@lsq64737/dsh-workbench-layout
DSH-styled three-column workspace with file editing, Markdown preview, Git controls, terminals, and native conversation
55 results
DSH-styled three-column workspace with file editing, Markdown preview, Git controls, terminals, and native conversation
驯兽师(驯兽场):把人类语言翻译给智能体的 DSH 插件——注入「开智」内核(第一性原理 + 需求剖析 + 极简沟通 + 最少 token),左上角悬浮萌宠,设置页可配内核与开关。
质感书房:DeepSeek Harness Web 的 3D 书房皮肤与门外体素世界。Cozy Study skin for DSH web.
Kimi (Moonshot AI) chat-completions adapter for the DeepSeek Harness LLM seam — three routes: kimi-code (Kimi Code subscription), kimi-cn, kimi-global
Enforced pain-point-check guard plugin for DeepSeek Harness: after two non-converged experiments on one problem it injects the three questions, denies non-investigative tool calls until they are answered in the reply text, and blocks same-direction retries
Bisect bug root causes in three modes: code / boundary / commit (git bisect run)
Extensible animated theme library for DeepSeek Harness
DSH Web 三栏工作台:对话流只保留 AI 输出(工具调用/思考移入右侧面板),左侧工作区文件树带 git 状态徽标。Three-column workbench for the DSH web GUI: clean conversation flow, workspace file tree with git badges, and a live tool-call/think panel.
Rick and Morty for the dsh web GUI: three-look skin (C-137 portal green / lab coat / Meeseeks blue) plus a desktop-pet companion with six characters, bilingual lines, agent-driven moods, combo petting, and a progression panel
DSH plugin: view OBJ/STL/STEP models in the web UI and translate them into a standardized, LLM-readable JSON
DeepSeek Harness dynamic plugin: renders three clickable, editable follow-up question suggestions under every agent answer
Better Harness evidence lanes — session, project readiness, and agent assets — as one DeepSeek Harness bundle of three routable skills.
dsh的跨会话记忆管理插件,让agent记住每一个任务的内容和进度。包含命题图、三层内存漏斗、混合向量 + 词法检索(RRF)以及浏览器端审查面板。 | Cross-session memory management for DSH — lets the agent remember the content and progress of every task while executing. Includes a proposition graph, three-layer memory funnel, hybrid vector + lexical retrieval (RRF), and a browser-side review panel.
Codekin creature collection and match-three RPG for DeepSeek Harness Web
Reflect2Evolve memory plugin: layered L1/L2/L3 memory, reflection-weighted value backprop, cross-task policy induction, skill crystallization, and three-tier retrieval for OpenClaw, Hermes Agent, and DeepSeek Harness.
Plugin lifecycle guardian for DeepSeek Harness. Read-only diagnostics (plugin_doctor) with three-tier confidence, plus installed-profile conflict scanning (plugin_profile_scan).
Multi-agent mathematical problem-solving & verification frameworks for DeepSeek Harness — THREE agent presets in one install: vibe-math-v2 (probability-driven: qs.json + Propos knowledge base + explorer→solver→review/debate verdict), vibe-math-v3 (THIRD-g
DSH host bundle plugin: builds a two-level (category + skill) recall index over all local SKILL.md files and routes a natural-language intent to the best-matching skills, with three-state (hit / low-confidence / miss) fallback.
Model selection as a three-level cascading menu (Provider -> Series -> Full model) plus thinking-intensity (reasoning effort) selection for the composer model seat.
DeepSeek official 3D Three.js particle whale animation for DeepSeek Harness / DSH Desktop
Three hand-tuned skins for DeepSeek Harness (DSH): Aurora (deep navy + electric cyan + warm coral), Paper (cool white + deep teal, daytime reading), and Hologram (near-black + lime-cyan, terminal vibes). Pure --dsw-alias-* token system, no core patches, persisted in localStorage.
A compact DSH model and reasoning quick-switcher showing the last three choices.
OpenBook RSS Reader as a DeepSeek Harness UI plugin: RSS sync, three-column reading view, notes/highlights, agent tools and chat commands
Three Ark presets (ark/ark-code/ark-cordis) and a side-channel CLI for DeepSeek Harness: frozen minimal wire surface with on-demand instructions, skills, tools, and MCP.