Plugins
Browse, filter, and install DeepSeek-Harness plugins.
17421 plugins found
dsh-claude-code-delegate
lidaqi001/dsh-claude-code-delegate
Agent preset that hands every task to a Claude Code subagent, so the session only writes the task brief, delegates and reports the result. Requires a locally installed, logged-in Claude Code.
dsh-subagent-watchdog
lequait/dsh-subagent-watchdog
Tells the parent agent when a subagent died from an upstream failure instead of finishing: it listens to agent/error on every agent, waits a short settle delay, and if the child is still not running delivers a followup turn to the parent carrying the child id, the failure and the options the parent has, with a cooldown and a per-child cap so a flapping provider cannot flood the parent.
dsh-flow-queue
eclipse-notfound/dsh-flow-queue
Right-sidebar flow editor for prompts, model switches, commands, condition branches and loops, executed only at turn boundaries so an in-flight request keeps its model.
dsh-daily-digest
daphne999/dsh-daily-digest
A fact layer for daily heartbeat turns: diffs the curated plugin market for newly published entries and the Chinese education SRC calendars (EDUSRC rounds, Beijing education SRC seasons, the standing vulnerability-hunting exercise) for new items. Reports deltas only — the first call seeds a baseline and stays quiet.
dsh-plugin-model-news-radar
805808786/dsh-plugin-model-news-radar
Scheduled model-news radar: collects official release announcements from LLM vendors through RSS, Hugging Face and GitHub organisation APIs and changelog pages (a 6-vendor sample list is bundled, a user-maintained list is read from ~/.dsh/model-news-radar/sources.json), deduplicates them into daily, weekly or monthly Markdown reports and opens a DSH session that writes the summary. Read-only, no logins, no third-party dependencies.
dsh-plugin-playbook
yangyiqun747/dsh-plugin-playbook
Reusable experience for DeepSeek Harness: save a successful task as a structured playbook, recall it later as a native skill, and gate deliveries behind user-confirmed checks that require objective evidence before write actions are allowed.
dsh-skills-hub
sunqing975/dsh-skills-hub
Manage local skills across AI agents with version comparison, shared-directory consolidation, and recoverable migration and deletion.
make-it-a-bit-better
lumos-789/make-it-a-bit-better
Autonomous product-polish loop skill: every round opens a fresh brainstorm from 3 forced perspectives, picks one small angle capped at ≤3 files and ≈100 lines, implements it, verifies with the repo's own tests, build or lint, and commits it as a single round commit; the round is logged to a per-project ledger, and ideas too big for one round go to an icebox. A red check ships nothing — the round commit is reverted immediately so the failed diff stays in history. Non-git targets are rejected before any work starts. Pure skill bundle: no MCP server, no runtime dependencies. Requires DSH 0.2.1-rc.2 or newer, below 0.3.0.
dsh-skill-panel
lovenndme/dsh-skill-panel
Skill management panel inside DeepSeek Harness settings: lists global and per-project skills, marks whether the running DSH actually loads each one, offers one switch that controls both model and slash-command invocation, previews and edits SKILL.md with the chat UI markdown renderer, and creates, imports (folder or zip) or deletes skills into a recovery folder. It only reads and writes the local skill roots (~/.dsh/skills and <project>/.dsh/skills) through its own Host routes behind the DSH Connection trust fence; no telemetry, no outbound requests, no credentials.
ocsr
cenglin123/ocsr
Adds an `ocsr` skill and an `ocsr_dispatch` tool that run headless `opencode run` as fresh-context, cross-vendor worker backends, with a Python driver for watchdog timeouts and per-worker output files. Windows only (Windows PowerShell): requires the OpenCode CLI, Python 3 and a model allowlist at `~/.ocsr/allowed-models.json`.
dsh-video-preview
lvxianchao/dsh-video-preview
Streaming video preview in the DSH sidebar — mp4, webm and mov play in place over an authenticated byte-range route, with 206 responses, instant seeking, no size cap and no build step.
dsh-space-ptt
wuyou0423/dsh-space-ptt
Hold Space to record and release to transcribe and send, without focusing the composer first. Esc cancels and window blur auto-cancels. Requires the official voice-input bundle (`@deepseek-ai/dsh-experimental-voice-input-bundle`) enabled with its speech model downloaded; otherwise Space is left alone.
