dsh-video-length
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-video-length
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-video-length in DeepSeek Harness to install this plugin; the full source is available at https://github.com/uckkk/dsh-video-length.
About this plugin
In model-inference workflows, video duration is often an under-the-radar variable that directly affects both output quality and resource cost. dsh-video-length exists to tackle exactly that: it ships a lightweight video_length tool that takes your parameters and returns a precise, structured duration recommendation, saving you from costly trial-and-error loops.
The entire plugin is implemented in pure Node.js with zero network dependencies. Once installed, it is available immediately within your local session, delivering fast and deterministic responses. This side-effect-free design makes it a natural fit for automated pipelines and offline environments.
Whether you are building a video-inference pipeline that needs to set output duration programmatically, or simply want to turn duration decisions from gut feeling into a calculable rule, dsh-video-length offers a reliable answer at virtually zero integration cost.
Use Cases
- Dynamically calculating optimal output duration based on input parameters in a video-inference pipeline
- Planning video duration in offline environments with zero network calls
- Turning duration decisions from gut feeling into a computable rule
- Embedding duration suggestions in automated pipelines to avoid trial-and-error
Best For
- Developers building video-inference pipelines
- Engineers who need to set video duration programmatically
- Teams working in restricted or offline environments that require dependency-free tools
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.