Plugins

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.

Convierte un enlace de Xiaohongshu, Douyin, TikTok, YouTube o X en texto: transcripción con códigos de tiempo, texto en pantalla, una descripción y OCR de cada imagen, leyenda y metadatos. Monta el servidor MCP alojado mediante streamable HTTP.

Un compañero de píxeles que vive en el área de chat: eclosiona de un huevo en uno de tres sprites o uno personalizado dibujado por el LLM a partir de una descripción de texto, salta solo sobre las burbujas de mensajes, se controla con WASD, charla en personaje a través de los modelos que ya configuraste y lleva un sistema de crianza (ánimo/energía/salud, niveles, tienda) impulsado por el uso real de tokens.

Adjuntos de imagen nativos para DeepSeek solo texto en la Web GUI: las imágenes pegadas o soltadas aparecen como miniaturas en la sesión y, antes del envío, el host las lee con la API de visión gratuita Zhipu GLM-4V-Flash (cadena de respaldo glm-4v-flash) y sustituye la descripción, de modo que DeepSeek responde sobre la imagen mientras el original se conserva en el historial.

Reutiliza el modo de visión integrado de DeepSeek web para modelos solo de texto: la herramienta deepseek_vision controla la automatización de navegador local deepseek-vision-cli (ayuda de inicio de sesión manual, deep-think activado, cierre automático del navegador) y devuelve descripciones de imágenes como texto.

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.

Convierte una necesidad declarada en una elección de plugin: una skill de agente que consulta un catálogo de todo el topic `dsh-plugin` (más de 2600 repos, recrawleado cada 6 horas, descripciones en chino desde Workers AI) mediante una API de búsqueda rankeada, y devuelve el comando `dsh plugin add` correspondiente.

Herramienta `describe_image`: un puente de visión que envía imágenes a mimo-v2.5 mediante la API opencode Zen (credencial `OPENCODE_GO_API_KEY`, ruta gratuita primero con respaldo de pago) y devuelve descripciones de texto para modelos solo de texto, con paso nativo y transcodificación ImageMagick de formatos SVG/TIFF/HEIC.

Puente de visión con autodescubrimiento para agentes DeepSeek Harness solo de texto: encuentra automáticamente un modelo capaz de procesar imágenes entre tus proveedores configurados y devuelve descripciones de las imágenes como texto plano mediante una herramienta de visión.

Adaptador DeepSeek aumentado con visión: un modelo con capacidad de visión describe la imagen de entrada y luego un modelo DeepSeek solo de texto razona sobre esa descripción.

Monta una fila en la composición y todas las tarjetas de plugin en la página de la lista de plugins de Ajustes Web obtienen una descripción bilingüe (zh/en); también publica el servicio pluginDescriptions para que otros plugins puedan registrar sus propias descripciones.

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.