Plugins

Um plugin de leitura de PDF sensível ao conteúdo para modelos de visão: perfila cada página para figuras (vetoriais e raster), tabelas, risco de fórmulas e layout de coluna dupla, depois aplica extração híbrida sensível ao conteúdo, renderizando páginas com figuras/tabelas/fórmulas como recortes de região de alta DPI. Fornece uma pré-visualização de baixa resolução para entender o layout da página e renderiza uma região especificada em alta resolução. Empacotado como múltiplas ferramentas para agentes.

Adds a versioned DPIA workbench to DeepSeek Harness for source-linked facts, follow-up answers, reassessment, and reviewable reports. Needs Python 3.9+ with `python-docx`, `pypdf`, and (for PDF templates) `reportlab` + `pdftoppm`.

Manually zoom the Harness Web UI from 75% to 200% via a Settings row, Ctrl+wheel, or a Session-header control, keeping text crisp and readable on high-DPI displays.

Publish size check skill: verifies a deliverable's geometric specs against a target platform before publishing - pixel dimensions, aspect ratio, dpi, file size, format, physical print width and colour mode. Geometry only: it does not review content compliance (QR codes, text-to-image ratio, copyright and prohibited content are out of scope). Pure Python standard library, no third-party packages, and inputs are never modified. Python 3.8+. Covers 10 platforms and 20 slots with per-platform confidence labels - WeChat MP, Xiaohongshu, Bilibili, Zhihu, Weibo, Douyin, WeChat Channels, journal submission, print and client delivery - and resolves a platform by id, Chinese name or alias with fuzzy matching. Two trigger modes: asked directly, or as a parasitic self-check that runs by itself once an image, poster, chart or export workflow has written a file and the user mentioned a publishing target, reporting in one line when everything passes and only expanding when something is wrong. For journal submission and print it judges by physical width (pixels / dpi), which catches files whose dpi metadata passes but whose actual printed size is too small; for multi-image posts it checks whether the whole set is consistent and names the odd one out rather than listing every file.

Windows GUI automation reliability layer: probes whether a window is minimized, foreground or DPI-scaled, then clicks and types with the coordinate space and activation order handled for you. Zero dependencies, local only.