Plugins
Browse, filter, and install DeepSeek-Harness plugins.
1640 plugins found
dsh-lark-cli-skills
stevenjj33/dsh-lark-cli-skills
Agent skills for the Lark/Feishu CLI: exports the complete skill tree embedded in the lark-cli binary — all 25 skills, nothing excluded — and registers them with the DeepSeek Harness skill registry so the agent can read them on demand. Covers Messenger, docs, sheets, base, calendar, drive, task, wiki, approval, mail, slides, meetings, minutes and more. Every cross-skill link resolves as shipped upstream. Requires lark-cli to be installed.
dsh-docmate
miaojinqwq/dsh-docmate
Immersive reading desk: md / docx / pdf render in the centre pane, and the right column is one ordinary Harness session per document that has already been fed the whole text, the research memory and the existing highlights. Select a sentence to ask about it; scanned PDFs and images have no text layer, so a marquee drag captures that region and sends it to a vision model under a turn-scoped runtime brake (max 2 steps, per-step output cap, every tool call denied before dispatch, 45 s cancel). Highlights are anchored as character offsets and painted with the CSS Custom Highlight API, so they survive reloads. Also KaTeX math, outline, in-document search and a draggable three-column layout. Zero runtime dependencies: pdf.js and KaTeX are vendored.
dsh-agnes-create
zxygithub/dsh-agnes-create
Sidebar panel for Agnes image and video generation. Images: plain text-to-image, or image-to-image and multi-image composition from up to eight reference images chosen from local files or from results already in the panel, at 1K-4K across eight aspect ratios, with six one-click style presets. Video: agnes-video-2.5-flash at 720p, 4-12 seconds, in three modes that the panel picks for you - plain text, keyframe (first frame, last frame, or both) and reference (up to five images) - plus an optional seed; the task is submitted to the host process, so switching panels, reloading the page and restarting the app all resume it instead of losing the job. The prompt is written into each generated PNG or JPEG and shown again when you hover the result, where one click copies it. Browse the output directory (images and videos on separate tabs) with automatic refresh, copy a path, reveal a file in Finder, or download it; the last 24 generations persist across restarts. Images and videos can also be produced from the chat itself through the agnes_image, agnes_video and agnes_video_status tools. Both the image and the video model can be switched from the panel, with a connection test, and local reference or keyframe images are sent as base64 data URIs so no public image host is needed. Needs an Agnes AI API key saved in a local file (default ~/.agnes-key.txt).
dsh-rst
jingyu-er/dsh-rst
Restart DSH with one /rst command: an external launcher shuts down the current process and starts a new one, then a receipt is written back to the session that issued the restart. Windows 10/11 only (relies on tasklist/taskkill).
dsh-optimized-tools
dragonhorizon-xtihc/dsh-optimized-tools
Per-session control of which skills and MCP tools/servers the model can see (built-in tools are untouched): default shows everything, auto asks the model each turn what to keep, smart picks from your saved groups, or tick groups by hand, with a switcher under the composer and fail-open to full visibility on any error. The default state is auto, which adds one model call per turn (the session model unless judgeModel is set).
dsh-task-instructions
you-qilin/dsh-task-instructions
DeepSeek Harness plugin: a Task Instructions button beside the input box pins reusable task requirements to a session, and the instruction survives context compression.
dsh-temp-task
raholly/dsh-temp-task
Adds a Temporary tasks section above the workspace list, where one click creates a timestamped folder, workspace and session; tasks support search, sort, pin, rename and archive, can be moved into a regular workspace, and tasks that never receive a message are cleaned up automatically.
dsh-auto-effort
subeichen1/dsh-auto-effort
Per-turn reasoning-effort routing that keeps the current provider/model: judges each user message (retry or correction, explicit intent, length, code blocks, errors, task scope) and sets reasoningEffort to a level the model actually declares, so Magpie and other OpenAI-compatible models work too. Ships a composer chip with an auto/manual switch and per-session decision history.
dsh-subagent-toolkit
leotpp/dsh-subagent-toolkit
Adds a Settings page to pin one OpenAI-compatible subagent model (or follow the main model), writes the official subagent-model-selection allowlist, reminds the parent to pass that route, and optionally runs one-shot tasks through an isolated Pi CLI provider.
dsh-skill-dev-delivery-rules
zmd12345/dsh-skill-dev-delivery-rules
Registers a battle-tested development delivery rulebook as a skill family - one core skill (clarification, delivery checklist, navigation) plus nine focused skills (layered architecture, evidence-driven debugging, minimal changes, impact-graded verification, migration feature parity, async UI feedback, sizing rules, CLI safety and cleanup, project notes). Only the skills matching the current task are loaded, trivial tasks (small reversible single-file edits) are exempted outright, so each session pays tokens just for the rules it actually uses.
dsh-timespan
qwayo/dsh-timespan
Tracks online, active and task time in DSH, with a day/week/month dashboard, per-workspace and per-session breakdowns, and a read-only `timespan_stats` tool for agents.
