Plugins

P0–P4 deterministic-first permission gate with permissive tier, learning sedimentation and approval-history UI; hard-deny credentials and protected paths, auto-allow internal read-only tools.

Forces periodic Engram memory recall and save reminders for DeepSeek Harness agents: injects a dynamic system-prompt context that reminds the model to load prior session memory at the start of a session, and to save new decisions/bugfixes/learnings every

Fail-closed network recovery, recommended answers, and safe unattended continuation for DeepSeek Harness.

Dual-model auto-routing plugin: low-cost direct / high-cost upgrade with an escape-learning closed loop (wrong direct answers auto-learn fingerprints, force-upgrading the same fingerprint next time), persisted and interoperable with the Python ModelRouter.

Motor de hábitos con autoaprendizaje para DeepSeek Harness: detecta señales de corrección del usuario, juzga los hábitos con un modelo de bajo coste al alcanzar un umbral y consolida los candidatos tras una puerta humana de dos niveles.

Un entrenador de vocabulario offline y acogedor para toda la familia: 1094 palabras seleccionadas, repetición espaciada, 6 tipos de cuestionarios, juegos de ortografía y un modo perezoso para pantalla grande; se abre como panel lateral y también funciona de forma autónoma como un único archivo HTML.

Agente de escritura de colaboración profunda para DSH: aprendizaje del estilo de escritura por usuario a partir de pares de ediciones, flujo aclarar→esquema→redacción por sección→equipo rojo→galería de lectores, síntesis de proyecto a informe (informe de laboratorio / presentación de producto / encuesta / README), 41 herramientas MCP y UI web de mejora de la selección con vista previa de archivos en la app.

Reescribe cada petición según un perfil de prompt aprendido y actualiza automáticamente hábitos, reglas antihallucinación y registros de aprendizaje.

Legal training workbench: three-pane academic UI that reads the "Minglü" (lawagent preset) learning profile (case dossiers, flashcards, wrong-answer book, notes) and sends instructions into a Minglü session with one click.

Coordinates bounded project recall from compatible memory and learning providers, with shared settings and provider lifecycle management.

Report stage — academic paper writing for asset pricing and machine learning research. Ships one skill.

Data stage — data discovery and quality assessment for asset pricing and machine learning research. Ships one skill.

Literature review stage — search, synthesis, and citation-chain tracking for asset pricing and machine learning research. Ships one skill.

Model training stage — end-to-end analysis, model training, and estimation for asset pricing and machine learning research. Ships one skill.

PPT stage — presentation generation (Beamer/Quarto) from the paper for asset pricing and machine learning research. Ships one skill.

Project-based learning coach: a subject-agnostic teaching engine plus swappable domain packs (Unity/C# included), shipped both as a DSH skill and as an installable bundle. The skill protocol enforces attempt-first teaching and graded hints; a zero-dependency validator rejects ability claims their evidence does not support and blocks stage acceptance while blockers are open.

dsh (DeepSeek Harness) plugins for project-level persistent context: session archive with a mechanical index, memory consolidation (CONTEXT.md + MEMORY.md), low-frequency skill autolearn, and automatic handoff.

Algorithm learning toolkit syncing Codeforces and AtCoder submissions, profiling weaknesses, generating AI training plans, and tracking spaced-repetition reviews across a 114-lesson algorithm curriculum.

Bridges the agent to a persistent OKF memory vault over MCP stdio: a Python server (SQLite FTS5 + Markdown) with 10 tools for searching and storing decisions, facts, learnings, conventions, profiles and sources.

Real Red Alert 2 AI battlefield for DeepSeek Harness with fog-safe control and post-match learning

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.