Discover The Best DSH plugins
7205results
Explore agent orchestration, multi-agent collaboration and task execution plugins.
novel-writerMulti-Core Collaborative Novel Writing — a DeepSeek Harness (DSH) preset plugin that installs a multi-agent novel-writing mode: one conductor plus five specialized subagents (多核协同写作模式).
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:sailoumili/novel-writeronebox-dsh-bridgeDeepSeek Harness plugin: bridge local dsh web to the OneBox Android app over the public internet (scan-to-pair, E2E encrypted tunnel). 万宝盒 App 的 DSH 云端中继桥插件。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wangzhishou/onebox-dsh-bridgepet-whale桌宠小鲸鱼：随 agent 状态切换动画的 DeepSeek Harness Web 桌宠插件（官方轮廓版）
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:nzl153/dsh-pet-whalepr-geniusPR 评估和建议工具 — 基于历史反模式和成功模式
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zsxh1990/pr-geniusproject-change-router-skillProject-level direction, boundary, and reuse governance for AI coding agents.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:WeirdSky924/project-change-router-skillreview-workflowA structured multi-panelist review workflow for the DeepSeek Harness: N panelists score in isolated subagents blind to each other, a chair reconciles disagreement, an independent critic audits the process.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:LeslieWylie/review-workflowround-tableDSH 多方群聊协作插件（圆桌）：多 Agent 研讨房间，@指定/全体研讨/接力链，轮次控制与一键总结
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:vuchisu069-source/dsh-round-tablesemantic-linterSemantic-Linter plugin and CLI for narrowing wide-boundary wording in LLM instruction files.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:SummerSec/semantic-lintershopline-ai-toolkit-dshSHOPLINE AI Toolkit for DeepSeek Harness (DSH): bridges the official SHOPLINE Developer MCP server and ships SHOPLINE agent skills, mirroring the Shopify AI Toolkit architecture. dsh-plugin.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lunw/shopline-ai-toolkit-dshspecpowersSpecPowers for the DeepSeek Harness and Claude Code: a spec-driven + test-driven engineering skill group fusing OpenSpec and Superpowers
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:SAXEM1997/specpowersstalegreenHooks that keep a coding agent's green claims honest: verification runs are recorded unmasked, and "done" is blocked when the evidence is stale, failed or masked.
SuperLcmSuperLcm — Lossless Context for DeepSeek Harness: fully asynchronous, cache-friendly compaction with exact recall.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ygc3817922006-sketch/SuperLcm-Lossless-ContextSuperLcmSuperLcm — Lossless Context for DeepSeek Harness: fully asynchronous, cache-friendly compaction with exact recall.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yu381792/dsh-superlcmteach-math-with-manim图书《Manim，让数学看得见》配套开源仓库：60+ 教学动画案例源码 + manim-teaching AI Skill（含 DeepSeek Harness 插件）
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Scorpio69t/teach-math-with-manimthink-like-codexCodex-inspired planning, evidence, goal, and anti-loop policy plugin for DeepSeek Harness.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zhangnan/think-like-codexwangdefa-memory本地优先的 Agent 五层记忆体组件 - DSH 插件
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:VinsonWild/Wangdefa.Memoryworktree-mgrdsh 插件：为任务自动创建隔离的 git 工作区，管理 创建/同步/收尾 全生命周期
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:JohnXu22786/worktree-mgryapaYAPA — Memory & Task assistant as a native DeepSeek Harness plugin
@240xu/dsh-tech-leadTech-lead lifecycle plugin for DeepSeek Harness: 21 read-only tools (classify/state/plan/evidence/gates/release/install audits, context/evidence/progress analysis, mutation preview). No writes, no subprocesses, no network.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:240xu/verdict-engine#b656c8e3284a9b6f1805c49a92873f473a30c976&path:packages/dsh-tech-lead@240xu/dsh-tech-lead-bundleOpt-in dsh profile bundle exposing the read-only tech-lead tool surface
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:240xu/verdict-engine#b656c8e3284a9b6f1805c49a92873f473a30c976&path:packages/dsh-tech-lead-bundle@240xu/dsh-tech-lead-corePure, dependency-free validators for the tech-lead lifecycle (state, evidence, plan, gate, release, install audit)
@240xu/dsh-tech-lead-pluginRead-only tech-lead lifecycle tools for DeepSeek Harness (classify, validate, lint, audit)
@a9i5k4/dsh-memory-fittingIntent fitting for DSH: the agent predicts several directions first, asks a batch of clarifying questions each round, narrows the distribution until one converges, then proposes it for your confirmation. Bottom-right floating panel, local JSONL archive, and both context injection and memory writes behind independent opt-in switches. 记忆拟合：AI 先预定若干方向（预测你的意图），每轮批量提问，轮间思考并展示方向可信度，收敛后提案待确认。右下角悬窗 + 本地留档；上下文注入与记忆写入各自独立开关，默认关闭。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Aik358/dsh-memory-fitting@ag-dsh/dsh-gen-commit-msg-zhDeepSeek Harness (DSH) plugin: generate a Chinese git commit message and commit interactively (slash command + skill)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AlphaGodzilla/ag-dsh-coding-plugins#5c9a78f999f32cd9cb49bd95d2ca4ad167999b54&path:packages/gen-commit-msg-zhUse 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.