플러그인

DSH용 딥 협업 글쓰기 에이전트: 편집 쌍에서 사용자별 문체 학습, clarify→outline→section-writing→red-team→reader-gallery 흐름, 프로젝트에서 보고서로 종합(실험 보고서/제품 소개/설문/README), 41개 MCP 도구, 인앱 파일 미리보기를 갖춘 웹 선택 개선 UI.

개발 전에 로컬 코드와 GitHub/npm을 조사해 재사용 가능한 구현을 찾고, 재사용과 재작성의 차이를 평가하며, 아키텍처 결합도를 점검한다.

Rich branching survey system for DeepSeek Harness (DSH) Web GUI — ask_survey tool with branch graphs, delayed hover insights, Mermaid diagrams, quick mode, reroll/push/discuss actions

Branching surveys in the web GUI: the ask_survey tool with per-option routing, hover insights, Mermaid diagrams, quick one-click answer templates, and resumable banked progress.

Deep-collaboration writing agent for DSH: per-user writing-style learning from edit pairs, clarify→outline→section-writing→red-team→reader-gallery flow, project-to-report synthesis (lab report / product intro / survey / README), 41 MCP tools, and web selection-improve UI with in-app file preview.

Model-autonomous context compaction for DeepSeek Harness: a mind_map tool surveys the agent context surface (stable seq ids, roles, token weights, clear-boundary markers, the clear-mind playbook), a clear_mind tool replaces a chosen conversation-history span with a model-written checkpoint through the native compaction transaction, call and result pairs self-collapse into one-line tombstones, and a proactive reminder nudges the model when the context grows long or a turn runs too many steps.

DeepSeek Harness plugin: ingest research PDFs into a citable OKF markdown library, then search, graph, measure coverage, and write surveys in the same conversation

维脑 Agent (Weinao) — HEMA (Historical European Martial Arts) literature research tools for DeepSeek Harness: search and read Wiktenauer pages, maintain a bilingual glossary, and produce cited research reports