Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

278 plugins found

F

dsh-plugins (archive-rsi)

feahter/dsh-plugins

Session archive with tags, notes and per-session metrics, plus a Plan-Do-Check-Act loop over the archived sessions that produces prompt and AGENTS.md rules and re-measures them on later sessions. Runs locally without calling a model.

02 days agoSessions & MessagesMIT
R

dsh-blunt-dev

rosemary-ewe/dsh-blunt-dev

Adds a system-prompt section that asks the model to drop stock AI writing habits: subheadings, bold and emoji overload, quoted aphorisms and grand-finale endings.

010 days agoIntegrations & RemoteMIT
H

dsh-half-page

heiyedehen/dsh-half-page

Half Page (dsh-half-page) — a reading room kept for the agent: through reading_* tools it reads a book from ~/.dsh/reading one chapter at a time, writes notes beside chapters and keeps its own writing there, and a panel shows its reading progress. It adds lines to the system prompt telling the agent the room is its own and optional. Not a to-do list.

010 days agoUI Enhancements
F

dsh-plugins (mind-canvas)

feahter/dsh-plugins

Infinite-canvas mind map in the sidebar: grow nodes with Tab, tidy a branch into a tree, ask the assistant to expand a node into child ideas, and export to Markdown, OPML, FreeMind, JSON or PNG.

02 days agoUI EnhancementsMIT
Y

dsh-devlead (bundle)

yankeguo/dsh-devlead

DevLead mode for DeepSeek Harness: a human-only switch turns one ordinary session into a lead with eight devlead_* tools to register workspaces and create, read, continue and watch other ordinary sessions; it dispatches work to those sessions, reviews the delivery and reports, is woken through a durable notification digest when a watched session's turn settles, and can give a dispatched writing session its own Git worktree when the host provides the experimental worktree service.

014 hours agoWorkflow & AutomationMIT
G

dsh-novel-mode

github-yousen/dsh-novel-mode

Writes a novel from one idea to a validated manuscript with a code-driven workflow: a JavaScript state machine runs the stages (constitution, outline, design, writing, validation, batch, export) and a 15-step per-chapter loop, PowerShell scripts validate each gate, and versioned checkpoints let a restart resume at the exact chapter. Nine subagent roles do the drafting and review. Needs PowerShell 7 (pwsh) and Python 3.7+; without pwsh the gates record a DEGRADED verdict and the run pauses.

09 days agoWorkflow & Automation
K

dsh-frontend-design-skill

kechao-sgp/dsh-frontend-design-skill

Registers a frontend-design skill that asks for a design plan and token system before writing code, and ships Chinese typography rules plus a measured no-screenshot self-check. It provides one skill and no tools, makes no network requests and writes no files.

013 days agoSkillsApache-2.0
5

ai-plugins (alibaba-java-guidelines)

511659192/ai-plugins

Ships the Alibaba Java coding guidelines, 44 selected rules, as an embedded harness skill, so writing, changing and reviewing Java code or DDL follows the handbook with a numbered self-check before delivery.

013 days agoSkills
Y

dsh-novelai

ysiguu/dsh-novelai

NovelAI image generation for DSH: `nai_image` (style presets, artist strings, per-model weight rewriting, token budget warnings, results rendered inline), `nai_status`, and `nai_prompt` (build / check / guide), plus a studio page with live draft previews, a standalone studio server, and a prompt guide distilled from four tutorials. Bring your own `pst-` token.

011 days agoVision, Voice & MultimodalMIT
M

dsh-CET6-learn

mount9527/dsh-cet6-learn

CET-6 training panel with word drills (core and syllabus lists, three modes), 25-question listening in three sections, cloze, long reading, careful reading, partial and full translation, timed writing, a vocabulary notebook and a wrong-answer notebook. Ships only an original sample bank (345 words, one mock paper); the full ~2,500-word core list, ~6,000-word syllabus list, papers, transcripts and audio come from your own files, built locally from a data-pack folder and never uploaded.

012 days agoTools & Capabilities
J

dsh-obsidian-vault

jinferth/dsh-obsidian-vault

Obsidian vault tools: 13 tools for listing, reading and searching notes, creating, appending and editing by line range, deleting to the vault's .trash folder, frontmatter CRUD, tag queries, image insertion, batch operations, and renaming notes while rewriting the wikilinks that point at them; writes are atomic and keep CRLF and BOM.

08 days agoTools & CapabilitiesMIT
S

dsh-plugins (dsh-mnemon-sync)

summerscar/dsh-plugins

Backup and restore for dsh-mnemon: pick any of its three memory components (memory spaces, project documents, runtime memory) and archive them to S3-compatible storage or WebDAV, then browse the archives and restore a chosen subset. Live SQLite databases are copied through node:sqlite backup() so a concurrent writer cannot tear the copy; every file carries a SHA-256 checked before upload and again before restore; a restore previews by default and deletes the stale -wal/-shm sidecars before writing a database back. Archives are named mnemon-sync-<device>-<timestamp>.zip so backups from several machines stay tellable apart. Runs a single timer with intervals from hourly to weekly, stores credentials in a 0600 file outside the DSH profile, and depends on nothing outside Node.

012 hours agoMemory
S

dsh-context-windows

soulzhou/dsh-context-windows

Adds a Settings section to adjust the advertised context window of each connected WorkBuddy and Trae model, writing the override into the connector's context budgets.

