jev-remix-cutter
Codex skill and Python CLI for local video remixes with shot and beat detection, Jev clip judgments and an originality report.
Overview
jev-remix-cutter is a standalone agent skill and Python CLI, documented in Chinese, for building reviewable local video remixes. It detects shots and beats, sets slots for original narration, asks Jev (pinned to jev-1.13.0) for judgments on clips, arranges them under constraints, and produces an originality and footage-licence report. Text goes to TypeSafe only after an explicit --allow-text-upload, and an optional image provider requires separate upload permission.
The README is candid about status for version 0.1.0: one licensed long-footage task ran real Jev text calls, but some responses failed the probability-distribution contract check and the slot-fit gate was not passed, so full automatic casting has not been validated; the image provider has not been called live, and advanced compositing, anonymisation and blind tests are incomplete. Licences for footage, music and narration must be declared, and unknown licences require confirmation before export. It registers as a Codex skill via symlink and requires FFmpeg.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Score | slot_fit: how well does this clip fit this slot? | — |
| Choice | Which candidate clip should fill this slot?(inferred) | — |
How it works
- Initialise a run with format and target duration
- Detect shots and beats; declare footage and music licences
- Ask Jev to judge clips for each slot (with explicit upload consent)
- Assemble under constraints and render
- Produce originality and licence reports
Strengths
- Explicit consent before uploading text or images
- Licence tracking built into the pipeline
- Candid status documentation
Caveats
- Automatic casting not yet validated with real Jev calls
- Advanced features incomplete
- Requires FFmpeg, Python 3.11+ and a TypeSafe key
Getting started
Clone into ~/.local/share/jev-skills, create a venv, pip install -e "${SKILL}[core]", run remix.py doctor --json, then install_skill.py to register with Codex.At a glance
- Type
- Agent skill
- Status
- prototype
- Language
- Python
- Runtime
- CLI and Codex skill
- Has code
- yes
Use cases and integrations
How curated lists describe it
Agent Skill and Python CLI for local video remixing, Jev judgments, and originality reports.
hellogumbo/awesome-jevCodex skill and Python CLI for local video remixes: shot and beat detection, Jev judgements on clips pinned to `jev-1.13.0`, and an originality and footage-licence report. Text goes to TypeSafe only after an explicit `--allow-text-upload`. Chinese docs.
MrJev/awesome-jev
Frequently asked questions
What does Jev decide?
How well clips fit remix slots, as typed judgments.
Is data uploaded automatically?
No. Text and images are sent only with explicit flags.
Is it production-ready?
No. The README states key paths are not yet validated end to end.
Related projects
Video summarizer that ties every line to its second; Jev checks each summary sentence against what was said, with numbers checked in code.
ProjectbetaPython- Building with Jev★ 155
Agent skill for writing and improving programs that call Jev: question design, state structure, thresholds and diagnosing wrong answers.
Agent skillproduction Unofficial hosted or local Jev MCP server giving agents a quick second opinion: it picks yes/no, scale or choice and returns probabilities.
MCP serverbetaTypeScriptCLI, MCP server and Claude Code plugin for closed-form yes/no, choice, score and rank decisions via Jev, OpenAI Decisions or Claude.
MCP serverbetaTypeScriptDecision plugin for agent harnesses where Jev recommends tools, skills or owners and scores output, for DeepSeek Harness and iPolloWork.
Agent skillbetaTypeScriptPortable Agent Skill teaching coding agents to use Jev as a bounded judgment layer, plus an optional MCP bridge.
MCP serverbetaTypeScript