dsh-resume-briefA DeepSeek Harness skill: write a one-page handover before continuing a project.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Tinzlu/dsh-resume-briefDiscover The Best DSH plugins
DeepSeek Harness plugins — Page 977
27480results
Search community plugins for DeepSeek Harness. Compare capabilities, installation instructions and compatibility to find extensions for your AI workflow.
dsh-resume-budgetResume input budget for DeepSeek Harness: before a restored session re-sends its whole history, check the projection and compact first when it is over the ceiling.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xingzoudefengye/dsh-resume-budgetdsh-resume-on-restartDSH 插件：检测 DSH 服务重启后自动唤醒主 agent，投递提示消息让中断的工作自动恢复。仅依赖 cordis ctx 服务，兼容 DSH Desktop 打包环境。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:nickkkkkk123123/dsh-resume-on-restartdsh-resume-pluginResume Claude Code and Codex sessions as inert handoff context in DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Demogorgon314/dsh-resume-plugindsh-resume-screeningResume screening plugin for DeepSeek Harness (HR): ingest up to 100k Word/PDF/Excel resumes into one searchable library with skills / coarse categories / ingest time, auto-ingest & de-dupe new resumes, then screen by plain-language criteria — rule pre-filter in the DB plus LLM fine-judge on the shortlisted few, CSV export. 简历筛选插件:批量收简历建档(技能/粗分类/入库时间),大白话下指令,库内规则粗筛+LLM精判少数入围者,自动入库去重、可导出、可追溯。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wangzhanchao883/dsh-resume-screeningdsh-resume-turnDSH 断点续接插件：模型回复因网络中断/超时半途失败时，自动把已生成的部分输出带进下一轮，让模型从中断处继续，而不是从零全量重跑。DSH plugin: on a mid-stream network failure, auto-resume the turn from its partial output instead of restarting from scratch.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Harris-Logic/dsh-resume-turndsh-retcon
★ 0dsh-retcon写判断时检查「什么情况下它是错的」——没写就不许过。一份封存格式 + 一把尺子；DSH 插件是可选的自动手，不装也能照格式手写。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:QiDouZu/dsh-retcondsh-retention-settlement-proofOffline body-free retention settlement evidence for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:dongsheng123132/dsh-retention-settlement-proofdsh-retro
★ 0dsh-retroDeepSeek Harness 经验复盘插件：采集、提炼、人工审阅、经验沉淀与博客联动。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:StellatoL/retrodsh-retro
★ 0dsh-retro复盘方法
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-retrodsh-retro-macRetro Macintosh — a classic Mac OS 8/9 Platinum skin for the DeepSeek Harness Web GUI: platinum greys, Chicago/Geneva/Monaco fonts, pinstripe wallpaper, beveled controls, hard shadows. 复古麦金塔皮肤：铂金灰界面、Chicago 字体、条纹壁纸、浮雕控件。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Leyan0365/dsh-retro-macdsh-retry-guardObserve repeated identical tool failures and optionally pause before DSH's next model step.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:sjh9714/dsh-retry-guarddsh-retry-pluginAutomatically retry the current DSH Web session when the AI access fails, so the conversation is never interrupted.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jedzqer/dsh-retry-plugindsh-retry-policy-settingsSettings UI for DeepSeek Harness (DSH) to edit each model provider's request retryPolicy — mode (normal/always), maxRetries, retryableCodes and exponential-backoff parameters — written to settings.yaml and applied by dsh-llm-retry. 模型重试策略设置：在设置面板中可视化编辑各模型提供方的 API 请求失败重试策略。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:guanosine-diphosphate/dsh-retry-policy-settingsdsh-return-frontReturn DSH to the foreground when a real-device control turn ends, with a settings-page toggle.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zxyan99/dsh-return-frontdsh-return-gift回礼预算
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-return-giftdsh-revbayes-forgeDeepSeek Harness (DSH) plugin that generates, statically checks, and dry-run validates RevBayes scripts, and hosts family model packs.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ZengZichao/dsh-revbayes-forge#11e1bd7f707d447ffb9dbedd3a283f7f3f78956e&path:packages/coredsh-revbayes-forge-pack-biogeoDevelopment fixture package for the biogeo model pack bundled inside dsh-revbayes-forge.
dsh-revbayes-forge-pack-chromosomeDevelopment fixture package for the chromosome model pack bundled inside dsh-revbayes-forge.
dsh-revbayes-forge-pack-coalescent-demographyDevelopment fixture package for the coalescent-demography model pack bundled inside dsh-revbayes-forge.
dsh-revbayes-forge-pack-continuous-traitsDevelopment fixture package for the continuous-traits model pack bundled inside dsh-revbayes-forge.
dsh-revbayes-forge-pack-dating-clockDevelopment fixture package for the dating model pack bundled inside dsh-revbayes-forge.
dsh-revbayes-forge-pack-diversificationDevelopment fixture package for the diversification model pack bundled inside dsh-revbayes-forge.
dsh-revbayes-forge-pack-fbdDevelopment fixture package for the fbd model pack bundled inside dsh-revbayes-forge.
Find the right plugin, then get started
Search by task
Use a feature keyword or category, then sort by recent updates or GitHub stars.
Explore capabilities
Read the description, AI analysis and original README to understand what a plugin does.
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.