luoyuejun9/dsh-cinematic-workflow
luoyuejun9★ 1TypeScript最后同步: 2026-08-16
—
README 摘要
dsh-cinematic-workflow Local-first, human-gated authorial film workflow for DeepSeek Harness. It turns a cinematic travel-film directing workflow into a real DSH plugin: media inventory, creative direction, rough-cut deliverables, import-ready FCPXML, Resolve handoff, restrained copy/subtitles, QC and delivery records. It is intentionally not a mouse macro for Final Cut Pro or DaVinci Resolve. The central rule is enforced in code: a stage never advances unless a human runs /cinema continue and the current stage has its required deliverables. Models cannot approve, skip, merge, or pre-run future stages. Install Restart or reload the DSH profile after installation. The package targets DSH 0.1.0-rc.6 ; Harness is a developer preview, so pin compatible versions when upgrading. Quick start Review the current stage. Record creative choices without moving forward: Workflow Stage Required human-reviewed deliverables Sample (optional) Style database Analysis Media inventory, director notebook, creative baseline, chosen arc Rough cut EDL, FCPXML, sound plan, director review Grade Grade brief, Resolve return artifact Finishing Copy script, subtitles, finishing timeline Delivery QC report, del…
在 GitHub 查看完整 README →分类
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件,为 DeepSeek、GLM 等纯文本模型外挂视觉能力,粘贴图片即得结构化 JSON 证据(OCR、版面、语义)。
★ 2,208
Anionex/agent-vision-toolkit为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
★ 933
Anionex/dsh-vision-toolkit让纯文本模型更好地做视觉任务的DeepSeek Harness插件:带意图的图片问答、长截图 OCR、UI 还原等|DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
★ 488