dsh-bcc
Run the following command in DeepSeek Harness:
dsh plugin install aixlb/dsh-bcc
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install aixlb/dsh-bcc in your terminal, then restart dsh web and hard-refresh the browser to see the panel in the session header. Source: https://github.com/aixlb/dsh-bcc
About this plugin
Turning a reference video into a structured script or storyboard used to mean endless screenshots, hand-written prompts, and manual spreadsheet assembly, fragmented and slow.
dsh-bcc collapses the entire pipeline into a DeepSeek Harness session: ffmpeg handles smart, scene, or interval-based cut detection and keyframe extraction; bcc_read_frames feeds stills directly to the current session vision model for per-frame beat or shot-style extraction; the script path auto-merges overlapping beats and runs a timeline coverage check, while the storyboard path groups shots by cinematic language. Every prompt is editable live in the panel, and a single final step exports to docx, md, or html (script) or xlsx or html (storyboard). All analysis reuses the model already active in your DSH session, with no external API keys or extra settings pages.
Built for creators pre-producing short films, ad storyboards, or course-script breakdowns, and for any team that wants to turn watch, structure, and document into a repeatable workflow without ever leaving the current session.
Use Cases
- Break a reference video into a shot-by-shot storyboard before production to align pacing and composition
- Extract a structured script from lecture or presentation videos for later editing and re-narration
- Pull beats, shot style, and rhythm from competitor creative to produce a style guide in the ideation phase
Best For
- Short-form and film creators who need to turn references and inspiration into actionable shot lists
- Ad and MV storyboard artists who batch-extract cinematic language from footage and export to spreadsheets
- Course and content teams that want lecture videos automatically broken into segmented script documents
Related Plugins
A method pack that makes AI coding agents plan against your real baseline, prove completion with fresh evidence, and reduce reworks and unsafe changes.
Turns the DeepSeek Harness session into a captain that builds a durable sub-agent team, splits goals into dependency-aware tasks, and coordinates work via direct messages and a live Web UI.
Gives coding agents design judgment, letting Claude Code, Cursor, and 70+ agents generate and iterate high-quality UI, presentations, and graphics right from the terminal.
Run the Pi ecosystem's plugins on DeepSeek Harness, unmodified, via a compatibility layer that implements Pi's public extension ABI on DSH's native services.