dsh-prompt-polisherComposer prompt-polisher button plugin for DeepSeek Harness (dsh)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yuluo554/dsh-prompt-polisherDiscover The Best DSH plugins
27094results
Search community plugins for DeepSeek Harness. Compare capabilities, installation instructions and compatibility to find extensions for your AI workflow.
dsh-prompt-polisherComposer prompt-polisher button plugin for DeepSeek Harness (dsh)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yuluo554/dsh-prompt-polisherdsh-prompt-prefillDeepSeek Harness 插件:Agent 回答结束后在输入框预填一条灰色的下一句建议,按 Tab 或 → 采纳;输入框为空时按 ↑ 填入上一次发送的内容。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Tleon-H/dsh-prompt-prefilldsh-prompt-presets提示词模板库 + 任务完成提醒 (prompt templates + task completion alerts) for DeepSeek Harness Web GUI — static Cordis plugin bundle (host + client halves)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Mryuanliu/dsh-prompt-presetsdsh-prompt-presetsReusable prompt presets for DeepSeek Harness: manage a preset library in Settings and inject any preset at the start of the composer draft with one click. / DeepSeek Harness 提示词预设库:设置页管理、对话框一键注入。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zhangdong456/dsh-prompt-presetsdsh-prompt-recallCodex-style up/down input-history recall for the DeepSeek Harness web GUI
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:liguanyu/dsh_PromptRecalldsh-prompt-refineDSH 提示词优化插件:在发送前拦截用户提示词,结合上下文给出 3 条改进建议
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:sojo-negai/dsh-prompt-refinedsh-prompt-reforgeReforge a rough draft into a precise prompt inside the DSH composer, with one-click revert.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Cloud017/dsh-prompt-reforgedsh-prompt-settingDeepSeek Harness 默认 System Prompt 管理插件:在 Web GUI「设置」里浏览、检索并覆盖最终装配进每轮会话的系统提示词。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zangxx66/dsh-prompt-setting#f73e7c609b6ec47ec7044ec4c8de9814d060d635&path:packages/dsh-prompt-settingdsh-prompt-starDSH plugin: a ⭐ button beside the conversation input that reads your draft + the project's doc files and turns them into a fuller, more efficient prompt, filling the input directly (Ctrl/Cmd+Z to undo).
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:MncStudio/dsh-prompt-star#82712301f0d0c1f65d75db3a36bd397d4eb74e6c&path:packages/extensions/prompt-stardsh-prompt-studio提示词工作台:优化、多轮迭代、多模型对比测试
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:CECILIALOVE0616/dsh-prompt-studiodsh-prompt-studioPrompt & Agent Preset Evolution Studio for DeepSeek Harness: Git-style versioning, diff timeline, golden test bench, and one-click regression evaluation. · DSH 提示词与预设演进工作台:Git 式版本化管理、时光机 Diff、金标测试集与一键回归评测。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ElioChen240/dsh-prompt-studiodsh-prompt-studioCustom initial system prompt, reusable chat modes and chat-only injection suppression for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:irislilymoon/dsh-prompt-studiodsh-prompt-studioPrompt Studio plugin for DeepSeek Harness: compose runtime prompts, overrides, and request-local synthetic turns in one live editor
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:PrismScopes/dsh-prompt-studio-compatdsh-prompt-studio提示词优化工坊:多风格一键优化、发送时自动优化,风格可在设置页自由增删改。Prompt rewriting studio for DeepSeek Harness.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zywnb-2/dsh-prompt-studiodsh-prompt-system提示词优化插件:模型选择左侧「优化提示词」按钮,结合当前对话与工作区文件,把草稿优化为「目标/实现措施/约束」三段式精准提示词,支持一键撤销
dsh-prompt-translationPrompt, reasoning and response translation for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:EPCN-fla/dsh-prompt-translationdsh-prompt-tunerComposer prompt tuner for the DSH Web GUI: rewrites the input draft through a model you choose (by default the session's own), with the model, reasoning effort, rewrite style and optimization prompt configured on a settings page
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lzyyzznl/dsh-prompt-tunerdsh-prompt-vcsEvery change to your agent's instructions is recorded with a diff, and any change can be undone.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hj01857655/dsh-plugins#5a7f8533f4dcd4f85ec3ebd7e9fa0a071445bf65&path:packages/dsh-prompt-vcsdsh-prompt-vcsEvery change to your agent's instructions is recorded with a diff, and any change can be undone.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hj01857655/dsh-prompt-vcsdsh-prompt-wispPrompt Wisp 提示词精灵 — 在聊天输入区发送按钮旁加一枚「优化提示词」按钮,一键把草稿交给宿主已配置的模型改写成清晰、结构化、可直接执行的提示词。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jr-create/dsh-prompt-wispdsh-prompt-workbenchPrompt rewrite workbench for DeepSeek Harness — four rewrite modes, cancellable streaming output, and a token-level before/after diff. 提示词重写工作台。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:fufuyin/dsh-prompt-workbenchdsh-prompt-zh把 DSH 内置的系统提示词段落与 MCP 指导说明本地化为简体中文(注入点 system-prompt/assemble)。工具的 description 与参数 schema 有意保持英文。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:KouzakiUmi/dsh-prompt-zhdsh-proofEvidence-Driven Completion Proof & Regression Attribution for DeepSeek Harness. Turns "I'm done" from a self-report into a recomputable evidence chain, and turns "I fixed it but broke something else" from a post-mortem into in-flight attribution.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:beijingwahw/dsh-proofdsh-property-tax物业费估算
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-property-taxUse 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.