Plugin
Sfoglia, filtra e installa i plugin di DeepSeek-Harness.
140 plugin trovati
dsh-prompt-optimizer
windrover/dsh-prompt-optimizer
Prompt optimizer nella riga degli strumenti input del composer: scegli categoria e template, poi ✨ riscrive la bozza sul posto con undo in un clic. Categorie Basic, Context, Image; annulla un’esecuzione e mostra durata e token. Include 15 template per riformulare istruzioni, pianificare fasi, impostare ricerche di sicurezza, schede ruolo per system prompt e prompt text-to-image/image-to-image. I template Context leggono i turni recenti per la coreferenza. Chiamate tramite il servizio modelli host; Settings mostra modello e budget. Un guard controlla che i vincoli dell’utente restino e avvisa invece di riprovare automaticamente. Adattato a dsh 0.1.7 e 0.2.
DSH-Chinese-Talk
tianlaoban/dsh-chinese-talk
Imposta in cinese il ragionamento e le risposte di ogni sessione, con tono conciso, un po’ ironico e diretto; mantiene i nomi propri in inglese e aggiunge la regola «rispondi solo a ciò che è stato chiesto». Nessuna UI, binari o chiamate di rete. Usa una sezione globale del system prompt (order 10) ed è inattivo nel preset minimal, che sostituisce l’intero prompt con la propria persona.
dsh-memvault
zhang66633/dsh-memvault
Collega DSH a un archivio MemVault locale: inietta i blocchi di memoria principali nel system prompt, estrae i turni conclusi tramite la pipeline propria di MemVault e offre un pannello per consultare, tracciare, rivedere e riprodurre quanto salvato.
dsh-ponytail-sync
mirelconstantin/dsh-ponytail-sync
Modalità lazy-senior-dev di Ponytail come skill nativa DeepSeek Harness, sezione system prompt e sei comandi slash. Sempre disponibile, livello selezionabile, nessun processo esterno.
dsh-prompt-desk
hwayn-pixel/dsh-prompt-desk
Banco di lavoro prompt DSH: mostra ogni sezione del system prompt, consente di scrivere regole personali, controlla duplicati e contraddizioni e registra ogni modifica.
dsh-prompt-profiles
knopki/dsh-prompt-profiles
Profili di prompt per sessione DeepSeek Harness: sezioni system-prompt riutilizzabili raccolte in profili nominati e fissate nel prompt della sessione.
dsh-reasoning-language
jide315/dsh-reasoning-language
Usa una sezione configurabile del prompt di sistema per richiedere la lingua di ragionamento desiderata (cinese semplificato per impostazione predefinita). Le righe di ragionamento sono espanse per impostazione predefinita e quelle chiuse manualmente dall’utente restano chiuse.
dsh-instruction-memory
hero476/dsh-instruction-memory
Inserisce le istruzioni permanenti modificate nelle impostazioni DSH nel prompt di sistema di ogni turno successivo.
dsh-adrian-inject-context
polohot/dsh-adrian-inject-context
Inserisce le voci di contesto salvate come riga Remember dopo ogni messaggio utente, a ogni turno o una volta per sessione; include editor in Settings e pagina di gestione.
dsh-agent-lang
kannakuron/dsh-agent-lang
Tre canali linguistici indipendenti per l’output: descrizioni delle chiamate agli strumenti (titoli di tutte le schede, incluso run_code nei preset PTC), thinking e risposte. Ognuno segue la lingua della Web GUI, forza una lingua specifica oppure si disattiva; per impostazione predefinita solo le descrizioni seguono la GUI. Direttiva runtime-context globale sull’host; il client comunica la lingua. Modalità nella scheda Plugin di Settings.
dsh-manage
elmaxid/dsh-manage
Impone promemoria periodici di recupero e salvataggio della memoria Engram per gli agenti DeepSeek Harness: inietta un contesto dinamico nel system prompt per caricare i ricordi delle sessioni precedenti all’avvio e salvare nuove decisioni, correzioni e apprendimenti alla fine. La fonte si interrompe dopo “every”.
dsh-workflows
patrickb46-hub/dsh-workflows
Per-session workflow presets: switching one sets each disk skill to full, first-sentence or hidden in the model catalog, hides chosen global tools, adds a system-prompt persona section, applies a permission preset, and can insert the preset's prompt template into the composer. A right-side panel switches presets and rewrites the draft prompt; a rewrite never writes back to a preset.
