Plugins

Drive a local ffmpeg as six structured tools: probe a file's streams, transcode or trim it, pull evenly-spaced frames or the audio track, and compress video to a byte budget with two-pass encoding.

Read, build and take apart EPUB 3 books with no external dependency — the ZIP reader/writer and the XML scanner are both built in. Inspect metadata, reading order and TOC for structural problems, assemble a book from chapters, or split one back into per-chapter HTML.

Per-turn development progress memory: completed turns are classified into date-indexed Markdown files under doc/progress/ with a maintained INDEX.md, system-level bugs are kept in a cross-project SYSTEM_MEMORY.md and re-injected on error keywords, and a progress_read tool loads full documents on demand.

Watches the foreground browser window, recognizes video courses, classifies them by subject, fetches Bilibili metadata/danmaku/comments, and generates Markdown + Mermaid knowledge maps and Word study manuals.

Aqua glassmorphism theme for the DSH Web UI, adapted to DSH v0.2.x and desktop v0.22.3+: the header, sidebar, composer, stats line and trajectory view become frosted glass panes over a live WebGL fluid board or an image/video wallpaper, with mica and compatibility layouts, adjustable blur, frost, hue and brightness, marine decorations (particle whale, fish, mesh, cursor glow), a one-click reset-to-defaults button, and a master switch whose off state restores the stock UI exactly; adapted from WYH66666666's original (0.1.x) and du-u-uck's 0.1.1-rc.2 port.

Shows what each assistant turn cost under every reply, priced from the token usage of that turn at the official peak and off-peak CNY rates, together with the account and bonus balances; when a turn cannot be priced it states the reason instead of guessing.

Use subscription accounts as DeepSeek Harness LLM providers — Kimi Code (OAuth device flow), Grok / X Premium (OIDC + PKCE), Google Antigravity (Google OAuth + Cloud Code Assist) and GLM / BigModel (ZCode's browser sign-in) — with per-model visibility, dr

Ships a skill for verifying a change with the cheapest check that still yields a definite answer: an L0-L3 cost ladder from static checks to a single suite, condition polling with a timeout instead of fixed sleeps, assertions that can actually fail, and durations that are measured rather than remembered. The package also carries the two zero-dependency Node tools the skill calls - wait-until.mjs (poll a command, a file, or a port until it is ready) and measure-runtime.mjs (wall-clock timing for any command, plus a segmented timer for library use).

Bundles the official Scrapling agent skill into a DeepSeek Harness profile: anti-bot bypass, stealth browsing, the spiders framework, adaptive parsing and JavaScript rendering, discovered through the host skill catalog.

Buffers consecutive short messages from the composer and merges them into one turn: no model wake-up until the user stops for a configurable silence window; long messages and attachments bypass the buffer.

WeChat-style light theme with a dark icon rail, grey conversation list and green chat bubbles.

Prices tokens with the official model price table, keeps the per-session and global running cost beside the composer context meter, mirrors your DeepSeek account balance in the sidebar, blocks a turn once this period passes your own global ceiling (clamped to that balance) or a per-session ceiling (each session sets its own, independently), and resets the billing baseline per session or globally — the two are independent, so resetting one never resets the other — so the period goes back to zero while history only rolls into the lifetime total.

DeepSeek Harness bridge to a relay-hub station: TOIP dynamic-password onboarding, LAN discovery, and per-plugin log accounting

Delegates self-contained coding subtasks to the local Claude Code subscription through the official Agent SDK and returns the result to the host session. Nineteen per-call parameters control model, thinking effort, permission mode, allowed tools, turn count and budget cap; background jobs return a jobId immediately and stream incremental output; the result carries a session handle that can be passed back as resume to continue the same conversation; commands expected to run past ~20 seconds go through the built-in mcp__dsh__shell channel, which streams output line by line without consuming model context; a Claude Code monitor panel in the session lists jobs, renders the structured process, shows live output blocks and cancels a run; the delegation procedure ships as a runtime-registered skill, so installing the plugin installs the skill.

Unofficial Gemini Cloud Code Assist OAuth integration with isolated account storage; carries account-ban risk.

Suggests the next user reply in an empty composer after the assistant finishes, using the session model and rolling context summaries, with Tab to accept.

Ambient-audio player with a local sound library, sequential, shuffle, single-loop and intermittent playback, a sleep timer, and optional AI-assisted audio downloads.

DSH 工具箱（装配包）：一个插件装好五个功能 —— 删除对话 / 重新生成（从这里重来）/ 队友命令（/teammate）/ 跨会话提醒 / 首轮结束自动命名；插件页呈现为 1 张卡 + 5 行组件，每行独立开关。 | DSH toolbox (assembly bundle): one card, five independently switchable features — delete conversation, rewind from here, teammate commands, cros

个人解决经验记忆：保存问题、做法、来源和适用条件，下次相似任务可检索复用，并支持纠正与删除。搭配 dsh-bubble 提问、dsh-look 提供现场上下文。

session_health for DeepSeek Harness — health intelligence (outcome classification, tool-health signals, prompt heuristics, context pressure, A–F grade) computed in-process from the session store, plus a standalone CLI over the same engine.

DSH 循环护栏：① assistant-stream 字符重复检测（可 abort）；①b 低多样性高重复（末窗 + 滑窗两支，抓「带噪声的交替空转」与「正常推理里夹一段空转」——① 线的精确匹配结构上抓不到它们）；①c ① 线命中时注入「停止」类词 + 预注册观测（注入是温和动作，先于掐断）；② 行动层「无进展」停滞检测；②b 同参工具调用连击（按**动作参数**判定，忽略 description 之类自注）；③ 反复卡住达阈值 ⇒ agent.cancel() 真切断；⑤ 零正文 turn（只有思考

24私助（24PA）: Feishu-backed personal assistant as a dsh workspace bundle.

Remote operations for the DSH Web app: manages SSH servers, collects hardware and process metrics, inspects logs with a read-only AI pass, and deploys a Git repo over SSH using git pull --ff-only plus a health check. Credentials are AES-256-GCM encrypted. Linux and macOS hosts; no Windows support.

It shows the number of confirmed loaded skills in the conversation header. Click **技能** (Skills) to open the right sidebar and check whether each skill's full main body remains in the current main assistant context, along with its recorded versions and sources.