プラグイン

One install for SpecFlow, GitFlow, Guardian, and Code Intel on DeepSeek Harness.

Identify whether a DSH UI element belongs to the host interface or an installed plugin, then export or hide it.

Local eyes for text-only models: eyes_render draws text/shapes/Mermaid onto a canvas in the Web GUI, eyes_paste captures pasted images, eyes_ocr reads text via the built-in Windows OCR (offline), and eyes_analyze inspects pixels as structured data — no vision model required.

A stateful, Agent-controllable Jupyter workspace for DeepSeek Harness: a persistent ipykernel runtime the DSH agent can read, edit, execute, and inspect, with VS Code-aligned cell UI and .ipynb save/load.

Model-agnostic visual-inspection pipeline for text-only agents: page-by-page HTML screenshots plus a ready-made vision-subagent briefing contract (gewu_prep), then source-code truth verification of every finding (gewu_locate); validated on mimo-v2.5 & qwen3.7-plus.

DSH Plugin Registry inside DeepSeek Harness — search, compare, and inspect source-backed plugin information before installation.

Lion-Skills — a developer-focused agent skill suite (in Chinese) as a DeepSeek Harness plugin: 11 workflow skills for code review, debugging, testing, naming, spec writing, and more.

Trellis × DSH workspace dashboard: a conversation-view tab showing the current task + progress (prd.md acceptance checklist), spec/skill usage, and workspace session summary.

Adversarial code review — parallel finders inspect a diff through separate lenses (correctness, lifecycle, contract, security), then each finding goes to independent verifiers tasked with refuting it, and one refutation drops it.