Plugins
Durchsuche, filtere und installiere DeepSeek-Harness-Plugins.
128 Plugins gefunden
dsh-git-manager
dayi-z/dsh-git-manager
Visueller, mit GitHub verbundener Git-Manager für DeepSeek Harness: geführte GitHub-Flow-Schritte, Commit-Graph mit PR-/CI-Badges, GitHub-Anmeldung per Klick, PR-/Issue-Verwaltung und strukturierte Git-Tools für den Agenten. In 2.0.0 von gitcompass umbenannt.
dsh-feishu-channel
whoisjiahao/dsh-feishu-channel
Feishu/Lark-Kanal, der DeepSeek Harness-Agenten aus Chats heraus steuert: Streaming-Rich-Cards mit Live-Denkprozess und Tool-Schritten, Kostenmessung pro Zug zu DeepSeek-Peak-/Off-Peak-Tarifen, Genehmigungskarten mit einem Tipp, modellgesteuerte Bildannahme und QR-Onboarding ohne öffentlichen Endpunkt.
dsh-planchart
smilebuild/dsh-planchart
Veröffentlicht einen Projektplan, den der Agent schreibt: geordnete Schritte in einem rechts angedockten Panel und der Framework-Graph als automatisch angeordnetes Diagramm in einem eigenen Center-Tab, herunterladbar als SVG oder PNG. Diagramme werden aus dem Sitzungslog neu aufgebaut, überstehen also Neustart und Wiederaufnahme.
dsh-trace
vibeinging/dsh-trace
Telemetrie-Backend, das Runden, Modellschritte und Tool-Aufrufe zu yiTrace exportiert.
dsh-expert-role
yjnmedia/dsh-expert-role
Expert Library (also called Expert Role or Private Think Tank). Domain knowledge libraries for agents: each expert is a folder with SKILL.md, a manifest and references; only its name and one-line description sit in the skill catalog until the model loads it, so a large corpus stays out of the context. Ships two experts (design, DSH plugin) that are copied into the library on first start, fill-only and never overwriting yours. 12 tools create experts, move material in, find documents, plan and record research, dispatch steps to child sessions or open a standalone workspace. A gap list shows which questions went unanswered, a five-star maturity score uses structure, coverage, content, freshness and research closure (the fifth star also needs real usage), and a panel shows per session which expert was loaded and which file was read. It reads and writes files under the expert root; its HTTP routes accept local requests only; dispatching steps or opening a workspace creates child sessions and spends tokens.
dsh-opticforge
wbmgggg/dsh-opticforge
KB-first optical-engineering task assistant. opticforge_assist aligns a concrete problem with the 40-section / 324-entry knowledge base before any web search. 3.1.1 activates up to three topic playbooks (16 cards, 98 dimension declarations), retrieves evidence per required dimension, and returns a dimension-by-source coverage matrix, a gated plan with dimension IDs and cross-check steps, formula cards, a five-section report outline and acceptance checks. Answers explain principle -> formula/criterion -> approach -> steps, and never expose KB layer or entry IDs; sources are named as documents, standards, manuals or URLs. web_gate allows external search only for declared KB gaps, standard versions, vendor parameters or price timeliness. opticforge_verify checks KB alignment, present-only citations, dimension evidence, cross-relations, source tiering, KB conflicts, 30-day freshness and five-section presentation, and reports an adoption gate. Includes 308 concept cards, 6 generic dimensions, 19 formula cards and the opticforge-task DSH Skill. 308 entries are citable; 16 declared gaps remain, limited to A03, C01 and E01 verbatim sources. Five tools, zero runtime dependencies, no calculator, no network access and no action execution by the plugin. npm publication is on hold; install from GitHub with node scripts/install-local.mjs.
dsh-experience-optimizer (plugin-recipe)
starlit-sky-code/dsh-experience-optimizer
Workflow blueprint planner for DeepSeek Harness: turns a business goal into validated steps, capabilities, permissions, failure handling, acceptance criteria and rollback, then exports Markdown or JSON.
dsh-vellum
avenyq/dsh-vellum
Native cards inside DSH replies: when the model writes a vellum code block, it renders as a theme-following metrics, chart, comparison, checklist, steps, timeline, form, quiz or sortable table card; clicks, submits and answers come back to the conversation as the next message.
dsh-tool-dispatch
66-zhimeng/dsh-tool-dispatch
Batches independent tool calls into one model round-trip: run_tools dispatches many steps concurrently (after-dependencies for ordering), run_parallel fans out sub-agents, so fewer round-trips and lower wall-clock time.
dsh-session-rotate
cry-flu/dsh-session-rotate
Session rotation for long conversations: when a session reaches its step budget, at the end of the turn the plugin opens a new session in the same workspace, posts a handoff summary it assembles itself from local session events, and archives the old one immediately or after a retention window. Per-workspace step limits, a minimum-steps floor, a cooldown, a rotation cap and a dry-run switch are configurable in the settings page, and the summary is built with no model call.
