@deepseek-ai/dsh-llm-deepseek-vision
Vision-augmented DeepSeek adapter plugin for DeepSeek Harness: a vision-capable model describes image input, then a text-only DeepSeek model reasons over the description
160 results
Vision-augmented DeepSeek adapter plugin for DeepSeek Harness: a vision-capable model describes image input, then a text-only DeepSeek model reasons over the description
Brave Search API provider for DeepSeek Harness web capability seam (ctx.web)
3D printing & additive manufacturing capabilities for DeepSeek Harness: parametric STL generation, calibration G-code, STL/G-code analysis and toolpath rendering as model tools, plus slicing / modeling / analysis / diagnosis knowledge skills.
DSH plugin for DeepSeek Harness: 25 model tools across PubMed, Europe PMC, OpenAlex, PubTator3 & Semantic Scholar — cross-source unified search, article metadata, full text, citations, MeSH & ID tools, citation counts & recommendations — plus a personal literature knowledge graph with an AI-powered PubTator3 concept layer (normalized entities, curated relations, evidence-backed edges). Core PubMed capabilities originate from @cyanheads/pubmed-mcp-server; the knowledge-graph, concept and unified-search layers are original extensions.
Expose DeepSeek Harness agent capabilities as an MCP server, so an external MCP client (e.g. Hermes) can drive Harness to execute coding tasks. Hermes = brain, Harness = arms.
Inspect and manage the skills, tools, and MCP capabilities available to a DeepSeek Harness agent session.
DSH Skill MCP Manager for DeepSeek Harness Desktop: manage MCP servers and Skills from Settings, publish compact capability descriptions, and progressively load each MCP server's tools only into the requesting session. Dual-face dsh plugin, no DSH source changes.
Model capability radar for the DeepSeek Harness web GUI: a Settings tab that charts codexradar crowd-benchmark scores per model tier — task-composition bars, 7-day IQ trend, efficiency badges
Desktop & web UI automation for DSH: full-screen capture, Windows OCR, mouse click/drag, typing, key press, window activate, plus battle-tested Paint drawing capability
K12 capability substrate for DeepSeek Harness: 143 objectively-decidable capability anchors and 6,091 list items extracted from China's MOE 2022 curriculum standards, with local-only learner profiles
DSH plugin development boundary skill: platform capability boundaries (Client↔Host channels, filesystem limits, dynamic vs bundle lifecycle, install/debug rules)
Render strict JSON ```echarts fences as interactive Apache ECharts charts in DSH Web.
让 AI 助手驱动 STUDIO NEUTRINO(免费日语 AI 歌声合成引擎)唱歌:给歌词和旋律,自动生成角色演唱的 WAV。需自备免费的 NEUTRINO 引擎和声库,插件内置官方下载引导。
V0 capability-disclosure scanner for DeepSeek Harness (DSH) cordis plugins: reports which sensitive services (credentials/shell/approval/sandbox/fs/tools...) a plugin declares or references before you trust it.
Ollama-backed search provider for the DeepSeek Harness web capability seam (ctx.web): adapts Ollama /api/web_search into dsh web_search tool.
Project stack detection and capability recommendations for DeepSeek Harness.
Windows computer-use capability for DeepSeek Harness: screenshot → vision model → simulated mouse/keyboard input, with self-evolving knowledge base.
A pixel-art Plugin librarian for dynamic capability sedimentation in DeepSeek Harness Web UI.
DeepSeek Harness Doctor: read-only DSH runtime capability diagnostics for tools, models, skills, workspaces, sessions, plugins, and MCP troubleshooting
DeepSeek Harness plugin that enhances custom provider setup by auto-discovering models and auto-populating contextWindow, maxTokens, vision, and reasoning capabilities from models.dev
OAuth2-capable IMAP email reader for DeepSeek Harness: list/read/search mail for accounts where password auth is disabled (Outlook post-2024), with automatic token refresh, app-password Gmail via optional proxy, and ol_email_* tools that coexist with the market dsh-email plugin.
Dify agent and knowledge-base capability for the DeepSeek Harness — the ctx.dify Service Definition, an HTTP Service Provider, and the model-facing dify_chat and dify_retrieve tools
云 Well-Architected 六支柱评审框架:可靠性(用户经验目标/SLO/冗余/水平扩展/可观测性/优雅降级/恢复测试/无指责复盘)、成本优化、运维卓越、性能优化、安全、可持续性——设计原则+建议驱动架构评估与改进。受 google/skills(18.5k★ Apache-2.0)启发。
Multi-platform messaging plugin for DeepSeek Harness — Feishu/Telegram with capability degradation