Tools & Capabilities

Turns markdown into a WeChat Official Account (微信公众号) draft: inlines every CSS rule onto its element because the editor discards `<style>` blocks and class names, uploads each local image through WeChat's own endpoint so it is not filtered out, and creates the draft; it never broadcasts.

Create, read, and edit PPTX, DOCX, XLSX, and PDF via the local zagens-office CLI as office_schema / office_write / office_edit / office_read tools.

Mojibake guard bundle for DSH: feature-based garbled-text detection before writes with review-then-release (an identical retry passes), plus pre-execution pwsh encoding audit (ANSI/GBK/UTF-16/Default), Windows and Chinese first.

Zero-dependency browser control: drive a real headless Edge/Chrome over CDP with 8 `pilot_*` tools (navigate/click/type/keys/eval/screenshot) plus a live draggable cockpit panel in the Web GUI - text-first snapshots for text-only models, no Playwright, no API key.

Publish an HTML document as a shareable link that opens in one tap and previews as a card in chat apps; publish, update, and export to PNG/PDF/Word.

Code knowledge graph bridge for codebase-memory-mcp: semantic symbol search (BM25), source snippets, architecture overview with Leiden communities, call/data-flow/cross-service traces, graph-augmented grep.

Desktop and browser automation bridge (36 tools): window/screen/mouse/keyboard control with PaddleOCR element perception, Chrome CDP browsing with accessibility snapshots.

Manages multiple Jenkins servers and triggers jobs from a Settings page, model tools, or a per-workspace "Run Jenkins Job" entry, with a bilingual host + browser UI.

Reuse-first capability evolution for agents: resolve existing tools and skills, discover and review exact-commit DSH plugins, install with one-time approval, verify real tool round trips, and minimally adapt partial matches instead of rebuilding from scratch.

A slim port of Headroom: compresses tool output, cuts up to 20% of context, without affecting the model's context cache or agent performance.

Indexes workspace symbols with Tree-sitter and provides lexical or optional embedding-assisted code search.

HTTP/API debugging toolset: full-control HTTP requests (method/headers/body/auth), curl command parsing and one-step execution, in-session request history with side-by-side response comparison, pagination-aware Link headers, and DeepSeek-branded UI cards (optional dsh-http-tools-ui).

Connect dsh to a local Obsidian vault: search, read, write, move, and trash notes through `obsidian_*` tools.

Plugin value auditor: pre-install review (source scan + LLM judge) and post-install audit of installed bundles, with model-switch re-audit reminders.

Ecommerce operator workbench: CSV batch preview with marketplace column adapters, reproducible profit/six-dimension scoring, public product-page snapshots, Chinese skills, and a replaceable store-policy KB.

SearXNG-backed web_search provider for the web seam: free, self-hosted, key-less metasearch through your own instance's JSON API, with a bundled loopback-only docker-compose example.

Optimize a raw instruction into a professional four-section prompt (Role / Task / Context / Format) through the harness llm service, with a composer button, one-click undo, a prompt_optimize tool, and an auto-optimize hook.

Keep the built-in web_search tool without an official DeepSeek API key: disable web-search-deepseek and use Tavily keyless by default.

A `search` tool that learns to pick between fast and thorough search strategies using a contextual bandit (Thompson sampling), improving from real usage instead of a fixed heuristic.

Multi-workspace sandbox: grants file-write access to every registered workspace automatically — add a workspace, write to it immediately, no config or escalation needed.

PubMed deep-research toolset: literature search, author investigation, same-name disambiguation, institution statistics and mentor-student matching.

Turn any SVG logo into a motion video inside DSH: an `animate_svg` tool renders a transparent 30fps assembly animation (parts fly in, or the whole mark settles) and synthesizes an MP4 with ffmpeg.

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.

CDP bridge to an already-running Chrome/Edge for DSH: screenshots, pixel assertions, DOM/CSS checks, and page JS evaluation over HTTP + WebSocket, with zero child processes, zero npm dependencies, and zero per-use approval.