dsh-code-explainer
xiaoluoli45/dsh-code-explainer
Adds a Chinese end-of-line comment to every line of code shown in a DSH tool card - grey for the call being made, blue arrows for code in the output - written instantly by a local rule set and, for lines the rules cannot judge, by the current session model; a header toggle returns the block to plain code, and credentials are masked before anything is sent or cached.
dsh-workbench (workbench)
philomelcc/dsh-workbench
Workbench shell: mirrors native sidebar entries into a fixed system bar, adds a second row of page tabs for modules, and exposes a small module API for full-page plugins. The restart button needs an external supervisor (DSH_RESTART_CMD or a scheduled task named by DSH_RESTART_TASK).
dsh-todo-progress
oak-liuhj/dsh-todo-progress
A task progress sidebar for DeepSeek Harness Web and desktop with a top-right Tasks button, completion percentage, current step, status filters and details; declares DSH 0.2.1-rc.5 or >=0.2.2-rc.1 <0.3.0-0 compatibility.
dsh-gfm-alerts
nevstop-lab/dsh-gfm-alerts
Renders GitHub-flavored Markdown alerts (the `> [!NOTE]`, TIP, IMPORTANT, WARNING and CAUTION callout blocks) in DSH replies as theme-aware boxes with localized titles, and registers a system-prompt section asking the model to prefer them.
dsh-todo-note
lp86ndlb/dsh-todo-note
A draggable sticky note beside the chat: short-term tasks and a long-term plan whose phases carry real progress, plus three todo_note_* tools (read, update, complete) so the agent works from the same note. A task only counts as done after the user ticks it off, and the state stays on the local machine.
dsh-tjing-reading
hijoywell/dsh-tjing-reading
Read EPUB, PDF, DRM-free MOBI/AZW3 and TXT in the DSH sidebar. WeChat Read style typography with TOC, bookmarks, highlights and progress memory; select any passage to translate it into Chinese; the Ask-the-Book AI answers only from passages retrieved from the open book. Books and progress stay in local IndexedDB. Four themes including an eye-care green paper, and PDF paper follows the theme.
dsh-desktop-autostart-win
nanwu98/dsh-desktop-autostart-win
Adds a Settings page with one switch that writes or removes the current user's Windows Run entry for the DeepSeek Harness desktop app, detects the installed executable from the running app, App Paths, the default install folders or the installer records, and clears the Task Manager disabled flag.
dsh-send-later
iasiv5/dsh-send-later
Delay-send for the DSH chat composer: a clock button beside the send button schedules a message into the current session via 10-minute, 30-minute, 1-hour and 5-hour presets or an exact date and time, with the default continue prompt freely editable; delivery runs through DSH's official schedule automation tasks, so pending sends persist across restarts and can be reviewed or cancelled from the panel's pending list or the automation-tasks page, with a per-session badge count, a bounded safe-continue snippet plus the latest custom text, and a smart default time that pre-fills the GLM five-hour window end plus a two-minute margin when dsh-quota-watch is installed.
dsh-maestro-codex
gaohu1997/dsh-maestro-codex
Manage Claude Code, Codex and Grok CLIs inside dsh and dispatch tasks to them as headless subagents, with dsh models, skills and tools bridged into each task, resumable CLI subsessions, and a hierarchical task board in the right sidebar (the board tab requires the separate DSH-better-sidebar plugin; without it the tab is not registered).
dsh-followup
bingomu/dsh-followup
Every conversation gets an ending: mark dev-done, release channel and version in the conversation header, see how many items still need attention in the sidebar, and read all unfinished conversations, tasks and schedules in the right-panel ledger.
dsh-my-agent-preset
zkbnfcnb/dsh-my-agent-preset
Build presets for DSH Agents: package personas, prompts, skills, tools and runtime contexts into reusable capability bundles. Each task loads only the components it requires.
dsh-live2d-stage
ikunua/dsh-live2d-stage
Renders a Live2D Cubism 4 model as the DSH web UI background: a transparent click-through canvas that covers the window without blocking any control. Eyes, head and body follow the pointer; expressions track the agent state (thinking, running a tool, turn finished, error, waiting) and the conversation (message arrives, reply ends, question asked); after an idle delay the character shows speech bubbles and plays motions and expressions drawn at random from pools you tick. Settings list the models under ~/.dsh/live2d-stage/models, expose position, scale, opacity, gaze strength and every interval and probability, and open a resizable live preview of the same canvas. Expressions and motions a model3.json omits are detected from the model folder; one sample model is included.
dsh-plugin-thinking-level
zmd12345/dsh-plugin-thinking-level
Judges the right reasoning level locally from the current draft and recent turns and switches it in one click; warns when the context grows long and tells apart "new topic" from "same unfinished task" — less overthinking on simple tasks, enough reasoning on hard ones.