Plugins

Mode d'apprentissage local-first : fils d'apprentissage inter-sessions avec explications par source.

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 mode d'apprentissage Feynman : boucle enseigner → reformuler → évaluer → réexpliquer, rendue en fiches de cours HTML riches (diagrammes mermaid + coloration syntaxique shiki).

Extension d'assistant d'apprentissage pour DeepSeek Harness (dsh) : tutorat DeepTutor pour votre agent — explications approfondies, questions d'auto-évaluation, parcours d'apprentissage, recherche dans une base de connaissances personnelle (RAG) et archivage de notes (HTTP/WS en priorité, repli CLI ; s'adapte automatiquement au local/distant).

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.