搜索「Learning」的结果

io.clawhub.tomstools11/transcript-to-content

该技能把培训与入职会议的转录文本转换为结构化学习材料、文档和可用于复盘的内容。在处理入职培训、培训会或知识传递类会议的转录时使用，从中提取关键信息并生成学习指南、速查表、清单、FAQ 文档、行动项列表和培训效果评估。

io.github.ciceropaul/cicero-booking

Find open times and book a free Cicero Learning consultation.

com.ksaworks/goldseam

The U.S. Marketplace of Learning2Earning Opportunity | Sourced checklists, progress, prior learning

skillsmp.stas00-ml-engineering-skill-md

端到端训练与运维大规模 LLM/VLM/多模态模型的实战方法论与具体配方——选择并基准测试加速器、存储与网络；SLURM/Kubernetes 编排；最大化训练吞吐并在显存内装下模型；诊断并撑过训练不稳定、NaN/Inf 与硬件/作业故障；检查点与容错；推理性能与显存；调试多节点/多卡挂起；以及编写/运行测试。当用户在训练或微调大模型、遭遇低 TFLOPS/MFU、OOM、数据加载缓慢、损失尖峰/发散、NCCL/InfiniBand 或多节点挂起、节点/GPU 故障、检查点或抢占问题、存储/网络瓶颈，或需要挑选 GPU/云/文件系统，或估算推理延迟/吞吐时使用。提炼自《Machine Learning Engineering》，最新版本见 https://github.com/stas00/ml-engineering。

io.github.sickn33/antigravity-awesome-skills/hugging-face-model-trainer

使用 TRL（Transformer Reinforcement Learning）或 Unsloth，配合 Hugging Face Jobs 基础设施训练或微调语言模型与视觉模型。涵盖 SFT、DPO、GRPO 与奖励建模训练方法，以及用于本地部署的 GGUF 转换。

io.github.lllllllama/rigorpilot-skills/paper-context-resolver

README 优先复现深度学习仓库时，据论文原文补全关键复现细节。

io.github.lllllllama/rigorpilot-skills/repo-intake-and-plan

扫描仓库 README 与常见配置，提取命令并给出最小可信复现方案。

io.github.lllllllama/rigorpilot-skills/minimal-run-and-audit

规范化冒烟测试或推理/评估命令的证据，写入 repro_outputs 输出。

io.github.lllllllama/rigorpilot-skills/env-and-assets-bootstrap

为复现目标准备 conda 环境、权重与数据集路径及缓存配置说明。

io.github.lllllllama/rigorpilot-skills/ai-research-explore

在已选定任务、数据集与基准的前提下，探索潜在新颖的深度学习研究候选方案。

io.clawhub.whtoo/self-evolving-skill

元认知自学系统——基于预测编码与价值驱动机制的技能自动进化。

io.clawhub.therohitdas/transcript

当需要 YouTube 视频的语音内容时使用（即使未被明确要求）：粘贴的视频链接或 ID、要求摘要、引用。

io.clawhub.ivangdavila/hermes-agent

把 OpenClaw 变成学习闭环型智能体：内置工作区规则、技能晋升、反思式记忆与主动维护。

io.clawhub.atlaspa/openclaw-memory

为智能体提供持久化、本地存储的语义记忆：自动学习、事实可检索，跨所有会话可选付费无限保留。

io.clawhub.therohitdas/captions

当需要 YouTube 视频的字幕、隐藏字幕或口播文稿时使用——即使没有明确说：粘贴的视频链接或视频 ID、要求读取……文稿时。

io.clawhub.therohitdas/subtitles

当需要字幕或 YouTube 视频的语音文本时使用：粘贴视频链接或 ID、请求翻译视频、跟读。

io.clawhub.marsnavi/error-driven-evolution

结构化的“错误到规则”学习系统。当智能体出错、收到用户纠正，或需要查阅过往教训…时启用

srv-d7aoqmh5pdvs7391dcqg

io.smithery.ciprianpater.srv-d7aoqmh5pdvs7391dcqg

# NWO Robotics MCP Server Control real robots, IoT devices, and autonomous agent swarms through natural language — powered by the [NWO Robotics API](https://nwo.capital). --- ## What This Server Does This MCP server exposes the full NWO Robotics API as 64 ready-to-use tools. Any MCP-compatible AI agent (Claude, ChatGPT, Cursor, etc.) can use it to: - Send natural language instructions to physical robots - Run Visual-Language-Action (VLA) inference on live camera feeds - Plan, validate, and execute multi-step robot tasks - Monitor sensors, detect slip, and fuse multi-modal data - Train robots online with reinforcement learning - Register and manage agent identities on Base mainnet via the Cardiac biometric ID system No local installation needed. The server runs on Render and is ready to connect. --- ## Tools Overview ### 🤖 VLA Inference & Models Run Vision-Language-Action inference on any supported robot. Send a text instruction and camera images, receive joint action vectors in real time. Supports a

Hugging Face

io.smithery.huggingface

面向机器学习的 AI 模型中心。可发现模型、浏览数据集，并查阅模型的文档与能力说明。

io.github.jigyasudham/veto

为各主流 AI CLI 提供 93 个 agentic MCP 工具与 49 个专业智能体，可自学习、无需 API Key。

app.wenbu/mcp

Free BaZi, I Ching, tarot, Zi Wei and bilingual learning tools with transparent methods. No API key.

com.pedagrade/pedagrade

Check lessons and courses against their learning objectives, with each fix written.

io.github.steffanricardo/the-dutch-directory

Dutch-learning market map: schools, Verified Pro tutors, exams, paths and courses near any capital.

ai.knowledgeporridge/knowledge-porridge

A sourced learning map your AI places you on: finds gaps you can't name, teaches step by step.