@yiyunet/dsh-learn-skillsDSH 插件:AI学习 —— 会话输入区的四入口学习插件(初始预设 / 收集提炼 / 关联升级 / 沉淀复用),把「收集→提炼→关联→升级→沉淀→复用」方法论做成有交互引导、预设管理、知识审核入库与体系体检的运行时能力。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yiyunet/dsh-learn-skillsDiscover The Best DSH plugins
7478results
Explore agent orchestration, multi-agent collaboration and task execution plugins.
@yiyunet/dsh-learn-skillsDSH 插件:AI学习 —— 会话输入区的四入口学习插件(初始预设 / 收集提炼 / 关联升级 / 沉淀复用),把「收集→提炼→关联→升级→沉淀→复用」方法论做成有交互引导、预设管理、知识审核入库与体系体检的运行时能力。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yiyunet/dsh-learn-skills@yottameta/yotta-skills-pluginYuanGe (元阁) — orchestration and routing for the YottaMeta skill family, packaged as a YottaMeta Agent Plugin and DeepSeek Harness profile bundle.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:YottaMeta/yotta-skills-plugin@youdotcom-oss/dsh-plugin-youcomYou.com search + fetch provider plugin for DeepSeek Harness (dsh), plus a stackable research-profile bundle
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:youdotcom-oss/dsh-plugin-youcom@yxie2/petrinetWorkflow-net runtime for DeepSeek Harness: resource-aware concurrency, native loops and fan-out, static soundness checking before a plan becomes durable, and process mining over its own event log.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yxie2/dsh-petrinet@yyfather/dsh-token-vaultSecure credential vault for DeepSeek Harness: store GitHub/npm/API tokens (secrets never leave the host), run gh/npm/npx/node/git with the token injected in the environment, and manage tokens from a Settings page.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:YYfather/dsh-token-vault@yzxoi/dsh-holos-researchStructured research management for the DeepSeek Harness (dsh): project state machine, entity lifecycles, adversarial review, audit trail — files as the single source of truth, no UI panel, no compute submission.
@zaimokuza/dsh-agent-teams-officeOffice views for DSH Agent Teams.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zaimokuza-yoshiteru/dsh-agent-teams-office@zaimokuza/dsh-plugin-hubNative DSH resource hub: Skills, MCP, third-party plugins and experiments
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zaimokuza-yoshiteru/dsh-plugin-hub@zaofan/dsh-qqbotQQ Bot IM channel plugin for deepseek-harness (dsh)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:gcry13067381632-jpg/dsh-qqbot@zekilou/dsh-ask-formStructured form questions for the Harness agent: typed fields, conditionals, validation, rounds, a native-convention centered form, and an opt-in script escape hatch.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Zekilou/dsh-ask-form@zenmux/dsh-pluginsZenMux OAuth 2.0 PKCE login, token refresh, and Harness credential mirroring
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ZenMux/dsh-plugins@zfdx123/dsh-codegraphDSH 代码知识图谱:把 codegraph CLI 包成原生 codegraph_* 工具(core 面 status/init/sync/explore;full 面再加 query/node/files/callers/callees/impact/affected/index/uninit),并用提示前置钩子把结构化上下文推进结构化提问,让代理无需 grep 即可建立、维护、查询预索引的代码图谱。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zfdx123/dsh-atelier#8a3566cc5762e3e6d26b23c75c6ee3c4a336304f&path:packages/dsh-codegraph@zfgcta/dsh-multi-folderDeepSeek Harness plugin: secondary working directories for a project. The agent keeps the primary workspace as cwd, gains equal write/exec permissions on configured secondary directories under workspace-write mode, and is notified of configuration changes at the next message boundary. Managed from the composer's own '+' menu (official option picker, with an owned directory browser when no native picker can answer), configurable before the first message through a sessionless multiFolder remote API, and referenceable with @ in the input, subdirectories included.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:HelloQingTao/dsh-multi-folder@zhchxiao123/dsh-devflowService Definition for the ctx.devflow task-card capability seam of the DeepSeek Harness
@zhchxiao123/dsh-devflow-agent-gateDevflow LLM admission policy: configured edges dispatch an independent one-shot checker subagent whose structured verdict admits or vetoes the move, failing closed on any checker fault
@zhchxiao123/dsh-devflow-artifact-gateDevflow artifact-contract policy: configured edges require registered artifact kinds whose newest registration passes a mechanical structure check
@zhchxiao123/dsh-devflow-bundleOne-command install for the devflow plugin line: the bundle patch that mounts every devflow plugin into a DeepSeek Harness profile
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zhchxiao123/dsh-devflow-plugins#5b2116861eed2981e9c39e718ac03dc229d90cfa&path:packages/devflow-bundle@zhchxiao123/dsh-devflow-commandHuman-facing /devflow intervention command over the devflow task-card seam
@zhchxiao123/dsh-devflow-filesystemFilesystem Service Provider for the ctx.devflow task-card capability seam
@zhchxiao123/dsh-devflow-fs-guardDevflow state protection on the fs intent waterfalls: agent file tools cannot mutate the journal
@zhchxiao123/dsh-devflow-gatesCommand gate policies on the devflow transition waterfall
@zhchxiao123/dsh-devflow-parent-gateDevflow completion policy: a decomposed requirement reaches done only after every sub-requirement does
@zhchxiao123/dsh-devflow-toolModel-facing devflow task-card tools over the ctx.devflow capability seam
@zhchxiao123/dsh-devflow-uiDevflow board, browser half: read-only card stages fetched over the plugin's own read-face route
Use 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.