Plugins

Installiert eine Multi-Agent-Voreinstellung zum Romanschreiben für DeepSeek Harness: Ein Dirigenten-Agent verteilt die Arbeit an fünf spezialisierte Subagenten — Weltenbau, Plotentwicklung, Charakterverwaltung, Prosaschreiben und QS-Review.

DeepEye-Vision-Plugin für DeepSeek Harness (DSH): Bildbeschreibung, OCR, VQA, UI-Layout und Zwischenablage-Analyse.

Ein auf DSH-better-sidebar basierender Frage-Tab in der Sidebar, der die Seiten-Fragefunktion von Codex bzw. `/btw` von Claude Code nachbildet.

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 für rein textbasierte LLMs: Bildbeschreibung / OCR / VQA über kostenlose Gemini- und GLM-Vision-APIs.