DeepSeek HarnessHub
プラグインを投稿

wakeup595626-cmyk/dsh-drop-to-path ↗★ 1

@dsh-external/dsh-drop-to-path

Drag, drop or paste images / PDFs / office docs / zips / media into DeepSeek Harness - they reach a text-only model as workspace file paths. | 中文：把图片、PDF、Office 文档、压缩包、音视频拖入或粘贴到 DSH，转成工作区文件路径交给纯文本模型。 适合需要向纯文本模型提供图片、PDF等文件路径的交互任务。

視覚ツール生産性ツール
パッケージ
@dsh-external/dsh-drop-to-path
互換性
未検証
Cordis ピア範囲
^4.0.1
バージョン
0.2.6
ライセンス
MIT
最終更新
2026/09/22

同名パッケージの別リポジトリ

インストール

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wakeup595626-cmyk/dsh-drop-to-path

ドキュメント

README 全文を読む ↗

Usage

  1. Paste or drop images as usual — the attachment cards behave natively (preview / remove);
  2. Drag or paste any other file (pdf / office / zip / video / audio) — a square chip with a format icon appears in the attachment rail next to the image thumbnails (full name on hover, ✕ to remove);
  3. Type your message (optional) and hit send — no attachments are sent; images and files are uploaded and their workspace paths are appended to the message automatically;
  4. The agent (paired with dsh-vision-toolkit) reads images with vision_glance / vision_pixel_diff and friends, and handles documents with PDF / spreadsheet tools.

Files are stored under /.drops/; clean them up whenever you like.