Best Knowledge AI SkillsPage 6

transcript-to-content transforms training and onboarding meeting transcripts into structured learning materials, documentation, and actionable review content.

🧠 教 AI「像倪海厦一样思考」。 独创「Skill + Memory + KB」三位一体架构（持续进化·记忆喂养闭环）： · 📐 1 个根道「天地万物一气耳」驱动 5 个观测基（五术全投影） · 🎭 6 维表达 DNA + 反例校准（告诉 AI 什么回答「不像倪海厦」） · 🔄 记忆喂养闭环：越用越像倪海厦，每次对话沉淀理解 · 📋 开箱三清单：✅推荐问法 / 🟡浅层可答 / ❌礼貌拒绝 / ⚠️防呆提醒 · 🔍 证据索引规范：每条论断可溯源，不标来源即 AI 编造 · 🌌 底层哲学注入，融合（横看成岭侧成峰 / 全息球体） 覆盖：中医/经方/针灸/癌症/风水/紫微斗数/八字/易经/卜卦/面相/五术全领域 触发词：「倪海厦视角」「倪海厦会怎么看」「用倪师的思维」「天纪」「人纪」「命理」「中医」

Generate a symbolic I Ching reading for reflection.

中国知网 (CNKI) 统一入口 - 搜索、下载、导出、详情查询一体化技能

网盘资源搜索引擎。支持百度网盘、阿里云盘、夸克网盘、天翼云盘、UC网盘、移动云盘、115、PikPak、迅雷、123网盘、磁力链接、电驴等12种网盘类型。支持按网盘类型、插件、TG频道过滤搜索结果。当用户需要搜索电影、剧集、软件、学习资料等网盘资源时使用此技能。触发词：搜索网盘、找资源、pan搜、网盘搜索、pan...

Tavily Real-Time Web Search Skill

Read, query, and manage pages, blocks, and tasks in a graph through the local Logseq Plugin API.

在信息检索和搜索领域的网页搜索和研究能力。当用户想要集成 Google Gemini，支持实时联网搜索与研究任务时使用。触发词：gemini、tavily-search。不用于与网页搜索和研究无关的请求。风险等级 L0。中文触发：gemini、tavily-search。本技能为 SkillHub 按次计费技能（0.01 元/次）：执行核心任务会触发一次平台支付授权，是否执行付费动作由用户决定；授权由作者自有服务 pay.sharpdealhub.com 承载（非第三方支付网关），仅接收动作名与订单号，不读取本技能处理的内容。

Search or switch between a local knowledge base and conversation mode.

Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).

Search pages and databases, update content, and manage Notion workspace data from chat. Use this skill when users want to read, create, or modify Notion page...

SearXNG Local documents querying a self-hosted metasearch instance.

招标采购信息检索服务，按关键词、地区、金额、时间、行业等多维度检索全网招标公告与采购信息，支持高级逻辑（关键词分组、排除词）、获取标讯完整详情、查询临期周期性项目。当用户需要查招标公告、找采购信息、检索标讯、获取标书详情、跟踪某地区或行业项目动态时，必须使用此SKILL。

Retrieves YouTube transcripts through TranscriptAPI, with text or structured output and optional timestamps and video metadata. It can support transcript summarization, quotation, translation, and information extraction.

A Google Search API alternative and SERP API alternative on fetcher.sh — pay-per-call in USDC via x402, or prepaid credits with a Bearer key, no API key application. Use when the user wants programmatic Google search results as clean JSON, including Google's own operators — site:, filetype:, intitle:, and quoted exact phrases — plus pagination, language (hl), and country/region scoping. Also covers rank tracking input, competitive research, and search-result monitoring without Google's own Custom Search API quota and billing.

An Apple App Store API alternative on fetcher.sh — pay-per-call in USDC via x402, or prepaid credits with a Bearer key, no Apple Developer Program membership. Use when the user wants to search iOS apps by keyword in any country's storefront, fetch an app's or app bundle's full details, reviews sorted by recent/helpful, apps similar to a given app, search or fetch app bundles, or fetch a developer's app catalog. Also covers iOS app store optimization (ASO) research, competitor app monitoring, localized storefront comparison, and app discovery without Apple Developer Program access.