011 days agoModels & ProvidersMIT
L

dsh-speakhumantalk

liuzx012/dsh-speakhumantalk

Removes AI phrasing so replies and documents sound human: an always-on de-slop style section injected into every session (on by default, switch it off with deslop_mode), four deslop_* tools (0-100 slop scan, deterministic rewrite, intensity switch, voice profile) and four skills (rewriting, conversation, technical docs, Chinese reports), copied into the DSH skills folder at startup. The effect is measurable: a typical AI-flavoured Chinese paragraph scores 49 before deslop_rewrite and 6 after.

011 days agoUsage & BillingMIT
T

dsh-notes

tyouter/dsh-notes

A page for writing notes inside DeepSeek Harness. · Minimal writing — one page that typesets as you type. · AI completion — a suggestion arrives when you pause, and TAB takes it. · Immersive writing — full screen, with only the page on it. · History — every note listed, searched and edited in place, and copied out as standard Markdown. · AI board — a data assistant that answers from your notes and pins the charts it builds.

08 days agoUI EnhancementsMIT
B

dsh-rsa

beckchiang/dsh-rsa

Configurable startup splash screen for the DeepSeek Harness desktop app on Windows only — a real main-process splash with live preview and light/dark themes. Deploys by rewriting the app's app.asar (a backup is kept) and takes effect on the next launch after you quit DSH; redeploy after each DSH upgrade.

0yesterdayUI EnhancementsMIT
S

dsh-buddha

shengmouqwq-sketch/dsh-buddha

Rewrites every assistant reply into Buddha-says ciphertext (佛又曰:…) with the 与佛论禅 AES-256-CBC + Chinese-character substitution scheme, rewriting the final block text as well as the streamed deltas; history sent back to the model is decrypted first, internal calls that carry a purpose pass through untouched, and a config file in ~/.dsh/buddha toggles it live.

013 days agoJust for FunMIT
X

dsh-clarify-mode

xiaofeng-bm/dsh-clarify-mode

Adds a clarify mode: the agent loses its file-writing tools and can only ask questions until the required dimensions are covered, then writes a spec with acceptance criteria before implementing.

014 days agoWorkflow & AutomationMIT
1

dsh-elysia-memory

1148462398-hub/dsh-elysia-memory

Elysia's memory plugin for dsh. One shared, human-editable MEMORY.md across every session: two-disk mirror, history snapshots, cross-process write lock; entries tier between the main file and a searchable archive by hit frequency; retrieval is keyword co-occurrence plus BM25. Nine sections (persona, requirements, corrections, lessons, methods, requests, sessions, method library, ingested docs) plus a dedicated self-identity section for a character's own self-cognition, injected above the persona. Ships an opt-in memory pack (packs/elysia: 61,903-char identity + 2,482-char persona, distilled from 1,696 officially-confirmed voice lines and 112,175 dialogue lines) that is off by default, backs up before writing, only touches identity/persona, and can be uninstalled. Also opt-in voice playback through a local GPT-SoVITS engine, a skills library, and a sticker library that sends a fitting sticker at the right moment. On by default: after every reply a bubble with an avatar pops up (voice.bubble: false turns it off), and unless the agent already spoke itself it costs one extra small-model request. Opt-in voice playback needs a local GPT-SoVITS engine (about 27 GB, installed separately, NVIDIA GPU required; the plugin downloads about 200 MB of weights) and is Windows-only; the automatic second-drive mirror is Windows-only too (elsewhere set mirrorPath, otherwise there is no mirror).

09 days agoMemoryMIT
R

dsh-xhs-style

refreshing-czq/dsh-xhs-style

Adds a requirements-discovery gate before product selection, version choices and competitive analysis: 2–3 clarification rounds with 2–4 decision-changing questions, validation of real pain points and hard constraints, comparison of original, alternative and minimum-cost routes, and a confirmation card before research and copywriting. Confirmed reports keep the Xiaohongshu-style structure, concrete steps, audited images and source links. Ordinary lookups and explicit user skips bypass the questionnaire. Host-only static prompt sections with no config, client UI or dependencies.

06 days agoIntegrations & RemoteMIT
M

dsh-myself-preset

mutexz/dsh-myself-preset

Yugan Huafang (语感花房) is a personal voice workshop for DeepSeek Harness: your own writing and corrections become explainable local style rules, optionally distilled by the current model, then compiled into a preset you pick per session; edits apply on the next message in that session.

013 days agoIntegrations & RemoteMIT
E

dsh-article-annotator

elycheng/dsh-article-annotator

Article Review page in DSH's native right sidebar: turns Markdown, Word, PowerPoint and PDF articles into sentence-addressable text, lets you comment on any sentence, and hands the open review to the agent as a composer draft. Six agent tools let the model read every comment, revise the article (in place for Markdown, as a sibling <name>.revised.md for binary formats), resolve the comments, and record recurring wording preferences into a long-term writing-style memory injected into later prompts. Extraction includes a dependency-free DOCX/PPTX reader; PDF text extraction runs locally through the host's Python + pypdf (or poppler's pdftotext) and is unavailable without one of them. No network calls, no telemetry.

08 days agoUI EnhancementsMIT
D

dsh-log-trim

dddmuc/dsh-log-trim

Trim idle DeepSeek Harness session logs at startup: keep the last N windows, cut the ones the model can no longer see, and verify the result with the host's own format, session and projection validators before writing. Not context compaction: this shrinks

013 days agoDev & Plugin Tools
Z

dsh-humanizer-zh

zhejiangf/dsh-humanizer-zh

An on-demand Chinese editing skill that reduces formulaic phrasing while preserving facts, uncertainty, genre, and author voice.

015 days agoSkillsMIT