dsh-age-calc
★ 0dsh-age-calc年龄计算
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-age-calcDiscover The Best DSH plugins
23436results
Search community plugins for DeepSeek Harness. Compare capabilities, installation instructions and compatibility to find extensions for your AI workflow.
dsh-age-calc年龄计算
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-age-calcdsh-age-edu分龄教育
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-age-edudsh-agency-marketExpert market inside DeepSeek Harness — browse expert cards, install one as a user agent preset, then chat in a session on that preset. · DSH 专家市场:逛一逛,点一下,装好,开聊。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:pbwheel/dsh-agency-marketdsh-agenoteDeepSeek Harness 的 agenote 集成插件:会话开始注入知识库健康度、turn 结束检测完成信号并转交 agenote-review 流程,外加 /agenote-summarize|curate|health 斜杠命令。行为规范由 agenote-skills 定义,插件只做事件触发与命令快捷入口。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ShineBreaker/dsh-agenotedsh-agent-alertDesktop alerts for DeepSeek agent states: browser Windows notifications plus PowerShell sounds.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:DeepVite/dsh-alertdsh-agent-boardThird-party Agent Board plugin for DeepSeek Harness web profiles
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:meisam2236/agent-boarddsh-agent-bridge飞书「算法组」机器人 → DSH 会话桥:在指定工作区开真会话,用 DSH 现有模型+插件执行任务并回传结论 — DSH bundle。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:CAI-MH/dsh-agent-bridgedsh-agent-browserAgent-driven control of the DSH right-Sidebar browser: read page content, act on it, size the viewport, and take screenshots from model tools (Desktop only)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:guanhaisen/dsh-agent-browserdsh-agent-browserIn-process agent-browser tools for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:win10ogod/dsh-agent-browserdsh-agent-chat让两台机器上的 DSH agent 通过 HTTP 互发消息并在回合开始时注入上下文
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:harmless0819-dev/dsh-agent-chatdsh-agent-checkpoint存档点管理器:最后的保活机制 + 试错回滚工具。定时/事件/主人指令创建健康存档点(记忆库+灵魂+校验和),验证器确保存档可启动,出事后一键恢复最近健康点。
dsh-agent-cleanRemove subagent entries from DeepSeek Harness session logs without breaking the log, delete orphaned projection caches, and purge whole sessions — a CLI (dry-run by default, always with a backup) plus an optional DSH settings page (Settings → Session cleanup) that shows what needs cleaning and can clean everything automatically on the next quit.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:PolitaryMonicy/dsh-agent-cleandsh-agent-clusterDSH 多实例通讯底座:本机(或共享盘)上多个 DSH 实例之间的去中心化消息总线 + 在线名册 + 点对点/广播消息,收到消息注入本实例会话交给 agent 处理。用于搭建多智能体工作台。v0.2.0 起带「重启收自己的尸」:同主机同 profile 的死前身心跳/状态在启动时清扫(保守判活,未知不删)。
dsh-agent-commanderDSH web plugin: multi-agent commander. Open Claude / opencode / codex agents with role & skill definitions, watch every agent's live terminal in a right-side radar panel, and let DeepSeek dispatch tasks through agent_* tools. Shared memory: 记忆库.md / 任务看板.md / 交接区 in the project directory.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:qinglang8609/deepseek_herdrdsh-agent-conductorIn-session cross-agent dispatch for DeepSeek Harness: the conductor_dispatch tool and an auto-triggered skill send self-contained tasks to 11 external agent CLIs. Host-only bundle — no client half.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:akqwpeter-prog/dsh-agent-conductordsh-agent-context-steward上下文管家(借鉴 ThoughtDAG「用户是你」):context_health 工具给当前会话上下文体检(压力/构成/健康 + 主动管理建议),增强我作为上下文主编的可见性与管理能力。
dsh-agent-contract多智能体契约工作流引擎:契约注入 / 每角色委派通道 / 产出契约三工具 / 台账三领域 / 元数据自动派生器 / 图书管理员(按需唤醒)/ 审计(警告制)。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:t2094308-star/dsh-agent-contractdsh-agent-delegateDelegation broker for DeepSeek Harness. 真实委派深度、角色衰减、并发预算、陈旧结果丢弃、写入型 child / 并行任务的 Git worktree,以及 sandbox partial 拒绝。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xingyingyuzhui/dsh-agent-delegatedsh-agent-dispatchHelper dispatch — a visible settings panel that decides whether the main agent may delegate work to helper agents, which helpers are allowed (free-lane models / subagents / experts / teams), and injects that division of labor into a systemPrompt section, taking effect on save.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Napstablooky233/dsh-agent-dispatchdsh-agent-emotion情感与人格插件:6 维进化棱镜的运行时传感器——感知层(订阅 DSH 工具管线/思考流事件采集 6 侧面信号)→ 情感引擎(增速差值=情感信号)→ 人格层(权重漂移)→ 呈现层(emotion_status)。结构化事件为主,思维链仅元特征,纯观察默认。
dsh-agent-evalDSH plugin: evaluate agent performance on defined tasks — run benchmarks, score outcomes, track improvement over prompt/model changes.
dsh-agent-evaluatorAgent benchmark evaluation plugin for DeepSeek Harness: web panel, slash commands, headless CLI, test-set import, model/judge switching, orchestration, scoring, and reports.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yan77-h/dsh-agent-evaluatordsh-agent-evolutionPreset-composed Agent experiments for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:FriendsHL/dsh-agent-evolutiondsh-agent-extensionDeepSeek Harness plugin for workspace commands, skills, and path-scoped rules.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:SugarFatFree/dsh-agent-extensionUse a feature keyword or category, then sort by recent updates or GitHub stars.
Read the description, AI analysis and original README to understand what a plugin does.
Review compatibility, dependency ranges and instructions, then copy the available install command.
DSH Hub is a community plugin directory for DeepSeek Harness, bringing together descriptions, source links and installation instructions to help you discover and compare extensions.
No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.
Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.