플러그인

88개의 패키징된 연구, 소셜 인텔리전스, 마케팅 및 비즈니스 에이전트 스킬을 파일 시스템 Skill 프로바이더를 통해 dsh에 마운트합니다.

사용자 GPU에서 이미지를 만들도록 로컬 ComfyUI 설치의 HTTP API에 워크플로를 대기열로 등록합니다. 빠른 초안에는 Z-Image-Turbo, 최종 에셋과 읽기 쉬운 이미지 텍스트에는 Qwen-Image-2.1을 사용합니다. comfyui_generate와 comfyui_status를 등록하고 모델 선택 및 프롬프트 작성 Skill을 제공합니다. 런타임 의존성이 없으며 수신 중인 서버가 없으면 ComfyUI를 헤드리스로 시작합니다.

PC 환경 진단 및 포트 제어 보드: 시스템, CLI 툴체인, 호버로 종료하여 해제할 수 있는 활성 리스닝 포트, 모델 키 준비 상태를 의존성 없이 검사합니다. 외부 호출 없음, 평문 시크릿 없음.

DSH를 위한 핸즈프리 듣기, 푸시 투 토크, 음성 인식, TTS 응답 및 백그라운드 Agent 위임을 갖춘 연속 음성 대화.

Settings → General에 재시작 항목을 추가해 분리된 헬퍼로 동일한 실행 인자의 dsh web을 다시 시작합니다. systemd 관리가 감지되면 allowRestart=true가 아닌 한 거부합니다. 수신 포트는 bind하지 않고 연결해 비어 있는지 확인합니다.

DSH용 로컬 개발 서비스 콘솔: 머신에서 수신 대기 중인 모든 서비스를 나열하고, 개발 중 시작된 서비스를 검사, 안전하게 중지하거나 재시작할 수 있게 합니다.

DSH 웹 포트 관리 플러그인: 로컬 수신 대기 포트를 모두 나열하고, 빈 포트를 선택하여 프로세스를 재시작하지 않고 DSH 웹 포트를 핫 스위치. 포트 관리 플러그인: 로컬에서 점유 중인 포트를 확인하고 DSH 웹 포트를 핫 스위치.

Controls the Chrome you are already logged into: the model clicks, types, fills in forms, reads pages and takes screenshots in your real tabs. macOS only; needs Chrome 116+ and Node 18+. Works over native messaging and chrome.debugger instead of a listening port. Ships 11 browser_* tools and a cb CLI, dispatches real CDP input events, draws an on-page cursor that also appears in screenshots, and adds a toolbar panel with live status, the controlled tabs and a pause switch. The native host and the MV3 extension travel inside this tarball: on first load the plugin copies them into place and writes the native-messaging registration itself, so there is no clone, no install.sh and no python3 - the one step left is adding the extension to Chrome: install DSH Bridge from the Chrome Web Store (https://chromewebstore.google.com/detail/bippcbbbipppmhjkjomgdnjbooecbimo, no Developer mode), or load the bundled unpacked copy at chrome://extensions (the plugin opens that page and puts the folder on the clipboard for you). Until then the tools fail loudly with those steps. On Windows/Linux the plugin reports the macOS-only platform requirement instead of failing silently.

Diagnoses WSL port listening and Windows localhost forwarding, with a 3080/3081 uiPlaybook for the dsh web relay and launch token.

Inventory every listening TCP endpoint and grade each holder as agent-spawned, workspace, dev-server, unattributed, system or protected; only the first two can be auto-selected, and a reap previews its descendant-closure plan unless confirmed.

Reads assistant replies aloud with Microsoft Edge neural voices and highlights the sentence being spoken, so you can follow along while listening. The highlight is yours to style: background colour, text colour and opacity are each adjustable in settings. Also adds a sound-wave play button to every reply, pause plus previous and next sentence, adjustable speed, and an auto-read toggle.

Turn English audiobooks (MP3) and documents into listening lessons: transcribe every sentence locally with the speech model DSH voice input already downloaded (about 241 MB, fetched on first use if missing; ffmpeg required), proofread and explain each sentence with your DSH model, then drill with blind listening, intensive listening and spaced repetition, with Chinese-dubbing export and offline Kokoro voices; ships a sidebar panel and four AI tools.

Native DSH right-sidebar tab that lists the ports this machine is listening on together with the process behind each one, and offers per-port actions to open it, copy its address, reveal its working directory or end the process.

Browse the skill library from a floating-ball panel: you choose the skill root yourself through a native directory chooser (defaults to ~/.dsh/skills, no path is shipped with the plugin), skills are grouped into first and second level categories, descriptions are read from each SKILL.md frontmatter, search filters by skill name, description or original text, and a card opens the full SKILL.md. Skills can be switched on and off per card, per category or for the whole library — the toggle rewrites disable-model-invocation in that SKILL.md and keeps a .bak-toggle backup, and disabled cards grey out until restored. A failure ledger separates automatic from manual entries and records skill successes and failures by listening to tools/result events, reusing an existing ledger file if one is found in the library and otherwise creating one under skill-master/references. The DSH settings page gains a floating-ball section that shows or hides the three balls and offers one-click restore of a ball dragged off-screen.