anglesvideo-dsh-plugin
Run the following command in DeepSeek Harness:
dsh plugin install anglesvideo/anglesvideo-dsh-plugin
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install anglesvideo/anglesvideo-dsh-plugin in DeepSeek Harness to install this plugin, whose source is available at https://github.com/anglesvideo/anglesvideo-dsh-plugin
About this plugin
Most teams have a solid product codebase but struggle to turn it into a compelling launch video in a reasonable amount of time. anglesvideo-dsh-plugin, an early DeepSeek Harness integration, reads a curated allowlist of product-facing files from the repository and produces a bounded context summary. That summary is then sent to the Angles service, which returns three distinct launch-video concepts for you to review and compare. Crucially, the plugin never uploads the raw repository: it skips dotfiles, common build directories, sensitive path names, and lines that resemble credentials, so only the context you have vetted feeds into concept generation.
The workflow spans the full pipeline from ideation to final render. You can list available templates and their media requirements, run a preview check on a chosen concept to surface blockers, warnings, and media usage without consuming a render allowance, upload user-selected screenshots or short clips as assets, and then kick off the actual render only after explicit confirmation. The render endpoint requires confirmed set to true and an idempotency key, guarding against accidental double-spends. A status-polling call returns render progress and, once complete, the final video or editor URL.
Deliberately kept small, this developer-preview bundle talks straight to the Angles Developer API rather than shipping a custom DSH panel or an embedded video editor. It is best suited for independent developers or small teams who are already experimenting with DeepSeek Harness, hold an Angles API key, and want to quickly translate product semantics in their repository into visual launch assets. In production, pin both the plugin version and the DSH version, as compatibility contracts are still in flux during the preview window.
Use Cases
- Extract key context from a product repo and generate three launch-video concepts
- Preview blockers, warnings, and media usage before triggering the actual render
- Upload screenshots or short clips as assets and poll status for the final video URL
Best For
- Independent developers experimenting with DeepSeek Harness
- Small teams turning product code into visual launch assets
- Product managers with an Angles API key seeking video output
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.