A DeepSeek Harness plugin that turns each video into a local folder workbench — topic, script, recording, subtitles, cover and publish status — without locking your content into a database.
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-08-23
License
MIT
01What can it help you accomplish?
Turn a content project into a local folder-backed creator workbench (topic, script, recording, subtitles, cover, publish status) inside DeepSeek Harness
One local folder per video with topic.md, script.md, mp4, srt, subtitled mp4, cover images and publish-package.json; workspace state in ~/.dsh-oil-creator/overlay.json
Creators and editors who run DeepSeek Harness (dsh) and want AI to help produce videos from a single local folder rather than a closed database
02How to install into DeepSeek Harness
Prerequisites
- Node.js 22.19+ (the README states compatibility with Node.js 22.19+)
- DeepSeek Harness 0.1.0-rc.6 / 0.1.0-rc.7 (the README notes current compatibility)
Installation steps
- 01
Run `npx @deepseek-ai/dsh plugin --profile web add github:oil-oil/dsh-oil-creator`
$ npx @deepseek-ai/dsh plugin --profile web add github:oil-oil/dsh-oil-creator
- 02
Restart the `web` profile to activate the plugin
Verify the integration
Not specified by the author
Rollback
- Run `npx @deepseek-ai/dsh plugin --profile web remove github:oil-oil/dsh-oil-creator` and restart the `web` profile (removal command is inferred from the install command; the README's update/remove section was truncated)
03DSH integration and capability boundaries
Installed as a dsh plugin into the `web` profile; registers itself into the Harness config without manual editing
Folder-bound project model
A local video project folder→topic.md / script.md / mp4 / srt / subtitled mp4 / cover images / publish-package.json
Writes a workspace state file at ~/.dsh-oil-creator/overlay.json (no copy of the body content)Recording & editing pipeline
Screen Studio project, script, subtitle and cover workflows→Bound recording project, burned-in subtitles, three cover aspect ratios, multi-platform publish drafts via video-publisher
04Who is it for? When not to use it?
Good for
- Creators and editors who run DeepSeek Harness (dsh) and want AI to help produce videos from a single local folder rather than a closed database
05Compatibility, maintenance and safety notes
- The README states compatibility with Node.js 22.19+ and DeepSeek Harness 0.1.0-rc.6 / 0.1.0-rc.7; core library works standalone while Screen Studio, subtitle, cover, WeChat and publish features are optional installs.
- The workbench does not perform recording, editing or final publishing itself — those steps stay with the human and external tools (Screen Studio, video-publisher, Ego Browser).
MIT · recently created (2026-08-19), no release yet
06Frequently asked questions
How do I install dsh-oil-creator?
Run `npx @deepseek-ai/dsh plugin --profile web add github:oil-oil/dsh-oil-creator`, then restart the `web` profile. It registers itself into the Harness config automatically — no manual config edit needed.
Does it work with DeepSeek Harness directly?
Yes — it is a native dsh plugin installed into the `web` profile. It requires DeepSeek Harness 0.1.0-rc.6 / 0.1.0-rc.7 and Node.js 22.19+.
Where does my content live?
Ordinary files in a local folder per video. The plugin only stores workspace state (project binding, publish marks, synced play data, tasks) in ~/.dsh-oil-creator/overlay.json and never copies your body content away.
Does it record or publish videos for me?
No. The workbench does not pretend to record, edit or final-publish. It puts the files, status and next action for each step into one context; recording, timeline editing, export and the final publish button stay with you and external tools.
07Related DSH workflows
zhuzhiliao
by imsai-sh
Web simulation of a traditional spinning cicada toy that chirps as it spins — zero-dependency single file with real audio samples, mobile-first.
picgo-core
by picgo
:zap:The ultimate image uploading engine. Both CLI & API supports.
helloagents
by hellowind777
Autonomous AI companion that doesn't just analyze problems — it keeps working until the implementation is built and verified.
k8e
by xiaods
k8e.sh - OpenSource Agentic AI Sandbox Matrix
08Data and sources
使用 DeepSeek Harness 自带的插件管理命令：
npx @deepseek-ai/dsh plugin --profile web add github:oil-oil/dsh-oil-creator
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-08-23. Found an error? Submit a correction.