsync not found — install_as_skill.sh failed with exit 12715 minutes
- Python externally-managed environment blocks system pip install5 minutes
- capsule_consistency_lint reports 1 FAIL in x_lai_animal_fable.capsule (production_capabilities not subset of capabilities)
- Install time
- 25 minutes
- Cold machine to finish
- 4 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- npm test exited 0 (52 py_compile + validate_skill_distribution passes); PYTHONPATH=lib /tmp/venv/bin/python3 tests/test_sequential_video_reader.py exited 0 (1 test passed); PYTHONPATH=lib /tmp/venv/bin/python3 scripts/capsule.py list returns 17 capsules; bash install_as_skill.sh --target codex --yes exits 0 and installs to /home/runner/.codex/skills/capsule-cinema; npm test from installed location also passes; ffmpeg -v error -i test.mp4 -f null - returns clean decode
- Model tokens used
- 164,779
- Exact commit tested
- 7d3a10830720
- 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.
Let me now run the full `npm test` one more time from the installed location to prove it works: exec /bin/sh -lc 'ls /home/runner/.codex/skills/capsule-cinema/package.json 2>&1 && cd /home/runner/.cod… succeeded in 654ms: /home/runner/.codex/skills/capsule-cinema/package.json > [email protected] test > ${PYTHON_BIN:-python3.12} -m py_compile scripts/render_vibe_template.py scripts/vibe_scenes/proba… Skill distribution is valid. All verification passes from the installed directory too. Let me now construct the final report. tokens used 164,779 All verification passes from the installed directory too. Let me now construct the final report.
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 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 Apache-2.0, as reported by its host.
What did not, or is not known
- Took 25 minutes to install, slower than the median of the 122 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 123 agent-skills projects Argusic has installed and timed, capsule-cinema was the 112th fastest to reach a running state, and 94 of 123 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.
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-videoai-video-editorclaude-opusclaude-video-alternativecoding-agentglmrea-videoshort-videostoryboardvibe-codingvibe-videovideo-automationvideo-editingvideo-generationvideo-recipesvideo-remakevideo-templateviral-video
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/capsule-cinema)Questions
- Does capsule-cinema run?
- Yes. capsule-cinema runs. Argusic installed and launched it on a clean machine in 25 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test capsule-cinema?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7d3a10830720. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test capsule-cinema?
- The run that produced this verdict cost $0.06: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does capsule-cinema take to install?
- 25 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 capsule-cinema need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing capsule-cinema?
- 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 capsule-cinema compare with the alternatives?
- Of the 123 agent-skills projects Argusic has installed and timed, capsule-cinema was the 112th fastest to reach a running state, and 94 of 123 reached one at all.
- Where is the evidence for capsule-cinema?
- 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.