Plugin

Adds a Screen-sense submenu (turn on, turn off, and an interval of 15, 30, 60 or 120 seconds) to the dsh-pet desktop right-click menu, forwarding each choice to dafeiyu-screensense. dsh-pet exposes no menu extension point, so this plugin appends a marked patch to its renderer.js after backing the original up to renderer.js.dafeiyu.bak; the patch is idempotent and is re-applied when dsh-pet is reinstalled.

Locks the model's reasoning, replies and tool-call descriptions to a chosen target language (Simplified Chinese by default) with system-prompt sections at the head, middle and tail of the prompt, offering three strength levels, an auto mode that follows the DSH interface language, a settings panel that shows the language currently in effect, and a sidebar quick switch.

GitHub project search and analysis: describe your idea in one sentence and the agent searches GitHub for related projects, ranks them by relevance weighted with stars, and returns a structured card — last updated, relevance, stars, weighted score, language and a one-line description for each project. Pick a few repositories and it reads their README, dependency manifest, directory tree and key files to lay out their architecture — so you stand on the shoulders of giants before you start building.

Converte un link Xiaohongshu, Douyin, TikTok, YouTube o X in testo: trascrizione con timecode, testo a schermo, una descrizione e OCR di ogni immagine, didascalia e metadati. Monta il server MCP ospitato su streamable HTTP.

Un compagno in pixel che vive nell'area chat: schiude da un uovo in uno di tre sprite o in uno personalizzato disegnato dall'LLM da una descrizione testuale, salta da solo sopra i fumetti dei messaggi, è controllabile con WASD, chiacchiera in character tramite i modelli che hai già configurato e porta un sistema di allevamento (umore/energia/salute, livelli, negozio) alimentato dal consumo reale di token.

Allegati immagine nativi per DeepSeek solo testo nella Web GUI: le immagini incollate o rilasciate appaiono come miniature nella sessione e, prima dell'invio, l'host le legge con l'API di visione gratuita Zhipu GLM-4V-Flash (catena di fallback glm-4v-flash) e sostituisce la descrizione, così DeepSeek risponde sull'immagine mentre l'originale viene conservato nella cronologia.

Riutilizza la modalità visione integrata di DeepSeek web per i modelli solo testo: lo strumento deepseek_vision pilota l'automazione browser locale deepseek-vision-cli (aiuto all'accesso manuale, deep-think attivo, chiusura automatica del browser) e restituisce descrizioni delle immagini come testo.

给 DeepSeek Harness 工具加上模型填写的步骤说明

Search field on the DeepSeek Harness Plugins page that filters the installed and official plugin cards as you type, matching each card title, description and package name; space-separated keywords must all match.

Find and compose DSH plugins from a task description, then open an independent chat environment or install the plan into the current profile.

Ships a skill about writing DSH skills - SKILL.md frontmatter and root precedence, how to phrase a description so it actually triggers, length and splitting rules, and an A/B check that the finished skill changes agent behaviour. The package also carries the checker the skill uses to validate a skill directory.

Searches a database of past motor-repair cases by fault description, motor rating and brand, and lets new diagnoses be saved back for future retrieval.

Three independent language channels for model output — tool-call descriptions (every tool-call card title, including run_code in PTC-style presets), thinking, and replies — each set to follow the web GUI language, force a specific language, or turn off (default: only descriptions, following the GUI). One global runtime-context prompt directive on the host; the client half reports the GUI language; a Settings plugin card switches the modes.

Trasforma un'esigenza dichiarata in una scelta di plugin: una skill agente che interroga un catalogo dell'intero topic `dsh-plugin` (oltre 2600 repo, riscansionato ogni 6 ore, descrizioni in cinese da Workers AI) tramite un'API di ricerca con ranking e restituisce il corrispondente comando `dsh plugin add`.

Strumento `describe_image`: un ponte di visione che invia le immagini a mimo-v2.5 tramite l'API opencode Zen (credenziale `OPENCODE_GO_API_KEY`, prima rotta gratuita con fallback a pagamento) e restituisce descrizioni testuali ai modelli solo testo, con passthrough nativo e transcodifica ImageMagick di SVG/TIFF/HEIC.

Ponte di visione con scoperta automatica per agenti DeepSeek Harness solo testo: trova da sé un modello capace di immagini tra i provider configurati e restituisce descrizioni delle immagini come testo semplice tramite uno strumento di visione.

Adattatore DeepSeek aumentato con la visione: un modello capace di visione descrive l'immagine in ingresso, poi un modello DeepSeek solo testo ragiona su quella descrizione.

Monta una riga nella composizione e ogni scheda plugin nella pagina dell'elenco plugin delle Impostazioni web ottiene una descrizione bilingue (zh/en); pubblica anche il servizio pluginDescriptions in modo che altri plugin possano registrare le proprie descrizioni

Bundles the 32 gis/ skills of opengis-skills (GDAL, QGIS, GeoServer, PostGIS, PROJ, PDAL, GRASS GIS, JTS, GeoPandas, Shapely, CesiumJS, OpenLayers, Leaflet, deck.gl and more) into the DSH skill catalog; only names and descriptions appear up front, and instruction bodies plus reference documents load on demand.

Shows what each installed skill costs in the model context and hides a skill from the catalog without deleting it. Lists every skill found on disk with the exact catalog line the model receives (description normalized and truncated at the catalog cap), its body size and token estimate; previews the catalog message byte-for-byte as the agent will receive it, compares that with the copy already published in the current session, and reports skills on disk that never reach the catalog (invalid frontmatter, or shadowed by a higher-priority root). Hiding writes disable-model-invocation into frontmatter and keeps the file, so the skill still works via /name. Also imports skills from ClawHub, Skills.sh and GitHub URLs and uninstalls user-owned ones.

Sorts every loaded skill into one or more user-owned workspaces in a right-sidebar tab: each workspace is its own category list plus where every skill sits, categories are created, renamed, reordered and deleted in place, and skills are dragged or picked between them. A first run can let the profile model build the first classification, or place skills into categories the user built first; clicking a row copies its /skill-name and hovering unfolds the description the skill ships.

Structured image recognition: local sharp measurements plus a cloud vision model return description, OCR with coordinates, object locations and fine-grained attributes in one call; a fingerprint cache makes repeated images return in milliseconds without spending model quota.

Renders installed DSH plugin titles and descriptions in Simplified Chinese: at startup it translates the plugins the local JSON cache lacks through the harness LLM service, then projects { en, zh } metadata for resolveText() to render — no DOM changes, no third-party API.

Tool-surface snapshot and drift gate: baselines the full visible tool registry (name/description/parameters, MCP tools included) into a committable JSON file and warns loudly when an upgrade adds, removes or reshapes a tool.