Plugins

Modo de aprendizaje local-first: hilos de aprendizaje entre sesiones con explicaciones por fuente.

Exports metadata-only DSH turn, model, tool, approval, retry, and error events to Tuning Engines for governed traces, policy evaluation, cost analysis, and Work Session review, with a disk-backed retry queue.

Learning Mode agent preset: a coding agent that teaches while coding — concrete scenario-grounded explanations, Socratic guidance, and TODO(你) practice blanks, modeled on Claude Code's Learning output style; installable via dsh plugin add (dsh-learning-mode on npm).

Durable citation-thread learning companion for DeepSeek Harness conversations

Plugin de modo de aprendizaje Feynman: bucle enseñar → reexplicar → evaluar → reexplicar de nuevo, renderizado como tarjetas de lección en HTML enriquecido (diagramas mermaid + resaltado de código con shiki).

Extensión de asistente de aprendizaje para DeepSeek Harness (dsh): tutoría DeepTutor para tu agente — explicaciones detalladas, preguntas de autoevaluación, rutas de aprendizaje, búsqueda en una base de conocimiento personal (RAG) y archivado de notas (prioriza HTTP/WS con alternativa CLI; se adapta automáticamente a local/r

Deep-collaboration writing agent for DSH: per-user writing-style learning from edit pairs, clarify→outline→section-writing→red-team→reader-gallery flow, project-to-report synthesis (lab report / product intro / survey / README), 41 MCP tools, and web selection-improve UI with in-app file preview.

Self-learning habit engine for the DeepSeek Harness — detects user-correction signals, judges habits with a low-cost model on threshold, settles candidates behind a two-level human gate

A cozy offline vocabulary trainer for the whole family: 1094 curated words, spaced repetition, 6 quiz types, spelling games and a lazy large-screen mode; opens as a sidebar panel and also runs standalone as one HTML file.

Deep-collaboration writing agent for DSH: per-user writing-style learning from edit pairs, clarify→outline→section-writing→red-team→reader-gallery flow, project-to-report synthesis (lab report / product intro / survey / README), 41 MCP tools, and web selection-improve UI with in-app file preview.

Rewrites each request against a learned prompt profile and automatically updates habits, anti-hallucination rules, and learning records.

Turn any markdown, local folder, or GitHub learning repo into a guided course inside DeepSeek Harness: gated skill-tree progression, BKT mastery tracking, SM-2 spaced repetition.

Evidence-backed Skill self-evolution for DeepSeek Harness: redacted trajectory learning, quarantined proposals, arena validation, canary monitoring, automatic rollback.

Beginner starter pack for DeepSeek Harness: welcome flow, 0→1 learning path, scenario-based plugin recommendations and a self-check checklist, paired with the dsh-handbook-zh Chinese tutorial repo.