플러그인

Generates a standard motor-repair procedure from the diagnosis and motor rating, with labour time, staffing and a quality-check point for each step.

Actionable quality diagnostics for DSH agent sessions, with tool-call evidence and next-step recommendations.

Stability audit for installed dsh plugins: static risk grading (hook surface, startup work, inject, entry, dep ranges) plus optional isolated install verification.

Image generation workbench and agent tool for DSH: one tool (ark9_generate_image) paints text-to-image and image-to-image via any OpenAI-compatible API. Channels are entirely user-configured - no bundled endpoint, you bring your own baseURL, key and model name (manual input supported). Agent-initiated generations are approval-gated by default: requests queue in the floating panel and nothing bills until you approve; approval is non-blocking (the agent replies "awaiting your approval" immediately, and results, denials or timeouts are injected back so the agent reports them in the next turn). Floating glass workbench with five tabs (Generate / Approvals / Prompts / History / About), aspect-ratio grid with quality-budget + 16px-alignment sizing, transparent background, batch up to 10 images as aggregated sub-tasks, prompt library with custom JSON sources fetched through a host proxy, persistent generation logs with one-click retry, multi-channel aggregation with per-channel model fetching, bilingual UI (zh/en), stroke-SVG icon set, config import/export. Registers as a Better Sidebar tab when dsh-better-sidebar is installed; stacks above the dsh-cua FAB when both are present.

Governs multi-model access, monthly credits, manual/quality/credit/auto routing, failure rerouting, and usage auditing for DSH.

DeepSeek Harness용 SOP 기반 비즈니스 Agent Teams입니다. captain/member agent 구성, 사람 또는 agent가 정의하는 SOP workflow(노드, 종속성, 품질 게이트, 수동 게이트), 이벤트 기반 작업 예약, 웹 대시보드(SOP 캔버스, 실행 보드).

재귀적 작업 분해, 동적 라우팅, 품질 게이트, 장애 복구, KPI 보고 기능을 갖춘 다중 모델 오케스트레이션용 DeepSeek-Harness 플러그인입니다.

컴팩션 품질 / 환각 탐지기: 대화 구간이 컴팩션될 때 핵심 정보가 살아남았는지 두 축에서 확인합니다 — FIDELITY(요약의 단언은 원본 리프 이벤트에서 그대로 발견되어야 하며, 그렇지 않으면 조작된 것으로 표시됨) 및 C

DeepSeek Harness(dsh)용 Forge 품질 게이트: forge CLI가 DSH의 타입화된 인터셉션 포인트를 통해 구동하는 작업 게이트, 편집 전 읽기, bash 위험 인터셉트 및 품질 스코어링.

DeepSeek Harness용 하이브리드 모델 라우터: 선언적 규칙, 사용자 구성 가능한 비용 제어(cost-first / quality-first / balanced), 선택적 LLM 작업 분류기 및 실패 fallback 체인.

LiuHe MCP 코드 툴킷(44개 도구)을 dsh web으로 연결: repo_map, 심볼 검색, 허용적 매칭을 지원하는 edit_batch, 실행 취소 저널이 있는 트랜잭션 편집, 결정론적 품질 게이트 — 충돌 격리된 Rust tree-sitter 파싱 데몬과 SQLite 인덱스로 지원.

DeepSeek Harness Web을 위한 조합 가능한 작업·추론·품질·사람 검토 자기진화 컨트롤.

DeepSeek Harness Web을 위한 조합 가능한 작업·추론·품질 컨트롤.

DeepSeek Harness 웹 플러그인을 위한 워크벤치 수준의 도킹 시스템

DSH에 commercial-ui-ux 스킬을 등록: 작업을 고려한 상용 UI/UX/GUI 설계·리뷰·수정·구현(SaaS, 대시보드, 관리자 패널, 폼, 테이블, 디자인 시스템)과 참조 문서 체계, 품질 게이트.

데이터 분석 툴킷: CSV/TSV/JSON 프로파일링, IQR 및 z-score 이상 탐지, 품질 이슈가 포함된 구조화 요약, 코드 없는 필터/그룹/집계 쿼리.

LiuHe MCP 코드 툴킷(도구 44개)을 dsh web에 연결합니다: repo_map, 심볼 검색, 관대한 매칭의 edit_batch, 실행 취소 저널이 있는 트랜잭션 편집, 결정론적 품질 게이트 — 충돌 격리된 Rust tree-sitter 파싱 데몬과 SQLite 인덱스 기반.

Quality-of-life enhancements for the DSH workspace sidebar: hide workspaces and their sessions, reveal them from the view options, and open any workspace folder in Finder, Explorer or your file manager. Display-only: workspace, session and archive data ar

Read-only static checks for DSH profiles, bundle resolution, version compatibility, patches and MCP name conflicts, with pre-install candidate checks.

Scores each assistant answer on five dimensions plus topic coverage, shows evidence, and turns the weakest dimension into copy-ready prompt advice. Observational only; local by default, with optional Jev review.

Token-efficient web reading for DeepSeek Harness: one call fetches several pages through a real Chrome/Edge over CDP, gates them by relevance and returns a single digest, cutting context tokens by 80-98%. Real search URLs, login flow, screenshots, three proxy modes.

Hybrid model router for DeepSeek Harness: declarative rules, user-configurable cost control (cost-first / quality-first / balanced), optional LLM task classifier, and failure fallback chains.

Turn-end quality gate: when the turn edited code or config it walks each file up to its project root, runs that root one check from a fixed whitelist (`pnpm check`, `cargo check`, `ruff check .`, `tsc --noEmit`) and, only if that check really ran and failed, opens a new turn carrying the failure output instead of letting the turn close.

OCR for scanned, image-only PDFs into Markdown, built around the fact that a book takes about an hour: every page is checkpointed so an interrupted run resumes, a progress log reports live status, and a quality report names empty pages and low-confidence lines. Requires Python 3.10+ and pip install -r requirements; the first run downloads the OCR model.