Plugin

Biblioteca di paper, lettore PDF e tutor. Le pagine citate portano al passaggio e lo evidenziano; domande su selezioni senza uscire dal paper. Piano di lettura, guida per sezione, quiz valutati tra sessioni. MinerU (self-hosted senza registrazione; cloud mineru.net richiede token) legge scansioni; formule citabili con clic (LaTeX in chat), ricercabili via QK^T e elencate per pagina. Endpoint embeddings opzionale per ricerca semantica. Eliminazioni recuperabili in .trash. Scorrimento/pagina singola, barra destra fullscreen, copia percorso, PDF tradotto, alternanza originale↔cinese con babeldoc senza preinstallazione. Trascrizione/ricerca locali per default; solo cloud MinerU/embeddings/traduzione attivati inviano il testo corrispondente al servizio configurato.

Analizza un file audio locale e offre un breve giudizio in linguaggio semplice su tempo, tonalità, dinamica, clipping e struttura dell’arrangiamento. Le misurazioni grezze restano in un blocco separato; l’audio non lascia il computer.

Una scheda di gestione plugin in Impostazioni → Plugin: nomi in cinese e descrizioni in linguaggio semplice per ogni plugin installato, attivazione/disattivazione con un clic, modifica delle note nell'interfaccia e ricerca/filtro nel catalogo installato.

Sostituisce la scheda traiettoria della GUI Web con una narrazione round per round facile per i nuovi utenti, etichette degli strumenti in linguaggio semplice, filtri per categoria e ricerca fuzzy.

Sostituisce la scheda trajectory della Web GUI con una narrazione round per round adatta ai nuovi utenti, etichette degli strumenti in linguaggio semplice, filtri per categoria e ricerca fuzzy.

Stile di output Conciso con un clic per DeepSeek Harness: risultati prima, niente riempitivo, stessa profondità di lavoro. Ogni risposta finale si apre con una scheda di sintesi in linguaggio semplice (seleziona il testo da copiare), con ambito per sessione, funziona anche in headless/CLI, con comando /concise, override style.md e API locale. Link e percorsi file dentro la scheda di sintesi sono resi come chip cliccabili: gli URL aprono il link, i file locali si aprono con l'app predefinita del sistema operativo (v0.9+). Un promemoria del contratto di pre-generazione per passo (v0.11.2+) corregge in modo misurabile le mancanze nella sintesi nelle risposte a forma di report di audit/tabella.

Controllo dello stato di salute con un solo clic per DeepSeek Harness: punteggio da 0 a 100, elenco dei problemi in linguaggio semplice e correzioni sicure e reversibili tramite il cordis.patch.yml del profilo.

Un catalogo di plugin e gestore di profili in linguaggio semplice per l'interfaccia web DeepSeek Harness.

DSH 插件：用你选的模型把最终回答润色成大白话，默认显示润色版、原回答可折叠。

DSH plugin: plain-language narration, an uncertainty gate, and mid-run interruption policy for DeepSeek Harness agents.

Agent preset for DeepSeek Harness: the standard tool stack plus four working rules written into the persona prompt — a project keeps at most four documents (intro, decisions, change log, current state and next steps), those documents describe only the current state with no AI edit history or superseded decisions, no git commit or push or pull request until the user explicitly asks, and a careful-coding workflow (restate the goal and done-criteria first, surgical diffs, evidence before claiming success) with plain-language reports.

Beginner panel for DeepSeek Harness: routes a plain-language request into ready-to-use plans (prompt variants, matching skills, advanced moves) with a local keyword engine and fills the chosen plan into a new session in one click.

Plain-language trust dashboard for the dsh trust family: aggregates the nine channels (injection interception, write denials, egress blocks, custody-chain verification, tool-surface and prompt drift, leftover scans, forgotten compaction constraints, profile composition) into one right-sidebar panel with a single status light and event cards that translate engine jargon into sentences a non-security user can act on; the read and egress engines run from the package's own npm dependencies so those channels work even without the sibling plugins, and absent plugins simply show as not installed.

A one-line caption above the composer that tells you what the AI is doing right now: the step number, the action (e.g. running npm test), and whether it is still going, done, or failed with a short plain-language reason. Inferred locally from tool calls and the thinking text; no model calls, no network requests, no writes to DSH data.

Turns one plain-language request into a live workbench window: a sidebar panel asks a few clarifying questions, the model writes a single-file HTML artifact, and the plugin mounts it in a resizable floating window or a standalone browser tab. Declared window actions are recorded as info-level project journal entries (without their payloads), and workbenches can be imported, exported, or installed from a market index.

Select a passage in a DSH conversation and read a plain-language explanation in a floating panel, which carries the surrounding message as the context. Three explanation depths (plain / general / pro) that re-explain on the spot when switched; optional web search and local file lookup (the model decides by default, and a button can force one lookup that reports only what is new); follow-up questions; and a button that hands the whole exchange to a new session in standby mode - the background is queued without waking the model or spending tokens. Settings live on the host in settings.json, and nothing is written until you press save. The repository also ships an OpenAI-compatible endpoint and a browser extension (source).

Bounded self-managed long-term memory (Hermes-style MEMORY.md / USER.md with hard character limits and a safety scan), a review that runs after every turn and writes plain-language notes or refines an existing skill instead of adding a near-duplicate, a curator that finds and surgically repairs skills the loader would silently discard, cross-session search over past messages, and a learning card above the composer that appears only when there is news and asks before it deletes or rewords a memory.

Resume screening plugin for HR in DeepSeek Harness: ingest up to 100k Word/PDF/Excel resumes into one searchable library with skills / coarse categories / ingest time, auto-ingest & de-dupe new resumes, then screen by plain-language criteria — rule pre-filter in the database plus LLM fine-judge on the shortlisted few, CSV export. Works on DeepSeek Harness 0.1.7 through 0.2.x, tested on 0.2.0-rc.1.