dsh-run2skill
Turn explicit DSH session experience into reviewable native Skills
56 results
Turn explicit DSH session experience into reviewable native Skills
Learning assistant extension for DeepSeek Harness (dsh): DeepTutor tutoring for your agent — deep explanations, self-test questions, learning paths, personal knowledge-base search (RAG), and note archiving (HTTP/WS first, CLI fallback; auto-adapts local/r
Vibe Learning,DeepSeek Harness 的一款氛围学习插件
DSH learning-mode plugin with a global local-first learning thread.
Standalone DeepSeek Harness plugin: continual harness self-evolution. The agent persists and refines reusable prompt notes, memories, skill contracts, and subagent specs through small evidence-backed edits, with automatic refinement gates, rollback, and prompt injection.
Feynman learning-mode plugin for DeepSeek Harness: /learn on|off, structured lesson cards, rich HTML teaching.
Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles policy, audit, usage, and token economics.
DeepSeek Harness plugin: quiz-style reading (答题式阅读) of any Markdown document — 5-stage game loop (diagnose→level→guided reading→checkpoint→settle) with a Web sidebar panel and a reading-area tab.
Evidence-driven learning memory and automation for Git-native AI agents
An eye that grows: accumulated design taste for DSH agents. A taste corpus + codified principles that sharpen with every example you feed — review designs against learned judgment, not a fixed ruler.
输出 token 压缩:让 agent 用紧凑的穴居人语回复(省 ~65% 输出 token),代码/命令/错误保持字节精确;token 下沉点审计(caveman learn:safe fix/offload/habit/load-bearing 分类)。受 JuliusBrussee/caveman(86k★ MIT)启发。
BrainAgent — brain-inspired plugin for DeepSeek Harness (dsh): a pipeline of heuristic filters, statistical memory stores and context injections; reward-ledger + UCB1 bandit learning loop (RL-lite)
Tacit learns what you leave unsaid in your prompts — from messy turns and your own corrections, with zero clicks — and tells the agent how to compensate, on every turn, via a system-prompt section you can read and edit.
会话记忆 → OKF 知识沉淀插件:预测驱动的神经自我学习记忆系统。把会话中高价值内容按 OKF v0.1 规范沉淀为长期记忆,跨会话自动唤起。Session-to-OKF memory plugin with neuro-self-learning (predictive recall, uncertainty-driven capture, reinforcement feedback).
DeepSeek Harness plugin: learning agentic router — rule + UCB + LinUCB + k-NN experts under an EXP3 meta-selector, with a durable quality-reward flywheel, REAL model switching via the session request-header precedence chain, and STEP-LEVEL routing (v1.5.0)
Real Red Alert 2 AI battlefield for DeepSeek Harness with fog-safe control and post-match learning
Retrieved ≠ injected: CBDC-gated memory for DeepSeek Harness — decides how memory is USED (use/verify/ignore decisions, feedback learning, full audit); local SQLite + FTS5, bounded, no extra model call
dsh 插件 · 自动复盘:对话收尾后自动复盘,把有价值的经验蒸馏成可复用的技能(skill)存入技能库,模型可直接调用;支持信号加速触发、手动立即复盘、审批模式与技能库治理(归档/恢复,永不直接删除)。
Image2 (gpt-image-2) generation plugin for DeepSeek Harness with simple relay settings, in-conversation previews, a chat-dock studio (text-to-image / image-to-image / multi-view character consistency) and a reusable prompt/flow preset library. Community fork of JuneLearn/dsh-image2-draw with gateway compatibility fixes.
Voice practice mode for the DSH web app: bilingual (中文 / English) conversation output plus read-aloud (TTS) and speech input (STT). Adds a 语音交流 dialog-mode toggle to the composer.
Interactive Learning mode and native learning activities for DeepSeek Harness
DSH 自进化长期记忆插件:回合后 LLM 自动提取记忆、每步召回注入、语义重排检索、冲突合并、learned-* 技能沉淀,附记忆库管理面板。记忆文件默认存于 harness 根目录($DSH_HOME,未设时 ~/.dsh)下的 imemory/ 子目录,可用 config.memDir 覆盖。
Agent-loop change review for the DeepSeek Harness web GUI: after every agent loop it snapshots the workspace, detects file/code changes, and offers one-click revert plus a right-sidebar diff review panel. 官方双面 dsh 插件(host + client),零依赖。
自改进 AI agent:内置学习回路——从经验自动创建技能、使用时改进、FTS5 会话搜索+LLM 摘要跨会话回忆、Honcho 辩证用户建模、跨平台网关(Telegram/Discord/Slack)、调度自动化、子代理并行、serverless 休眠唤醒。受 NousResearch/hermes-agent(154k★ MIT)启发。