@ddtcorex/dsh-maestro-diagram
Maestro diagram studio: mermaid_verify + mermaid_drift tools (hybrid with diagram-studio skill)
926 results
Maestro diagram studio: mermaid_verify + mermaid_drift tools (hybrid with diagram-studio skill)
Unofficial community plugin: per-session Engram memory for DeepSeek Harness — spawns an engram MCP child per agent session rooted at the session workspace, registers mem_* tools per agent scope, and injects the Memory Protocol as a system-prompt section.
Freeze a working sequence into a hosted production line. Turn a sequence of tool calls that already works into a named pipeline that runs on our servers on a schedule, with a receipt per run — plus recurring watch tasks that notify you only when a result actually changes.
OpenRouter image, video, and speech generation as dsh tools, shipped as an out-of-tree profile bundle
DSH plugin that registers a fetch_url tool: fetch any URL (direct for domestic targets, HTTP CONNECT proxy for overseas) and return a bounded text/JSON summary. Reuses the battle-tested Node TLS logic from tools/fetch-url.cjs, exposed as a model-callable tool.
DSH Desktop Operator: safe Windows Computer Use, desktop automation, UI Automation, and MCP tools for DeepSeek Harness
聊天输入框图片工具(自研):上传图片(≤10MB 防烧 token) + 自定义区域截图(Electron desktopCapturer),注入 DSH 草稿图片轨。零外部依赖。
DeepSeek Harness Doctor: read-only DSH runtime capability diagnostics for tools, models, skills, workspaces, sessions, plugins, and MCP troubleshooting
Semantic long-term memory for DeepSeek Harness: embedding-based retrieval over a persistent cross-session memory store, with model-facing tools, proactive per-question recall, automatic conversation summarization, and auto-selected embedding provider (apiKey present → API, otherwise local).
Safety-gated SSH tools for DeepSeek Harness and Codex laboratory operations
DeepSeek Harness frontend runtime verification: detect, run, preview, interact, diff, and prove local web apps.
Hierarchical long-form writing for DeepSeek Harness — WriteHERE as an agent driver, not extra ReAct tools.
AI turns repeated dev commands, prompts, and instructions into one-click DeepSeek Harness actions.
DeepSeek Harness guardrail that limits how many files an AI coding agent can edit per turn
DeepSee: DeepSeek Harness vision, multi-model routing, and Gemini visual self-checks before delivery
MATLAB + ModelSim + Vivado full-flow tools for digital communication IC design tasks — a DeepSeek Harness plugin bundle.
Cache-prefix stabilization and evidence-based cache metrics for DeepSeek Harness
Windows access tools for WSL agents: win_ls/win_read/win_write/win_run/win_open/win_path/win_drives.
GitHub/Git deployment plugin for DeepSeek Harness (DSH): a Git settings section after model/plugin/agent preset, global GitHub account config, visual repository management (init/create/commit/push/status/log), branch create/switch, commit graph, and 9 git_* model tools for agents.
基于抖音官方资料的 DeepSeek Harness 自媒体创作与运营插件
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.
Remote multi-server GPU status board for DeepSeek Harness Web: read-only nvidia-smi over SSH with ControlMaster-muxed connections, a host-side cached snapshot, per-server selection, and gpu_overview / gpu_refresh agent tools.
DeepSeek Harness (DSH) plugin that delegates coding tasks to the Claude Code and Codex agent CLIs and streams the whole run live — autonomous control, multi-account, automatic install, git worktrees, and any Anthropic-compatible endpoint.
DSH plugin: /tabs popupSelect to list and select browser tabs via chrome-devtools-mcp, writing the chosen URL into the composer.