Discover The Best DSH plugins

DeepSeek Harness plugins — Page 927

26751results

Search community plugins for DeepSeek Harness. Compare capabilities, installation instructions and compatibility to find extensions for your AI workflow.

dsh-progress-reporter

Codex-style, time- and milestone-oriented progress updates for long-running DeepSeek Harness agents.

Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:baiyuscc13724-max/dsh-progress-reporter
dsh-progress-rules

DeepSeek Harness bundle plugin: a process-discipline system-prompt section plus a deterministic nudge that makes agents narrate progress between silent tool steps.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Adamaik/dsh-progress-rules
dsh-progress-secretary

工作进度小秘书 — a workspace progress notebook for DeepSeek Harness with two manual operations: record progress and brief progress

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zpda88888a88888-debug/dsh-progress-secretary
dsh-progress-summary

Out-of-band progress narration for DeepSeek Harness: a cheap auxiliary model turns live reasoning into one short status line, for the Web UI and dsh-tui

Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:tastynoob/dsh-progress-summary
dsh-progress-widget

Task progress bar for DeepSeek Harness web: stages, percent, current action, elapsed time and ETA. Fully event-driven task lifecycle, auto stage templates, multi-session support. Independent DOM, never touches dsh UI slots.

Agent collaboration · Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uuhihj/task-progress-bar
dsh-project

DeepSeek Harness 的「项目」插件:把多个文件夹 + 多个会话 + 一份共享记忆/指令收敛到一个项目实体。项目树收纳(项目→文件夹→会话)、多文件夹(自动注册工作区)、项目内新建会话、项目级 PROJECT.md 共享记忆(会话开始整体注入 + project_memory_write 工具)、AGENTS.md 项目指令注入。

Memory and knowledge · Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lanyun077/dsh-project
dsh-project-based-learning

项目制学习教练:学科无关的教学引擎 + 可替换领域包(随包提供 Unity/C# 特化)。以 DSH 技能与组合包双形态分发。

Skills · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Kirisame1969/dsh-project-based-learning
dsh-project-config

Per-workspace subagents, commands, MCP servers and hooks for DSH from .dsh/settings.yml · 从 .dsh/settings.yml 为 DSH 工作区加载子代理、命令、MCP 和 hooks

Agent collaboration · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:RicardoYan/dsh-project-config
dsh-project-dev

「项目开发模式」+ 开发进度看板:预设 persona/团队职责/看板守则,7 个 project_board_* 工具(含 prune 批量清理),只读快照路由与聊天内悬浮看板。

Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:kkomia/dsh-code-team
dsh-project-env

Per-project runtime environments for DeepSeek Harness: auto-adopt or create a project-local Python venv (.venv_local/python) and wire in the toolchains/env vars for the runtimes each project uses.

Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:emuco/dsh-project-env
dsh-project-forge

Project Forge — a DeepSeek Harness agent preset that keeps a project recoverable, traceable, and continuable: local-only git, four state documents, layout and naming discipline, compaction recovery, and five write guards.

Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:sopreigj/dsh-project-forge
dsh-project-guard

Permission guard for DeepSeek Harness: work inside the workspace is never interrupted, and only the extra permission a call asks for is judged — machine-safe actions pass, system changes ask with a consequence analysis, destructive ones are refused.

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Inceptzws/dsh-project-guard
dsh-project-handbook

Company-grade project handover & onboarding handbook generator for DeepSeek Harness: evidence-backed Markdown (PROJECT-HANDBOOK.md + handover checklist + glossary + runbook) built from real repository inspection, with a deterministic inventory scan and a documentation quality gate.

Skills · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Gan-lang/dsh-project-handbook
dsh-project-inbox

Project workbench for DeepSeek Harness: cross-session inbox, automatic project attribution, interruption alerts, and external delivery

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Lingrui98/dsh-project-inbox
dsh-project-initialization

DSH 插件「想法落地」(DSH-Project-Initialization):原子化 73 skill(6 主 + verify 调度 + 66 原子子,无场景预设按上下文加载),确认绑定/操作分级/扮演假设规则体系,覆盖需求确立、技术选型、维护与发布、清除整理、反馈闭环,让 AI 创建产品每一步对齐用户想法。

Skills · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Lorvaste/DSH-Project-Initialization
dsh-project-j4agent

Jira-like Agent-native Project Management for DSH

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:esonx/dsh-project-j4agent
dsh-project-memory

Bounded, git-committable project memory for DeepSeek Harness: five whitelisted .ai/ files with capacity budgets, structured entries, tiered retention, a stable prompt section, and explicit forgetting.

Memory and knowledge · Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xingzoudefengye/dsh-project-memory
dsh-project-memory

Cross-session project engineering memory for DSH coding agents: durable per-project records of problems, failed attempts, verified root causes and constraints, recalled automatically before the agent plans.

Memory and knowledge · Agent collaboration · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yuyuyyyyyyyyyyyy/dsh-project-memory
dsh-project-notes

DeepSeek Harness 原生插件:工作区便笺、轻量待办、自动保存与草稿插入。

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yxue301603/dsh-project-notes
dsh-project-ops

Cordis project task planning and verification with native Harness execution

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Missher12/dsh-project-ops
dsh-project-ops

Cordis project task planning and verification with native Harness execution

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Missher12/Missher-DSH-Project-Ops
dsh-project-panel

DSH 工程面板:把低代码工程目录树搬进 web 端 —— 左栏常驻图标 + 中栏工程浏览器(多级文件树 / 推送状态 / 文件内容)。

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lzqzm/dsh-project-panel
dsh-project-portfolio

Unofficial DSH plugin — long-term, cross-project memory for coding agents: an embedded project-portfolio skill plus portfolio_status / portfolio_log tools over plain markdown files the user owns. Not affiliated with DeepSeek. 非官方社区插件,与 DeepSeek 无关联。

Memory and knowledge · Skills · Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:mc856/dsh-project-portfolio
dsh-project-progress

DSH 插件:工作区共享项目进展文档(PROGRESS.md),跨会话进度感知与发布状态档案

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Jolly-J/dsh-project-progress

Find the right plugin, then get started

  1. Search by task

    Use a feature keyword or category, then sort by recent updates or GitHub stars.

  2. Explore capabilities

    Read the description, AI analysis and original README to understand what a plugin does.

  3. Check and install

    Review compatibility, dependency ranges and instructions, then copy the available install command.

Questions about DSH Hub

What is DSH Hub?

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.

Does inclusion mean a plugin is tested and compatible?

No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.

How do I install a plugin?

Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.