dsh-prompt-lab
eustia-ast/dsh-prompt-lab
Per-session DeepSeek Harness system-prompt section editing with templates, presets, automatic backups, blank-window drafts, message appends and per-session global-tool switches; only explicitly enabled sessions are affected. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-zh-yayan
arthurzhu1992/dsh-zh-yayan
Thought and word, both in Chinese. DSH opens in Chinese, all the way down — Chinese reasoning and thinking for the main agent, subagents, teams and background tasks. What it claims, you can verify.
dsh-cache-doctor
qinghuidaqzp/dsh-cache-doctor
Explains DeepSeek prompt cache misses in a right-sidebar tab. It observes system-prompt/assemble and llm/stream, compares each request with the previous one in the same session, and names the first part that changed: a system prompt section (shown before and after, with the changed characters marked), the tool list, rewritten history, an expired cache or compaction. Shows today's hit rate, money the cache saved, avoidable extra cost at DeepSeek's peak and off-peak list prices, the last requests and seven days of totals.
dsh-think-flow
cv588888888888888888888ju/dsh-think-flow
Chinese add-on fork of the dsh-think-flow sidebar chain-of-thought panel: while upstream folds each session's live reasoning into turn → step groups, this fork sends each step to a separate, configurable model (titleProvider/titleModel) and shows an 8–18 character Chinese title plus a 20–60 character Chinese explanation under every step, and a one-line Chinese title per turn. The main model is untouched — no system-prompt injection, no extra tools, no context changes; the plug-in just makes its own request. autoTitlesOn arms title generation as soon as a panel connects, and batches over 10 steps are split so long turns (100+ steps) no longer come back empty; steps that only call a tool (no reasoning) are summarised from the call itself, and a failed segment is retried up to three times with backoff.
dsh-model-price
hao0311/dsh-model-price
Passive peak / off-peak price note for the model: one short system-prompt section states whether the DeepSeek API is in peak (2x) or off-peak (half-price) hours and when it switches, with no timer and no interruption.
dsh-global-fonts
lt123456b/dsh-global-fonts
Pin a fixed Source Han font table into the DSH system prompt so the model stops re-detecting, comparing, or asking about fonts; a settings panel remaps every role for CJK and Latin text. Requires the Source Han fonts to be installed on the machine.
dsh-stack-diagram
a895047059/dsh-stack-diagram
Bundles the stack-diagram architecture-diagram skill as a runtime skill, and injects a system-prompt section so the model draws diagrams without being asked. Output is self-contained HTML plus light and dark PNGs from bundled Python scripts; brand logos are fetched at run time.
dsh-agent-team-policy
mr-pounds/dsh-agent-team-policy
Adds one system-prompt section that limits delegation to subagents and teammates to two cases: adversarial review of freshly produced output, and one-shot context reading that returns a summary.
dsh-steward
stallenlu/dsh-steward
Read-only diagnostics for a DSH install — boot-crash logs and the cause named in them, config drift against a recorded fingerprint, backup freshness, workspace growth, plugin updates, host-version compatibility, duplicate client ids, and model availability — plus an action layer that always shows a plan first and needs a single-use fingerprint and explicit confirmation before anything is written. A checkup also runs 45 seconds after every host start; when the 3-hour probe cache is stale it sends a one-line test prompt to the default model and a few models of each configured provider (model.probeOnReport can switch this off). Registers the agent tools dsh_steward_report and dsh_steward_act (clean caches via dsh-disk-cleaner, backup via dsh-config-manager, disable or enable a bundle, set the default model; execute takes the plan's hash plus confirm: true) and a system-prompt section telling the agent to run the report first when something crashed.
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.
dsh-global-prompt
kunkun24/dsh-global-prompt
Add one global prompt or persona that is injected into every new DeepSeek Harness conversation.
dsh-github-oss-radar
otto883/dsh-github-oss-radar
Standing GitHub-first open-source check: a system-prompt section makes the agent extract 1-4 keywords on every new request and make one cached, rate-limit-aware github_search call, so the answer can list up to five reusable repositories with stars, language, license, last push and topics.