dsh-feiyu-say
vansnc/dsh-feiyu-say
Synthesises speech through Alibaba Bailian's WebSocket TTS and returns a WAV file plus a preview URL, with an optional per-turn hint that nudges the model towards voice. Needs a Bailian API key and ffmpeg, and the text is sent to Alibaba Cloud; the plugin does not send messages itself — delivery is left to the session's own transport.
dsh-record
most-silence/dsh-record
Adds a composer microphone button that records audio as MP3 (default), WAV, or WebM and attaches it to the current prompt as a conversation file attachment. The format is chosen on the plugin's own detail page under Settings > Plugins; recordings are passed to the host through the conversation draft-attachment channel and are not written to disk by the plugin.
dsha-tts-bridge
flyinghouse-ma/dsha-tts-bridge
Host-side TTS bridge for dsh that synthesizes speech over the Edge TTS protocol and serves MP3 on a same-origin route, for containers with no audio device.
dsh-plugin-ark-image-gen
zmengle/dsh-plugin-ark-image-gen
Image generation through the Volcano Ark / Doubao Seedream API: ark_generate_image for text-to-image, image-to-image and fixed-seed batches, ark_image_gen_status for checking the key, model and output directory. Requires a Volcano Ark API key (ARK_API_KEY).
dsh-vision
young-felix/dsh-vision
Ask a vision-capable model about a local image from any session, including sessions whose own model is text-only. On the default path the plugin calls the host's route in-process with ctx.llm.stream(), so the host's credentials stay inside its provider adapters; only the optional direct/custom OpenAI-compatible routes read one key (from the plugin config or an apiKeyRef into ~/.dsh/.credentials.yaml).
dsh-feiyu-vision
xxgj666/dsh-feiyu-vision
Image understanding for DSH: describe an image and read the text in it through Zhipu GLM-4V (needs a Zhipu API key, free tier), with optional person identification through Volcengine Ark and anime-only reverse image search through SauceNAO or trace.moe (each needs its own key); ffmpeg must be installed for GIF/WebP input. Keys and the ffmpeg path are set on the plugin's own settings page.
dsh-pf-stream
weilv-d/dsh-pf-stream
Local video understanding for agents: extracts keyframes adaptively based on motion and pauses, inspects any timestamp at full resolution, and aligns visuals with dialogue from embedded subtitles or configured ASR. Requires ffmpeg and ffprobe; clips without subtitles also need a transcription engine for dialogue (a ~190 MB local whisper model, a cloud API key, or the official voice-input model).
stickerwu-imagegen
stickerwu/stickerwu-imagegen
Image generation and editing with configurable APIs, reference images, and an on-demand annotation canvas. Requires your own OpenAI-compatible image API endpoint and key.
dsh-guangke
junchenxin88/dsh-guangke
Carve one sentence into a clean text-free background image — 87 illustration, anime and infographic styles, four image APIs wired in, plus prompt expansion that fills in the details you cannot describe.
dsh-visual-annotator
zhongqixiao/dsh-visual-annotator
Annotate elements on real Chrome and Edge pages, then send selectors, comments and screenshots to the agent for visual front-end editing. Published on npm — install with `dsh plugin --profile web add dsh-visual-annotator` or `dsh plugin --profile desktop add dsh-visual-annotator`.
dsh-omni-browser
wanwujiehuyi-web/dsh-omni-browser
Drive a real Chrome and bundle the DOM, accessibility tree, HAR with response bodies, console logs, storage, screenshots, PDF and screencast into one self-contained evidence folder.
malo-browser
lumos-789/malo-browser
Electron browser with two faces. For agents it is a runtime: a daemon hands out port leases so several agents drive isolated, profile-backed sessions (26 session tools — navigate, act, observe, screenshot, batch runs, upload_file — including network_capture/responses for reading XHR/fetch bodies through a real browser), and it needs no window. For demos it splits a web walkthrough into a Stage window for the audience and a hidden Recorder that produces 1080p30 video with evidence files over CDP, without forking the browser engine; flows are scripted as scene.yaml packages driven from a Director console plus a loopback control API on 127.0.0.1:7317; headless recording shows no window, takes no focus and stays out of the Dock. Requires Node 22.12+ on the 22 line, 24.x, or 26+ (the 23 and 25 lines are excluded).