Make continuous-take product launch films with the onetake agent skill
The onetake repository is a Claude Agent Skill that lets a coding agent produce product launch films, teasers and feature demos as one continuous camera take. An automated oracle checks that each beat visibly grows out of the previous one before a person reviews the film.
The problem
Motion videos made by AI or by template tools tend to feel like a slideshow: title card, fade, UI shot, fade, feature card. Each shot may look fine, but nothing connects one beat to the next, so scenes simply replace each other.
How they did it
- Clone the repository into the skills folder of your agent (~/.claude/skills/onetake for Claude Code, ~/.agents/skills/onetake for Codex and similar agents).
- Install the requirements: python3 with playwright (chromium), numpy, scipy, Pillow, matplotlib, plus ffmpeg and node. Reference analysis needs opencv-python and narration needs faster-whisper and Kokoro TTS.
- Ask the agent for a film, for example a launch video for your app or a feature demo rebuilt from screenshots.
- The agent deconstructs a reference, proposes three one-sentence concepts, and writes a beat sheet where every boundary names what survives it.
- It composes one HTML file on the move library, renders with motion blur, and scores sound from the film's events.
- The oracle (probe.py and verify) scores continuity before a human watches the result.
From the official docs
# Claude Code
git clone https://github.com/feitangyuan/onetake.git ~/.claude/skills/onetake
# Codex / other agents that read skills
git clone https://github.com/feitangyuan/onetake.git ~/.agents/skills/onetakeResults
- The README lists ten example films across concept ads, launch films, app promos and feature demos, each with a finished film and a breakdown document. Their source code is not included.
- As reported by the repository, an earlier launch film scored 0.00 on the continuity (carry score) check and was rejected, a later version scored 0.75 and was accepted, and the onetake launch film scored 0.83.
- As reported by the repository, drafts render at 1080p30 and finals at 4K60, and seeking to any time gives the same frame.
- The skill is licensed PolyForm Noncommercial 1.0.0, so commercial use needs the paid onetake Pro.
As reported by the source (onetake GitHub repository README); AgentGid did not measure these figures.
Best for a developer or small product team that is comfortable with Python, ffmpeg, Node and Playwright, since the setup is advanced and a human still reviews every film. Watch the license: PolyForm Noncommercial means commercial launch videos need the paid onetake Pro, and the carry scores are repository-reported. If you lack a paid agent, OpenCode (Free + $10/mo) is a cheaper terminal option.
The agents used here
Anthropic's agentic coding tool that reads a codebase, edits files and runs commands from the terminal, with VS Code and JetBrains integrations plus …
- Price
- $20/mo
- Gid Score
- 81 #2 in Terminal
OpenAI's coding agent, offered as an open-source terminal CLI, an IDE extension, a desktop app and a cloud agent that works on repositories. Users si…
- Price
- Free + $8/mo
- Gid Score
- 84 #1 in Terminal
Compare: Claude Code vs OpenAI Codex
Similar use cases
Produce AI short dramas from a novel with shuohao-skills in Claude Code
An individual developer published an open-source set of agent skills that take a novel through to shoot-ready AI short-drama material: outline, character bible, art bible, screenp…
As reported by the repository author, each pipeline skill has script-checked quality gates: 14 for the outline, 10 for the art bible, 10 for the scre…
Mod almost any PC game with Claude Code and the universal-modder plugin
An open-source GitHub project packages skills, a command-line tool, a shared knowledge base and the fal MCP server so AI coding agents such as Claude Code can mod PC games the use…
The repository ships three worked examples: a Terraria tModLoader weapon and boss pack with sprites made through fal, an Age of Empires II DE civiliz…
Run a YouTube channel with eleven Claude skills for scripts, edits and retention
An open-source MIT pack of eleven Claude skills helps a YouTube creator draft scripts, package titles and thumbnails, cut edits, read retention data and plan a week of content. It…
The pack bundles eleven skills and six dependency-free Python tools, including a hook scorer, title and thumbnail linter, dead-air detector, chapter …
Guides
Claude Code Deploys: 6 Open-Source Repos for a Containment System, Checked
A viral post says GitHub Actions, Argo CD, Argo Rollouts, Prometheus, Sentry and OpenTelemetry turn Claude Code deploys into a containment system. We checked each: role, license, what needs Kubernetes, and what Claude Code's own permissions add.
How to Cut Token Usage in Claude Code and Cursor (2026)
Practical ways to spend fewer tokens with Claude Code and Cursor: measure first, keep context small, match the model to the task, filter what the agent reads, and the open-source tools that help.
Sonnet Builds, Opus Reviews, Haiku Reads: Does the Claude Code Advisor Save Money?
A viral post says running Sonnet, Haiku and Opus together in Claude Code gives better code for fewer tokens. We checked it against Anthropic's docs and prices: when the advisor pays off, when it costs more, and why a ready project kit matters more than the model mix.
JEV for Claude Code: A Second Opinion on Every Command, Checked
A viral post says jev-axi screens every command your Claude Code agent runs for a fraction of a cent. We read the repo, TypeSafe's docs and privacy policy: what runs locally, what is sent, how it fails, and how it compares with auto mode.