Plugins

Drive Jiey Browser from DeepSeek Harness over MCP: navigate, snapshot, act, read, screenshot, and manage tabs in a real Chromium profile.

Browser automation for DeepSeek Harness: Playwright-powered open/click/type/screenshot/eval tools so the agent can drive real web pages.

DeepSeek Harness plugin: web browsing tools (markdown / screenshot / pdf) powered by Cloudflare Browser Run — real headless Chrome with JS rendering, login sessions and WebMCP support.

Browser automation connector: drives the local Edge or Chrome over the DevTools Protocol with zero runtime dependencies — launch a headless throwaway-profile browser or attach to one started with --remote-debugging-port, then navigate, read page text and interactive elements, click, type, and screenshot through 11 agent tools.

AX-first macOS computer use for DeepSeek Harness: accessibility snapshots with stable refs, background input, Unicode typing, menus and apps, set-of-mark screenshots, on-device OCR and verified actions — 11 tools bridged to the macos-cu CLI.

Windows desktop control connector: through 10 agent tools it captures the screen (including occluded and partially off-screen windows), lists and focuses windows, moves, clicks, drags and scrolls the mouse, and sends key chords or arbitrary Unicode text. Built on koffi FFI: no compiler, no per-call subprocess, and its own GDI screenshot plus PNG encoder.

Native headless and visible Chromium browser automation agent for DeepSeek Harness with DOM tree extraction, screenshot capture, and built-in SSRF protection.

Windows-native computer use for DeepSeek Harness: two tools drive and read any desktop app. One batch call runs find, click, type, key, read, wait and screenshot steps in a single engine pass, so a task whose steps are known up front costs one model round trip; reading returns window text rather than an image, and input and capture prefer UI Automation patterns, Win32 messages and offscreen PrintWindow so the user's focus and pointer stay untouched.

Figma design context for the agent: reads a frame's node tree, auto-layout, paints and typography, resolves the variables it is bound to, and renders a screenshot to compare code against — plus four bundled design-to-code skills. Connect with one button against Figma's own consent page; the plugin ships its own OAuth app, refreshes tokens automatically, and never asks for or displays a token.

DSH right-sidebar plugin that compares two git commits, builds a manual-test checklist from the impact scope, and supports fail notes, screenshots, task attachments, and defect submission to Yunxiao, GitHub, GitLab, or a webhook.

Agent screen capture on macOS and Windows: one tool captures the screen and returns the image itself, so the model sees it without a second call. On Windows a whole burst runs in one engine call; on macOS a resident helper drops a region capture to 13ms and a change check to 23ms. A second tool, macOS only, reports whether Screen Recording is granted and opens the settings pane that fixes it.

Computer Use for macOS desktop applications: reads any app's accessibility tree as text with element indices, then clicks, types, pastes, scrolls, drags, selects text and sets values through it, plus screenshots read back as images. Driven by a persistent JavaScript REPL — the agent gets two tools (`js`, `js_reset`) and calls an `sky` API inside them, so state survives between calls and the tool schema stays fixed as capabilities grow. Accessibility trees come back as diffs after the first read; actions address elements by index and indices from a stale read are refused rather than misapplied; typing waits for keyboard focus and reads the field back; paste restores the clipboard. Requires macOS 14.4+, Accessibility permission (Screen Recording only for screenshots) and Node 20+; ships a prebuilt native module, so nothing compiles at install time.

Preview, debug (logs and screenshots), and publish WeChat Mini Games inside the dsh Web GUI, through the official mini game helper service

Windows computer-use plugin for AI agents with reusable window targets, UI Automation, window-bound screenshots, background-first verified input, isolated Chromium automation, MCP, CLI, and installable skills.

Isolated-environment browser verification skill for DSH plugin development: a throwaway DSH_HOME, its own `verify_<random>` profile, its own port and its own browser instance in one command, cleaned up on exit, so the profile you are actually using is never touched; ships a zero-dependency raw-CDP driver (snapshot / click / screenshot / eval) and an optional isolation audit.

Teaching board view: agent-generated self-contained HTML is projected into a sandboxed iframe as a board, annotated by hand (brush, four colours, eraser, undo), extended in place across several tool calls, and screenshotted back into the conversation as a real user message.

WeChat-style in-app screenshot button: drag a region, fine-tune with 8 resize handles, Enter to capture and Esc to cancel; auto-numbered PNGs plus a \[Shot N HH:mm] marker written into the composer. Windows-only, tested on DeepSeek Harness Desktop.

Evidence-first frontend release checks: real-browser content, accessibility, runtime, network, and baseline regression reports with screenshots.

Apple on-device Vision tools for text-only dsh models: local OCR (zh-Hans + 30 langs), image classification, face detection, document layout, and a combined describe — 100% offline, no API key, tall-screenshot slicing.

Computer use through an external USB HID device: name a target in plain language, a vision model locates it in a cropped window screenshot, and a Raspberry Pi Pico 2 moves the real mouse and types on the real keyboard. 7 tools. Windows has window listing, per-window cropping and automatic window raising; macOS needs pyobjc and has neither; Linux is unsupported.

Linux X11 computer use for DeepSeek Harness: 9 tools (screenshot, move/click/drag/scroll mouse, type, key combos) driven by a zero-dependency Python XTest helper — native-pixel coordinates, per-action verification, optional auto-observation screenshot.

Enhanced vision toolbox: 14 pixel-level vision tools (describe, ground, detect, crop, pixel-diff, OCR, long-screenshot OCR, vectorize, colors, cutout, screenshot, present, materialize, html-screenshot) driven by one OpenAI-compatible endpoint, with clean \[图片: path] bridge markers, content-safety classification and rate-limit auto-retry.

The small deterministic operations an agent needs mid-task. JSON/YAML round-trip, JSON Schema validation, text diff, JWT decode, regex testing, SQL dialect transpiling, QR codes, timezone and unit conversion, page screenshots.

Windows computer-use capability for DeepSeek Harness: screenshot → vision model → simulated mouse/keyboard input, with self-evolving knowledge base.