Plugins

Terminalartiger Composer für die DSH-Web-GUI: Shell-Prompt-Verlauf (↑/↓, Präfixsuche, Ctrl+R), Codex-ähnliche Vervollständigung und Vorhersage des nächsten Prompts (mit Tab oder → übernehmen), Auswahlleiste (kopieren/zitieren/im Seitenchat fragen), Einfügen per Rechtsklick, verschiebbares Chat-Inhaltsverzeichnis und paralleler Seitenchat rechts.

Eingabevorhersage für den DSH-Composer: Schlägt nach jeder Runde den nächsten Prompt als Geistertext vor und übernimmt ihn mit Tab (autocomplete / input prediction / prompt suggestion).

Polymarket-Toolkit für DeepSeek Harness und Claude Code: Marktdaten-Tools für Gamma/CLOB/Data-API (31 Modell-Tools in DSH; schreibgeschützte Teilmenge über MCP zugänglich), optional authentifizierte Trading-Tools, WebSocket-Stream-Dienst und eingebetteter Polymarket-knowhow-Skill.

Bayesianisches Aktienvorhersage-Plugin, das MACD, RSI, gleitende Durchschnitte, Volumen und weitere technische Signale zu einer Posterior-Wahrscheinlichkeit eines Kursanstiegs fusioniert, mit Multi-Horizont-Vergleich, Trendzustandsklassifikation und Positionsrisikokennzahlen für A- und US-Aktien.

Tab autocomplete for the DeepSeek Harness desktop and web composer: next-message ghost text, inline draft completion, and Alt+Up/Alt+Down candidate cycling.

Prompt optimization, next-sentence prediction, inline completion, and per-session draft stashing for the DSH input box.

Next-prompt suggestions: after each answer it predicts your next message as grey ghost text in the composer. Tab fills it without sending, and the prediction model is selectable.

Predicts the user's next prompt after each assistant reply and shows it as gray ghost text inside the composer; accept it whole with Tab, accept it piece by piece with Alt+→, reroll it, or dismiss it with Esc.

Eingabevorhersage für den DSH-Composer: Schlägt nach jeder Runde den nächsten Prompt als Geistertext vor, der mit Tab übernommen wird (autocomplete / input prediction / prompt suggestion).

Analyse von Plugin-Kombinationen für DeepSeek Harness: Abhängigkeitsbäume, Konflikterkennung, Risikobewertung mit Vorhersage, Visualisierung und Kombinationssimulation.

SSQ-Helfer (China Wohlfahrtslotterie Doppelte Farbkugel, Double Color Ball) für DeepSeek Harness: Trend-Verfolgung über 1000 Ziehungen, sechs Vorhersagemodelle mit Ensemble-Voting, Strukturanalyse sowie dan-tuo/Zufallsgenerierung über das ssq-Tool.

Predicts your next instruction from the current conversation and shows it as the composer placeholder; press Tab to turn it into an editable draft.

Shows a dimmed suggestion of the user's next message in the empty composer after a settled turn; Tab accepts it into the draft and Escape or typing dismisses it.

ChatGPT-style composer predictions for DeepSeek Harness: after each assistant turn, suggest the user's next message as ghost text in the composer. Tab accepts, Escape dismisses.

Input prediction: the likely continuation of your draft appears as grey ghost text after the caret and Tab accepts it, and after each assistant turn 1-3 clickable follow-up suggestions appear above the input box and send on click. Ghost completion, suggestions and the suggestion count can be toggled in Settings, Built-in plugins.

Live usage gauge injected into the system prompt every turn: session tokens and estimated spend, a next-turn estimate, and two predictions the model can act on — which step fills the context window and which step burns the budget. /qm panels, zero-config by default, optional price table, and it publishes a summary.json budget contract sibling plugins read.

The composer predicts what you are about to type. Inline ghost text sits on the caret, measured against the editor's own font and line box, and Tab turns it into real text (Esc ignores it). The prediction is one short call through the session's own model router, seeded with your draft and the last few turns of the conversation, so an empty composer also gets a next-prompt guess written in the user's voice; suggestions that merely restate the assistant are dropped. Host side is one HTTP route with sub-path endpoints (loopback-only, 64 KB body cap, 2-minute result cache, 20-second miss cache, one in-flight call per session); client side is one 0-height overlay registered on conversation.input.overlay, with insertion guarded by the composer's draftRev CAS and a setDraft fallback. IME composition and slash commands are skipped. 16 node:test cases, zero runtime dependencies, real screenshots in docs/.

Predicts your next message after each completed turn and shows it as ghost text in the composer: press → to accept, or keep typing and finish it word by word with Ctrl+→, Esc to dismiss. The prediction model follows the session by default or can be picked in the settings card, which also has an on/off switch and a speed test.

蛋白质结构预测与设计插件：序列设计（ProteinMPNN/SolubleMPNN/LigandMPNN）、结构预测（ESMFold）、复合物界面筛选、序列理化打分与多样性聚类——零手动自举（本地 CPU/GPU 自适应），供 dsh-bio-genie 消费 | Protein structure prediction & design toolkit for dsh (sequence design, folding, interface screening)

Claude Science-style AIDD research workbench for DeepSeek Harness — ReAct research loop, versioned artifacts with provenance, and 17 skills for virtual screening, molecular generation, ADMET prediction, DTI modeling and model reproduction.

Dependency-topology guard: pre-install conflict prediction and post-install detection of duplicate @deepseek-ai/dsh-* copies, version drift, and vendored core services that cause Symbol-key crashes like "Cannot read properties of undefined (reading 'prepare')".