@axiaohungry/dsh-llm-workbuddy
通过 WorkBuddy API Key 或 WorkBuddy 登录令牌为 DeepSeek Harness 接入 WorkBuddy 模型
52 results
通过 WorkBuddy API Key 或 WorkBuddy 登录令牌为 DeepSeek Harness 接入 WorkBuddy 模型
Multi-provider Web Search & Fetch for DeepSeek Harness — 8 deeply adapted providers, SearchHints, resilient fallback, and native X / Xiaohongshu retrieval
中文开箱即用预设全家桶:小红书笔记助手 / 中文文案润色 / 日报周报生成器,一键应用到官方 Agent presets / Out-of-the-box Chinese agent presets: Xiaohongshu notes, copy polishing, daily/weekly reports.
Qingxiao (Wuthering Waves) themed skin with ice-blue/jade/moon-white palette, sword-light motes and user-swappable background for the dsh web GUI
DeepSeek Harness-native publicity toolkit: turn any long-form source into a source-grounded, platform-native promotion matrix.
为 DSH Web 添加 Xiaomi MiMo TTS 语音朗读、浏览器本地语音兜底和可选 UI 音效。
Oh My Pi bash runtime ported as a deepseek-harness tool plugin: persistent shell session, output minimizer, managed background jobs, command interception
RedFox community skills for DeepSeek Harness: 100+ social-media data skills (Douyin, Xiaohongshu, Kuaishou, Bilibili, WeChat, Weibo, YouTube, TikTok and more), mirrored one-way from the redfox-community hub repo.
Xiaomi MiMo search + multimodal tools for DSH agents (mimo_search/vision/audio/video/asr/tts) plus the merged voice UI: 🔊 read-aloud, in-conversation speech strips, and a configurable voice map (docs/adr/0001).
将 MiMo 桌面 App 包含的模型自动接入 DeepSeek Harness,在 DSH 对话窗口里零配置使用。复用客户端已登录的额度,无需单独申请 API Key,也无需常驻程序。Bring the models included in the MiMo desktop App into DeepSeek Harness automatically, with zero configuration.
Lightweight agent workflow for DeepSeek Harness: one workflow = one JSON (React Flow native) with prompts inline, compiled into a dispatch plan the model executes itself. No execution engine; optional per-workflow run state kept by the model in a YAML file.
夕小瑶 × DeepSeek Harness 黑鲸实验室主题皮肤
豆包式语音对话客户端插件:麦克风按钮→语音转文字发送→回复自动朗读(支持 Edge TTS / MiMo TTS / 自定义 TTS)。
图片识别插件:自动判断当前模型是否具备视觉能力,有则用当前模型并按插件预设提示词分析,无则调用插件配置的视觉模型。文本模型可直接在对话框粘贴/上传/拖拽图片,发送时自动写入 DSH 附件存储(永久),消息区渲染缩略图,模型自动调用 image_vision / ocr / ground / crop 系列工具识别与精读;模型选择器保持简洁。
Customizable theme plugin for DeepSeek Harness web UI. Ships with a Xiao-style jade palette by default; accent color, mascot badge text, injected voice and frosted background are all configurable. Built with TypeScript and pnpm.
Mi Home (米家) control for DeepSeek Harness agents — list homes/devices, read props, and control devices behind a human approval gate.
DeepSeek Harness bundle: plan-travel-guide skill with map/OTA/ticketing catalog sweep, Xiaohongshu/Douyin/Weibo/Bilibili discovery, POI verification, and day-by-day route clustering.
Media downloader for DeepSeek Harness. Detect and download video/audio from Bilibili, YouTube, Douyin, Xiaohongshu.
AI 生图 (image generation) plugin for the dsh web GUI: text-to-image and image-to-image through a configurable OpenAI-compatible endpoint, with multi-provider support, model discovery, and agent tool registration. 与 @xiaoyuink/dsh-image-vision 同系列的图像插件。
VS Code / IDEA-style run control for the DeepSeek Harness web GUI: run buttons, task run configurations (LLM prompt / background command), configuration CRUD, and an LLM-exposed configuration tool with an on-demand usage skill
Project-scoped AI memory: records pitfalls and user habits per project, injects them into future conversations
Host-level vision bridge for text-only models: analyze_image tool (Ollama local / Xiaomi MiMo cloud / any OpenAI-compatible endpoint) returning structured evidence.
WeChat Official Account content studio for DeepSeek Harness: anti-homogenization writing methodology, blessing-image visual baseline, gpt-image cover pipeline with OCR acceptance, interaction rules, and the measured xiaolvshu (newspic) draft web API.
AI 编译纯文本小说工作台 for the dsh web GUI: import a novel outline (docx/text), plan volumes & chapters with LLM, generate chapter by chapter (3000-4000 chars each), auto AI review & book audit, and export the full book as Markdown/TXT into your chosen output folder.