misakanet
Deployment scripts for MisakaNet Workers
11 results
Deployment scripts for MisakaNet Workers
Feynman learning-mode plugin for DeepSeek Harness: /learn on|off, structured lesson cards, rich HTML teaching.
Task planning with experience muscle-memory for DeepSeek Harness: condition-reflex recall of past solutions + LLM-driven capability matching + auto-persisted lessons. Zero keys, zero hard-coded paths.
DeepSeek Harness plugin for synchronized K12 English PPTX and DOCX lesson materials
Solve the AI goldfish brain: a personal memory layer for DeepSeek Harness — preferences, project conventions, workflows, and error lessons, stored locally as auditable, evidence-backed Markdown/JSON. 解决 AI 金鱼脑:偏好、项目约定、工作方式与纠错教训的本地可审计记忆层。
Education toolkit for DeepSeek Harness agents: lesson-plan skeletons by grade band, quiz validation, analytic rubrics, grading sheets, study plans, flashcards, and text readability levels
Configurable user-confirmed lessons that help DeepSeek Harness avoid repeating mistakes.
Teacher-focused vertical industry preset for DeepSeek Harness — supports school teachers and tutoring teachers with mode switching
教学课件大纲生成工具插件(DeepSeek Harness dsh-plugin)— 输入主题,输出结构化课件大纲
记忆审计技能:对 AI agent 的记忆文件(MEMORY.md/LESSONS.jsonl/规则库)做静态体检,扫出越界宣称(已达 AGI/最强/100% 成功)、无证据完成声明、重复条款;报告是候选不是判决,每条带行号与原文供人工复核。适用:审计自己或他人的 agent 记忆、季度记忆体检、向团队展示记忆质量时。
Tiered task queue for DSH↔Hermes coordination: queue.json is the single source of truth; tasks are enqueued by DSH mechanisms (review/lesson/reset) and consumed by the Hermes-side cron with a lease/claim model. Also provides the busy-mutex for serializing Hermes calls from the approve fast path.