dsh-preflight
ruaibeite/dsh-preflight
Predict a task's steps, tokens, duration and cost from this machine's local session history, with a local price table for cost estimates. Read-only, local-only.
dsh-ui-placement
inaflash123/dsh-ui-placement
Moves the question panel's Skip and Submit buttons in from the right edge, and steps the composer column left so its controls stay clear of a bottom-right desktop pet.
dsh-echochat-plugin
verchiel666/dsh-echochat-plugin
Adds one tool, echo_judge, that scores 1-4 draft replies to an emotionally loaded message on three steps (perception, mental-state inference, response strategy), combines the steps with a cascade gate and step-level credit assignment, and names the weakest step to redo; scoring runs through ctx.llm of the running engine, so no API key is needed.
dsh-session-recap
sas-159/dsh-session-recap
Adds a recap card under the composer for the current session: turns, steps, tool calls grouped by name, the uncached / cache-read / cache-write / output token split, the cache-hit rate, and a cost range computed from the official Flash off-peak and peak list prices. Exports the same card as Markdown or a standalone HTML page.
dsh-model-quick-selector
arrosam/dsh-model-quick-selector
Adds a quick-select model list to the DSH composer model button: a settings icon on the Model row of the model menu opens a dialog to pick and reorder favourite models, dragging vertically on the model button switches between them on release, and dragging left or right steps the reasoning effort; the menu's reasoning-effort row also gets a draggable slider (based on Microqian2th/dsh-codex-effort-slider). Text follows the DSH language setting (English / Chinese).
gemworks
geml-spec/gemworks
Runs the agent through GEML workflows: work items move through flow steps, practices are recorded at the step they belong to, and a board tab in the right sidebar shows where each item stands. Also mounts the GEML MCP server and skills; when the project has a fixed workflow, a supervisor gates tool calls by its current state. Needs Node.js 22+; the GEML MCP server is fetched with npx (@geml/geml) when a session starts.
dsh-computer-use
mount9527/dsh-computer-use
Windows desktop operation layer for DSH: 17 tools for window listing, screenshot plus OCR, UI Automation, keyboard and mouse, file operations and CDP browser control. Non-intrusive by default (UI Automation patterns and window messages, never the physical pointer), irreversible steps go through a native confirmation dialog, Esc or an on-page button stops a running task, and a global lease keeps two sessions from driving the desktop at once.
dsh-pua-receipt
dingchenhui0618-arch/dsh-pua-receipt
Measured /pua for DeepSeek Harness: every pressure message gets a receipt comparing the last N completed model steps with the next N — tool calls, verification-class steps, repeated-call peak, failed calls and text volume — with a three-way verdict (changed approach / merely restated / no change) and a daily ranking of which sentence moved the work. Ships a conversation-view panel, a /pua command with list/status/receipts/rank/off, append-only local JSONL receipts (no tool arguments, content or session ids), 38 node:test tests and a zero-dependency build. Reports observed differences, not causality. Inspired by MichengAI/dsh-pua (independent code); it registers the same /pua command, so it cannot be installed alongside dsh-pua.
dsh-subtext
muninn-and-zmx/dsh-subtext
Reads what a message means beneath its literal wording in everyday chat, then steps aside the moment work starts.
Dsh-Microsoft-ToDo
wekyjay/dsh-microsoft-todo
Microsoft To Do panel: browse lists, add, edit, complete and reopen tasks, and open notes, due date, reminder, recurrence, steps and attachments. Lists can be collected into local groups, and a batch of tasks can be picked into a My Day shortlist. Signs in with the Microsoft device-code flow; the token cache belongs to the upstream microsoft-todo-mcp server, pinned to 0.2.0 and started with npx (so Node.js and npm access are needed) with only an allow-listed environment, while groups and My Day live locally. Today, Overdue, My Day and new due dates and reminders follow the device time zone (override with DSH_TODO_TZONE). Chinese and English UI.
dsh-Visualization
peilopielo/dsh-visualization
Turns a live session into a layered instrument: seven toggleable rings (session, steps, skills, tools, jobs, approvals, file changes), a per-turn timeline, hover and click on every ring node, and per-step ladders drawn beneath the rings. It reads the session log directly and updates as the conversation runs, in Chinese and English.
dsh-human-step
yyhy110421/dsh-human-step
Pauses a DSH task at steps that need a human, such as 2FA codes, QR scans, signatures or payments, and shows a native card with done, skip and cancel actions.
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.
dsh-next-steps
xiaoxiaolelang-ai/dsh-next-steps
Per-turn next-step suggestions under each reply: a 2x2 grid of up to four clickable actions, projected from that turn's own tool result instead of a shared per-session store.