@deepseek-ai/dsh-client-webWeb shell kernel: bootWebShell (module system holding + seed table + two-stage boot + AppRoot gate + app-shell assembly entry), consumed by the apps/web vite entry
최고의 DSH 플러그인을 만나보세요
2028개 결과
재사용 가능한 스킬, 도구 모음 및 작업 기능의 설치와 사용 방법을 찾아보세요.
@deepseek-ai/dsh-client-webWeb shell kernel: bootWebShell (module system holding + seed table + two-stage boot + AppRoot gate + app-shell assembly entry), consumed by the apps/web vite entry
@deepseek-ai/dsh-client-web-reactShell-side React glue: createSlotRenderer, SessionProvider, bindSnapshotSelector (uSES bridge), useInvoke
@deepseek-ai/dsh-cmdlineImmutable command-line handoff from a dsh launcher to any app plugin that injects cmdlineArgs
@deepseek-ai/dsh-headlessThe dsh one-shot bundle: a direct core Agent/Session runner over dsh-base with no Host, HTTP, or browser layer
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:luxiu666/OmniOps#9ec3d6a99a28a9bf23c275dad870af4b4e1d265e&path:packages/bundle/headless@deepseek-ai/dsh-web-appThe dsh browser-surface bundle: the web patch layer over dsh-base plus the runtime glue plugin (frontend dist serving, web-surface prompt, bash runtime variables, URL line)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:luxiu666/OmniOps#9ec3d6a99a28a9bf23c275dad870af4b4e1d265e&path:packages/bundle/web-app@luxiu666/dsh-mysql-diagMySQL 慢查询诊断 bundle:skill(mysql-slow-query-analysis)+ mcp-client(stdio 自动拉起 mysql-diag-mcp)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:luxiu666/OmniOps#9ec3d6a99a28a9bf23c275dad870af4b4e1d265e&path:packages/bundle/mysql-diagdsh-embedded-workbenchEmbedded C/C++ firmware development toolbox — 4 agents, 8 skills covering FreeRTOS, ISR, NVM storage, Keil MDK, ARMCLANG, HardFault, state machines, architecture, LVGL patterns, and claim fact-checking. Ships a native DeepSeek Harness (dsh) bundle that injects the session-start gate into the first model step.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AmethystLuna/embedded-workbenchshidi-dsh-pluginAI-for-Science research workflow skill bundle for DeepSeek Harness: multi-angle literature review with per-angle files, anchored experiment design with a caveat list, figures, paper reading; cross-verification briefs.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:IcyCreamDAS/shidi-skill@limuyang2/dsh-agent-teamMulti-agent team management plugin for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:limuyang2/agent-team@morlay/dsh-desktop-hostDesktop host process for dsh-desktopify: boots the desktop profile and serves it through an in-process, portless webServer over byte pipes — upstream apps/desktop-host with the web carrier taken over and the Office skill mount removed.
@morlay/dsh-reference-injectionExpands a referenced skill (`skill:name`) into an injected <skill_content> instructions message and a referenced `@path` into a read-shaped file content block at the pre-step boundary.
dsh-fail-loggerDSH 插件:全模式工具失败自动实录——把原生工具、PTC(Code Mode) run_code、代码内嵌工具调用的失败按错因去重计数,自动写入 skill 的机器维护区段,越用越少错。Auto-record tool failures from every execution mode into a skill's machine-maintained section (dedup + counts).
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Areium/dsh-fail-loggerdsh-memory-evolve为 DeepSeek Harness 带来分层记忆(全局 / 用户 / 项目 / GIT 分支 / 每日)与自我进化(经验沉淀 + 技能自动创建)和技能管理、待办管理、CLI 调度(kimi/codex/grok/hermes 等外部 AI 统一调度)、临时信息便签,带 WebUI 管理界面。Hermes-style long-term memory, self-evolution, skills, todos and external CLI agent dispatch for DeepSeek Harness.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:picoaide/picoaide-harness#517bf0c6b000c32de0f459fe78770c4fb9720c13&path:packages/vendor/memory-evolveweshop-dsh-pluginNative Cordis WeShop canvas, tools, skills, and Web UI for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:weshopai/weshop-dsh-plugin@bainianling/dsh-jailbreak-modeLogged per-agent jailbreak mode: automatic prompt-injection prefix for red-team safety evaluation
@deepseek-ai/dsh-client-ui-skillWeb skill references and the dedicated skill tool row
@dsh-jev/plugindeepseek-harness-jev: native DeepSeek Harness (DSH) plugin integrating TypeSafe Jev / System One for selection, supervision, corrections, tool-output filtering, and approvals
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:luobosibing2/deepseek-harness-jevchicheng-crondsh 定时任务插件:在左侧栏“新会话”下方提供“定时任务”入口,支持 cron 定时执行 shell / python / nodejs 脚本、skills 与自定义 agent 任务,可对接 chicheng-push 与 messaging-core 推送通知、成功后自动归档会话,移动端适配
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:534119219/chicheng-crondsh-archifyDeepSeek Harness 插件:用 JSON 规格生成可验证的架构图、流程图、时序图、数据流图与生命周期图(移植自 tt-a1i/archify)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:GongYuanCaiJi/dsh-archifydsh-codex-portDSH 技能移植工具插件:把 ~/.codex 里的 Codex 官方插件(170+ 个)一键移植为 DSH 技能(codex_list / codex_port / codex_status),frontmatter 自动转换、名称清洗、幂等跳过。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:STARDUSTLC666/dsh-codex-portdsh-life-pack爱生活总管插件:单 DSH设置面板槽(爱生活卡)+ 爱生活页签槽 children,技能设置页动态聚合,不依赖单品、不 import 单品页
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:FeatherHunter/ilife#9c7c84a2345e47c8df452f41742c3742d84bb787&path:packages/plugin-managerdsh-octoInstallable dsh bundle for the dsh-octo heterogeneous-agent orchestration skill
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:tokentopo-ai/dsh-octodsh-plugin-miliastra-toolboxDeepSeek Harness plugin: 千星沙箱知识库(节点/指南/教程/FAQ)查询工具与技能
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:1475505/dsh-plugin-miliastra-toolboxdsh-probhubDeepSeek Harness tools for the installed ProbHub CLI
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:greenthree/ProbHub-skill#88a4dba168027e0a0143de0d07668b72728aa993&path:plugins/dsh-probhub기능 키워드나 카테고리로 범위를 좁히고 최근 업데이트 또는 GitHub Star로 정렬하세요.
소개, AI 분석, 원본 README를 읽고 플러그인의 기능을 확인하세요.
호환성과 의존성 범위, 설치 안내를 확인한 뒤 제공된 설치 명령을 복사하세요.
DeepSeek Harness 커뮤니티 플러그인 디렉터리입니다. 소개, 소스 링크, 설치 안내를 모아 확장 기능 검색과 비교를 돕습니다.
아니요. 상세 페이지는 기록된 호환성과 의존성 범위를 표시합니다. 알 수 없음은 호환을 의미하지 않으므로 설치 전 프로젝트 문서를 확인하세요.
상세 페이지의 설치 영역을 확인하세요. 명령이 있으면 Harness 환경에 복사해 실행하고, 없으면 프로젝트 README를 따르세요.