Plugins
Explora, filtra e instala plugins de DeepSeek-Harness.
370 plugins encontrados
dsh-media-kit
daphne999/dsh-media-kit
Pull frames and audio out of a local video with ffmpeg and hand back plain file paths, so the agent can look at the frames with its own vision. Five tools: probe, evenly spaced frames, one frame at a timestamp, scene-change frames (the practical version of frame-by-frame), and audio extraction. No models, no uploads, no routing guesswork.
dsh-memelens
whatif146/dsh-memelens
Explains Chinese internet memes to an agent: registers a meme_explain tool that returns the meaning, tone, origin and lifecycle of a sticker, which memes can and cannot be combined, occasions to avoid, and both a meme-version and a plain-version reply. Answers come from a local memory store with spacing-effect decay, falling back to a user-configured OpenAI-compatible vision endpoint (BYOK).
dsh-review-outbox
zjukop3/dsh-review-outbox
Evidence-gated acceptance for research reports: claims, citations, data scope and method limits each need a tick plus written evidence before a deliverable can pass, with same-artifact revision history and a standalone SHA-256 receipt that says when the bytes moved.
dsh-wenjian-team
sarsgy-wenjian/dsh-wenjian-team
Long-form manuscript verification team for DSH: installs 10 skills that run a read-only content/structure check, three-tier revision proposals, a human-selection gate, exact replacements and a final re-check; it never edits the manuscript by itself and requires Agent Teams to spawn teammates.
dsh-vision
young-felix/dsh-vision
Ask a vision-capable model about a local image from any session, including sessions whose own model is text-only. On the default path the plugin calls the host's route in-process with ctx.llm.stream(), so the host's credentials stay inside its provider adapters; only the optional direct/custom OpenAI-compatible routes read one key (from the plugin config or an apiKeyRef into ~/.dsh/.credentials.yaml).
dsh-feiyu-vision
xxgj666/dsh-feiyu-vision
Image understanding for DSH: describe an image and read the text in it through Zhipu GLM-4V (needs a Zhipu API key, free tier), with optional person identification through Volcengine Ark and anime-only reverse image search through SauceNAO or trace.moe (each needs its own key); ffmpeg must be installed for GIF/WebP input. Keys and the ffmpeg path are set on the plugin's own settings page.
dsh-pf-stream
weilv-d/dsh-pf-stream
Local video understanding for agents: extracts keyframes adaptively based on motion and pauses, inspects any timestamp at full resolution, and aligns visuals with dialogue from embedded subtitles or configured ASR. Requires ffmpeg and ffprobe; clips without subtitles also need a transcription engine for dialogue (a ~190 MB local whisper model, a cloud API key, or the official voice-input model).
dsh-computer-use
lqq151510/dsh-computer-use
macOS computer use with eight computer_* tools: accessibility-tree and Vision OCR screen reading, actions by element index or visible label that also reach background windows, and CoreGraphics mouse and keyboard events with a resident low-latency daemon for game-grade input sequences; its Swift helpers compile on first use, so there is no runtime dependency.
galadon
lumos-789/galadon
A five-stage engineering loop for agent-built projects — spec, build, verify, ship, learn — with one artifact and one gate per phase, so an agent always knows the single next action. Role policy, project templates and deployment sit behind explicit ports: swap the implementation without rewriting the loop. Its scaffold generator lays out the internal layers of a project — `init --layout {none,webapp,service,plugin} --stack {python,node,none}` — from nine layers sampled out of three unrelated production projects: entry docs, an OpenSpec plan face, a spec truth layer (INDEX, one file per domain, TESTING, CONSTITUTION), a wiki split into knowledge / progress / runbook, the six `.agents/` slots, server+web, scripts/deploy/config, tests+e2e and a gitignored out/. Non-none layouts also gate the directory contract and compile every source root. Ships a Python CLI (init/next/check/ship/new) plus a local command adapter and an SSH/systemd adapter with release directories, an atomic current/previous switch, a deploy lock, a commit-versioned JSON probe and automatic rollback on a failed probe; bootstrap and teardown provision and remove the unit and the reverse-proxy block idempotently and refuse to delete a root they did not create. Includes a runnable example workspace and a skill that keeps the agent on one phase at a time. Requires Python 3.10+ and PyYAML; remote deploys need SSH access, rsync, systemd and Caddy on the target.
dsh-pet-watch
learner202699/dsh-pet-watch
桌宠陪看:定时截屏,让视觉模型点评你正在看的画面,投喂给 dsh-pet 的气泡。Pet watch-along for DSH: screen sampling + a vision model + dsh-pet's bubble.
dsh-crash-guard
zxzc114514/dsh-crash-guard
Intercepts startup crashes, isolates broken frontend plugins, and recovers GUI cleanly with revision-bound quarantine.
dsh-codex-runner
halftin/dsh-codex-runner
Runs local Codex CLI tasks from DSH on Windows with background execution, progress queries, follow-up instructions, completed chat records, and optional supervision; requires Node 22.23.4+, DSH >=0.2.1-rc.3 <0.3.0, and an installed, authenticated Codex CLI.
