dsh-file-upload
kamilhzn
dsh的文件上传解析插件:把本地文件 (txt、md、各类代码文件、Word、Excel、PDF)上传到对话框,解析为文本后随下一条消息 注入给模型,并在输入框上方以可删除的条带展示。
DSH-PLUGIN STORE / LIVE CATALOG
聚合 GitHub 上的 DSH 插件,打造 DeepSeek Harness 生态的一站式目录。
84 个项目,匹配「pdf」
kamilhzn
dsh的文件上传解析插件:把本地文件 (txt、md、各类代码文件、Word、Excel、PDF)上传到对话框,解析为文本后随下一条消息 注入给模型,并在输入框上方以可删除的条带展示。
mikasa-servent
Deliverable evidence-chain & conformance checks for DSH — turn requirements into an executable spec, trace every number to a provenance ledger, audit PDF/OOXML metadata and archive manifests. MCP-ready.
qingmumingyang
DSH 文档读写工具包 - PDF/DOCX/XLSX/CSV 读写与 PDF 导出(利用dsh制作的,希望能帮到你们)
wj2514939573-ui
dsh-text-master — All-in-one text processing plugin for DeepSeek Harness (Cordis): polish, summarize, translate (24 languages), correct, expand, condense, tone/style conversion, creative writing; batch processing with format preservation (Markdown/docx/PDF) and custom dictionary.
zhoupengyun572-cell
A local literature review, PDF annotation, evidence synthesis, and research notes workbench for DeepSeek Harness.
HiSeax
Overlay reader for agent output files: Markdown/GFM rendering, in-panel PDF, DOCX/XLSX/PPTX text preview, reply-end file chips. Pure JS, zero deps.
LR611415
`DSH plugin to read/write Word (.docx), PDF and text files`
bauerelizabeth07139
DeepSeek Harness plugin: convert Word .docx to PDF with the dxpdf Rust/Skia engine — no Microsoft Office, no LibreOffice, no network. It repairs the schema-invalid constructs WPS Office writes and restores Word's odd/even page parity.
ice5kysl
dsh (DeepSeek Harness) file explorer: browse the active session's workspace and preview files (Markdown/image/PDF/text/binary) right inside the chat GUI — a standard Cordis bundle plugin (read-only /dsh-files host routes + a conversation.view file tab).
l2685209197
DSH 插件:用 DeepSeek 翻译文本型 PDF,保留版式/字体/图片/链接,输出可编辑 PDF(单次 ≤50 页)
liiydong
DSH Web 插件:把「AI 改 md → 生成 Word/PDF/Excel → 你审这一版」变成一条看得见的时间轴(含技能库与文档配对)。自带演示数据、零依赖、只读为主。
protoctistmoses143
Convert PDFs, Office docs, scanned images, and more to clean Markdown, JSON, or text locally with offline OCR—no servers, no API keys, fully private.