dsh-agent-team
Contexera
dsh-agent-team: Agent Teams for DeepSeek Harness. Hand work to a team of agents that carries it end to end while you set the direction and hold the gates. You stay on the loop, and step back in whenever you want.
yangdcm182Updated 5d ago
Role-based multi-agent expert team for DeepSeek Harness: one sentence in, a staged and gated team delivery out. 12 role subagents, 9 gated phases, shared-workspace artifacts, zero runtime dependencies.
Practical score
82 / 100
Setup
Ready to use
License
MIT
Language
JavaScript
Copy the command, or hand the whole task to your harness agent.
dsh plugin --profile web add @yangdcm/dsh-expert-teamPlease install the DeepSeek Harness plugin "dsh-expert-team" for me. - GitHub repository: yangdcm/dsh-expert-team (https://github.com/yangdcm/dsh-expert-team) - Type: a Cordis plugin (installed into a DSH profile) - The plugin declares a DSH version requiremen…
A cleaned excerpt from the project's own documentation.
专家团 · dsh-expert-team English 中文 角色化多智能体专家团 = 你的数字员工 : /team 做一个带登录的支付模块 —— 给 中小团队与个人接单者 一支完整技术部: 一句目标即自动组建产品 / 架构 / 前端 / 后端 / 审查 / 测试等多角色专家团, 按九阶段门控流水线协作交付,并支持常驻团队反复指挥; 实现者直接改你工作区的代码, 全过程留痕成可复核的工件 。 装在 DeepSeek Harness 上的 dsh 插件: 零运行时依赖、无构建步骤、无安装钩子 。 12 角色 9 阶段 90 个测试文件 0 运行时依赖 0 构建步骤 --- --- --- --- --- 各带角色子预设(persona + 工具边界)/ maxDepth: 1 含 1 道硬门 + 1 道确认门 CI 每次 push 跑全套测试 dependencies:…
Open on GitHubSimilar tools from the same corner of the ecosystem.
Contexera
dsh-agent-team: Agent Teams for DeepSeek Harness. Hand work to a team of agents that carries it end to end while you set the direction and hold the gates. You stay on the loop, and step back in whenever you want.
ishuowang
Native DSH rooms for connecting independent Sessions and provider-backed AI members—without bundled roles or scenarios.
PerryLink
Industry and company research domain pack: industry_map chain maps, public-source policy/news tracking over ctx.web (industry_track), company_scan cards from user data files, and industry_report with an optional ctx.researchReport sealing bridge and a builtin-fallback renderer, plus two methodology skills.