dsh-fairy-zzz-for-jediliu
jediliu005/dsh-fairy-zzz-for-jediliu
Skin H.D.D Fairy III (Zenless Zone Zero) para DSH. Saludos horarios: el modelo escribe 5 líneas/día (hasta 20 caracteres); GPT-SoVITS sintetiza localmente. Audio: today -> latest -> bundled audio. Lectura: marcador final > heurística de longitud; respuestas largas se resumen a 1 frase. MD5: 1 lectura por respuesta; cambio de sesión, silencio. Fork con package/rutas/almacenamiento propios, resumen con límite de tasa, motor POST-only, cachés TTS/saludos acotadas y logs client revision/decision trace locales. Fork de AssassinVIX/fairy-zzz-plugin (upstream dsh-fairy-zzz); instala uno solo: ambos ocupan el mismo fullscreen DSH. Saludos dinámicos/resúmenes hablados requieren clave DeepSeek compatible en ~/.dsh/fairy-tts.json o DEEPSEEK_API_KEY; sin clave, solo saludo incluido.
dsh-auto-convert
yimengsuper2432/dsh-auto-convert
Prepara archivos antes de que los abran read, read_image y las herramientas vision. Reduce imágenes de más de 2048 px o 8 MB (un reintento a 1280 px durante el mismo turno), convierte BMP/TIFF a PNG y corrige cargas mal etiquetadas examinando sus bytes. Convierte docx/xlsx/pptx, PDF con capa de texto, csv/tsv y html a Markdown sin programas externos.
dsh-custom-vision
lightingha/dsh-custom-vision
Usa tu propio modelo vision compatible con OpenAI en DeepSeek Harness: describe las imágenes antes de que el modelo principal vea la solicitud y ofrece `image_understand` para leer gráficos, capturas, UI y OCR.
dsh-model-manager
jyshangguan/dsh-model-manager
Gestor de modelos basado en roles para DeepSeek Harness: asigna modelos a planificación, ejecución, visión y rol principal; enruta el trabajo de subagents por rol y escala al rol de planificación las sesiones que invocan una skill de planificación (grilling / grill-me).
dsh-relay-isolation
alannerfranklin/dsh-relay-isolation
Prepara un `DSH_HOME` separado para el relay AgentRouter (perfil mínimo y launcher) y proporciona egress de red controlado al agente sandboxed.
dsh-auto-vision
thanderming/dsh-auto-vision
Cuando el modelo seleccionado no puede ver imágenes, las lee con un modelo de visión del mismo provider y pasa la descripción al modelo de texto.
dsh-video-eyes
fj7937290-sys/dsh-video-eyes
Lee vídeos con un modelo de solo texto: con ffmpeg instalado, toma fotogramas cada 0,1–10 segundos y crea hojas de contacto con el timecode real de cada imagen; extrae el audio y lo envía a iTingnao para una transcripción con marcas de tiempo (requiere ITINGNAO_API_KEY), y describe cada hoja con un modelo del host capaz de procesar imágenes. Funciona sin otro plugin de visión. Un slider del composer define el intervalo; los archivos solo de audio se transcriben sin muestrear fotogramas.
dsh-local-library
fucaplos/dsh-local-library
Biblioteca local de documentos para DSH Desktop (solo Windows; se instala con el script PowerShell incluido). Sube los archivos una vez y cualquier conversación podrá buscarlos y leerlos con cuatro herramientas: library_list / library_search / library_read / library_save. La carga, descarga y descarga por lotes se hacen en Settings. Los archivos permanecen en el equipo salvo que actives el modelo de visión opcional, que envía imágenes al endpoint configurado.
dsh-better-answer-view
solstice621/dsh-better-answer-view
Inserta gráficos, tablas comparativas y bloques interactivos entre los párrafos de una respuesta, con estado guardado localmente e historial de revisiones.
dsh-youtube-study-notes
jagathsrujan/dsh-youtube-study-notes
Convierte un enlace YouTube en apuntes: obtiene los subtítulos publicados, opcionalmente lee la pantalla con un modelo de visión y luego pide tus notas para unirlo todo en un documento. Requiere python3, ffmpeg y yt-dlp en PATH; si faltan, el skill se detiene con instrucciones de instalación.
dsh-prompt-inject
379385796-sys/dsh-prompt-inject
Adaptación MIT del gestor de plantillas de prompt de H1a3x, con ConfigForms nativos, guardado verificado por revisión, selección global/workspace y compatibilidad comprobada con Windows Desktop RC3/RC5. No puede instalarse junto al original H1a3x/dsh-prompt-inject.
dsh-glm-web-search
czpghost/dsh-glm-web-search
Búsqueda web, lector web y visión de Z.AI (GLM) para DeepSeek Harness, con autenticación mediante inicio de sesión OAuth con correo Z.AI en vez de una API key.