Plugins

Installe un préréglage d'écriture de roman multi-agents pour DeepSeek Harness : un agent chef d'orchestre répartit le travail entre cinq sous-agents spécialisés — construction du monde, intrigue, gestion des personnages, rédaction de la prose et révision qualité.

Plugin de vision DeepEye pour DeepSeek Harness (DSH) : description d'image, OCR, VQA, mise en page d'UI et analyse du presse-papiers.

Un onglet de questions en barre latérale basé sur DSH-better-sidebar, reproduisant les questions latérales façon Codex ou la fonction /btw de Claude Code.

Design-fidelity QA for text-only models: a `deepseek_vision` tool borrows an eye from any OpenAI-compatible vision route, so the model can judge whether an implementation matches its mock — shipped with the benchmark behind that judgement (four fixtures, 23 injected defects, raw transcripts) and the questioning discipline it depends on.

Design mode for DeepSeek Harness: the design-loop agent preset plus design-principles and design-qa skill packs

dsh-qa QA Workbench: a local software testing workbench plugin for DeepSeek Harness. Project/iteration dual-mode, full-flow requirements / test cases / defects / milestones / reports, native QA preset, themes, kanban and calendar.

Runs work as a crew of role agents: a product manager writes the PRD or DoD, waits for your confirmation, then starts architect, engineer, QA and reviewers whose tool sets are locked per role, and shares work through files on disk.

Translation toolkit for DSH agents: sentence segmentation, term and glossary extraction, source-target QA (numbers, units, brackets), tone guides, and a durable workspace translation memory.

Academic writing toolkit for DSH agents: paper outlines, title and abstract skeletons, GB/T 7714 / APA / MLA citations, phrasing QA, and a pre-submission checklist.

Vision pour les LLM texte seul : description d'image / OCR / VQA via les API de vision gratuites Gemini et GLM.