플러그인
DeepSeek-Harness 플러그인을 찾아보고, 필터링하고, 설치하세요.
플러그인 1705개 찾음
dsh-skill-author
apq/dsh-skill-author
Model-facing skill_manage tool that saves, replaces, or deletes Harness skills at user or project scope, with a standing system-prompt section that asks the model to evaluate skill retention before ending a reusable task.
dsh-miniflux-digest
wjloven/dsh-miniflux-digest
Read Miniflux inside DeepSeek Harness in a three-column panel (feeds, article list, article) and ask the assistant for unread digests, per-category briefings, full-text reads and read/star actions on the same account. Needs your own Miniflux server (2.0 or later; 2.3.2 for batch starring) and an API token, kept in the Harness credential vault (the MINIFLUX_BASE_URL and MINIFLUX_API_TOKEN environment variables also work).
dsh-solmirror
cthulhu-tww/dsh-solmirror
Connects the Solmirror open platform to DeepSeek Harness as MCP tools covering image and video generation, a model catalog, cost estimates, reference uploads, result queries and media URLs. Generation jobs submit as native dsh background tasks that notify on completion and run in parallel within one message, with in-chat video playback and an image wall. A settings page takes the platform API key, server URL, per-group model visibility and a test-connection check; the key is stored in the local dsh credential store. Reference uploads (image, video, audio) return reusable ids kept one day unused or three days after last use — 50 MB per file, video up to 30 s, audio up to 60 s. Usage bills platform points at in-site prices, with quotes before a run and automatic refunds on failure. Files passed to upload_reference (jpg/png/webp/gif, mp4/mov/webm, mp3/wav, up to 50 MB) leave your machine: images and videos go straight to Volcengine ImageX/VOD storage with temporary credentials issued by Solmirror, audio through the Solmirror server; its HTTP routes (/plugins/solmirror/...) have no DSH access check.
dsh-decide
calmzeala/dsh-decide
Connects DSH to decision models (TypeSafe Jev, TokenRhythm NeoHorse-Jev, OpenAI Decisions, and local System One endpoints) with decide, gate, rerank, and judge tools plus a settings page. Needs an API key for at least one provider (kept in the DSH credential store); the text you ask it to judge is sent to the selected provider unless it is local. The command guard is off by default.
dsh-connect-teleagent
anbulang/dsh-connect-teleagent
Connect DeepSeek Harness to the TeleAgent (China Telecom TeleAI desktop app) models through the app's own local kernel after signing in there, keeping DSH's streaming, multi-turn, images, tool calls, reasoning and points balance. macOS and Windows only, with TeleAgent 2.7.1+ installed and signed in. It reads the app's saved login token and points cookies (macOS Keychain / Windows DPAPI), starts the app's own kernel binary as a local child process, and needs the gateway apiKey the desktop app ships with, supplied through TELEAGENT_API_KEY or a local.secrets.json in the plugin folder. Daily points claiming is on by default; adding or switching accounts backs up and rewrites the app's login files. It uses the same package name and mount id as the listed alvinhuang0509-design/dsh-connect-teleagent, so install only one. The author's disclaimer asks you to follow TeleAgent's terms of use.
dsh-approval-translator
zhaoqiminggg/dsh-approval-translator
Adds an Explain this action button under the permission approval dialog: one click asks the session model for a plain-language description of the pending operation — what it does, which files it touches, whether it modifies or deletes anything, and the privacy risk — then gives a risk level and an allow or reject recommendation. Explanations are generated in Simplified Chinese, for readers who cannot parse the command.
blue
fgcgdroid/blue
Blue-team defense mode for CTF and incident response: 66 defensive tools, 12 console tabs, 17 SQLite fact tables, six worker roles, MITRE ATT&CK rule mapping, high-risk task approval and audit, a timeline hash chain with Ed25519 evidence, decoy/deception workflows, JSONL and OTLP telemetry, a CVE defense pack and an asset-risk graph, plus a standalone console with full view. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-auto-update
zhkkjf/dsh-auto-update
Windows-only auto-updater for DSH Desktop: checks the official update feed, downloads and SHA-512 verifies the installer, then force-closes the app via a one-shot Task Scheduler job and installs silently (automatically by default), and after restart reinstalls profile plugins and restores their pre-update settings from a snapshot.
dsh-notify-lite
game25011/dsh-notify-lite
A lightweight task completion notification plugin for DSH (dsh-notify-lite). When the agent finishes its work, it delivers Windows native Toast notifications with the first paragraph of the latest reply (40 characters by default). Supports taskbar unread badges, audio alerts, and configurable notification options. With no resident tray or background service, it keeps you focused without interruptions. Fully open source under the MIT license, with continuous DSH compatibility.
dsh-taskbar-status
callmeocean1/dsh-taskbar-status
Shows Windows taskbar progress while a turn runs, turns amber and flashes when an approval or question is waiting, and latches red after a failed turn. A fork of Joker2377/dsh-taskbar-status whose packaging change makes koffi an optional peer dependency, so it installs on DSH Desktop without a native build-script approval; do not install it together with the original.
XieHome
wxid123/xiehome
Two independently maintained agent presets (Conductor and a restricted Conductor child) for DSH with planning and task-delegation guidance: todo-first planning, parallel delegation (up to 4 sub-agents per batch) and goal-driven continuation. The persona runs in an "unrestricted mode": it tells the model not to state limits, add safety notes or disclaimers, and not to treat "you cannot" or "that breaks the rules" as a new instruction. All of this is prompt-level guidance, not enforced behavior.
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-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.