dsh-composer-polish
Composer draft polisher for DeepSeek Harness: a ✨ button in the composer tool row rewrites the current draft with a zero-prefix flash call and fills the polished text straight back into the input box.
803 results
Composer draft polisher for DeepSeek Harness: a ✨ button in the composer tool row rewrites the current draft with a zero-prefix flash call and fills the polished text straight back into the input box.
PBR model preview for DeepSeek Harness: render GLB/GLTF game art with physically-based materials, textures, environment lighting, and orbit controls — fence language `pbr3d` + `pbr_render` tool.
DeepSeek Harness (DSH) web GUI plugin: a draggable liquid-glass floating card showing DeepSeek API balance, cumulative spend and token usage in the top-right corner.
Use the locally installed Claude Code CLI as a DeepSeek Harness LLM provider — no API key, native tool calls through an MCP bridge
Gives the DeepSeek Harness agent a configurable humanized whale-girl maid persona (address, self-name, speaking mode), an immersive no-plugin-meta rule, and a lightweight layered memory with query-triggered recall.
VibeOS for DeepSeek Harness: a model-driven virtual desktop that takes over the DSH web UI — AI-generated app windows, taskbar, spotlight, skins — with classic chat one toggle away. Port of benis-me/VibeOS.
We Need 模式包装(DeepSeek Harness 插件):把「we need to ...」思维链引导规范(源自 scp3500/oh-we-need,MIT)做成 DSH 原生能力 —— weneed 工具(会话内一键注入)/ /weneed 命令 / WeNeed agent-preset(新会话常驻)
Renders images, video, audio, PDF and Office documents inline in the dsh web UI through a display_file tool, streaming bytes over a signed HTTP route with range support.
Agent-native browser DevTools workbench with session-scoped controller arbitration for DeepSeek Harness
Wang Hong-inspired Notability academic handwritten PPT skill for DeepSeek Harness
Enhanced model picker for the dsh web GUI: provider-tabbed left column with model list on the right, both independently scrollable, plus cross-provider search
Curated, verified MCP server bundle for DeepSeek Harness (dsh): one install brings demo, memory, filesystem, GitHub, Playwright and remote HTTP MCP servers, with a connectivity verifier and CI checks.
ADHD behavioral coaching skill for DeepSeek Harness. Guides readers through task execution - breaks tasks into micro-steps, manages overwhelm, provides launch rituals, calibrates time estimates, and recovers from self-blame.
Global proxy for DeepSeek Harness: route agent tools, model requests and web fetches through the Windows system proxy or a custom proxy with one persistent toggle, an editable settings card, agent-visible status and a bypass-aware prompt section
DeepSeek Harness usage dashboard with model, provider, workspace, cache, balance, and CSV insights
DSH plugin: CodeBuddy supplier family for dsh-router. Provides two same-family suppliers through the router.suppliers cordis service: codebuddy (Tencent CodeBuddy, copilot.tencent.com) and codebuddy-en (WorkBuddy international, www.workbuddy.ai). Both share one implementation; only the gateway profile differs.
Cline free models provider for dsh: scan the Cline model catalog dynamically and serve the :free models through the harness LLM seam
DSH 背景壁纸主题插件:设置页「背景主题」入口,渐变预设/本地图片/剪贴板/图片链接,设置持久化到 DSH_HOME,重启自动恢复。
Unofficial industrial Endfield-inspired theme bundle for DeepSeek Harness Web.
Keyboard shortcuts for the DSH chat composer: Arrow Up/Down to cycle through historical user messages, Ctrl+C to clear input.
Floating desktop traffic lights for multiple DeepSeek Harness sessions
A Yogācāra (唯识) self-model plugin for DeepSeek Harness — eight consciousnesses, the 51 mental factors, a perfumed seed store, and a measurable self-grasping meter, rendered back to the agent as first-person state.
Cloudflare Tunnel plugin for DeepSeek Harness: expose the local web GUI through a quick / token / API tunnel behind a token-gated loopback proxy, with optional Cloudflare Access email OTP.
DeepSeek Harness plugin: direct multimodal image transfer declarations + per-session image clearing, reasoning-effort auto-fill, and progressive Figma MCP bridging (design-to-code + AI-driven design).