Plugin

Composer stile terminale per la GUI Web DSH: cronologia dei prompt shell (↑/↓, ricerca per prefisso, Ctrl+R), completamento e previsione del prompt successivo stile Codex (accetta con Tab o →), barra di selezione (copia/cita/chiedi nella chat laterale), incolla col tasto destro, indice chat trascinabile e thread parallelo nella barra laterale destra.

Previsione di input per il composer DSH: suggerisce il prompt successivo come testo fantasma dopo ogni turno, accettabile con Tab (autocomplete / input prediction / prompt suggestion).

Toolkit Polymarket per DeepSeek Harness e Claude Code: strumenti di dati di mercato per Gamma/CLOB/Data-API (31 strumenti modello in DSH; sottoinsieme di sola lettura esposto tramite MCP), strumenti di trading autenticati opzionali, servizio di stream WebSocket e uno skill knowhow Polymarket integrato.

Plugin di previsione azionaria bayesiana che fonde MACD, RSI, medie mobili, volume e altri segnali tecnici in una probabilità a posteriori di rialzo, con confronto multi-orizzonte, classificazione dello stato di trend e metriche di rischio di posizione per azioni A e USA.

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.

Prevede il testo nel compositore DSH: dopo ogni turno suggerisce il prompt successivo come testo fantasma, accettabile con Tab (autocomplete / input prediction / prompt suggestion).

Analisi delle combinazioni di plugin per DeepSeek Harness: alberi delle dipendenze, rilevamento dei conflitti, valutazione dei rischi con previsione, visualizzazione e simulazione delle combinazioni.

Assistente SSQ (Lotteria di Beneficenza Cinese Doppia Palla) per DeepSeek Harness: monitoraggio delle tendenze sulle ultime 1000 estrazioni, sei modelli di previsione con voto di insieme, analisi della struttura e generazione dan-tuo/casuale tramite lo strumento ssq.

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')".