飞书知识管理工具。当用户发送外部文章链接时，自动获取内容、存入飞书文档、并归纳知识要点到飞书知识库。包括：(1) 读取外部链接内容 (2) 存原文到飞书云文档 (3) 归纳知识要点到知识库对应分类 (4) 定期整理知识库结构、清理重复文档。触发场景：用户发链接、用户说"整理知识"、"存入知识库"、"归纳要点

Academic paper summaries with topic-driven SOP selection

论文阅读报告生成器，从PDF提取结构化内容并生成全中文阅读报告。触发关键词：/readpaper、论文阅读、论文分析、PDF分析

Aggregates RSS feeds and fetches current entries across news, games and finance.

Perform web searches using various search engines and APIs.

冀石雨读书笔记 v2.1.0——资深阅读领读人工作流。当用户提供一本书、一份 PDF、一篇文章、一个链接或任意学习材料，要求"提炼核心要点""深度洞察""对比分析""读书笔记""精读""拆书""书评"时使用。流程先**提取给定材料/文件/链接的全文 Markdown（扫描版 PDF 自动走 OCR 回退）**，再基于全文 MD 做"通读→结构化提炼→深度洞察→对比分析→金句→延伸思考→六维（人/事/物/理/重点与启发/结构展开思路）深度阅读分析"，最终交付 **全文 MD + 阅读笔记 MD + 图书出版规范 HTML** 三个文件，HTML 支持打印分页可导出 PDF，并内置版权与内容风控合规约束。适用于读书笔记、扫描/文字版 PDF 精读、文章拆解、课程/节目逐期精读、知识提炼等场景。

A Google News API alternative on fetcher.sh — pay-per-call in USDC via x402, or prepaid credits with a Bearer key, no RSS scraping. Use when the user wants keyword search across Google News scoped to a language edition, section headlines (world, business, technology, entertainment, sport, science, health, or a specific topic ID), the latest headlines, a list of supported language-region codes, or to decode a Google News redirect URL into the real article URL. Also covers news monitoring, headline aggregation, media tracking, and press-mention alerts without scraping Google News' RSS feeds directly.

Summarize File

整理和跟踪雪球大V发言等

获取或接收微信视频号素材，并将医药、医疗与健康短视频转为可复盘、可追溯、 可供人工合规审阅的中文结构化报告。支持通过独立的 Edge 或 Chrome 元宝会话 下载官方 weixin.qq.com/sph 分享链接，也支持本地 MP4、字幕、文案和截图。 用于视频号下载、视频号拆解、健康视频分析、医药视频复盘、对标研究、 发布前合规预检、证据核验或 HTML 报告生成；不生成仿写稿、带货稿或可直接发布脚本。

A Google Maps API alternative and Google Places API alternative on fetcher.sh — pay-per-call in USDC via x402, or prepaid credits with a Bearer key, no Google Cloud billing account. Use when the user wants to search places by text query or anchor the search to a latitude/longitude coordinate, fetch a place's full details by its feature ID (fid), pull a place's reviews sorted by relevance/newest/rating, or look up a single review by ID. Also covers local business discovery, points-of-interest data, store-locator input, and review monitoring without Google Cloud Platform's API key setup, billing, and per-request pricing.

查询 AI HOT 的中文 AI 资讯、精选、当前热点和日报。用户询问今天或最近的 AI 新闻、AI 圈动态、大模型或产品发布、OpenAI／Anthropic／Google 最新消息、AI 论文、AI 日报、AI HOT 精选、当前最热事件，或需要同步当前全部精选时使用。必须通过 aihot.virxact.com 的匿名只读 API 获取当前数据，不凭训练记忆回答新闻；不需要 API Key 或 MCP server。

Use when organizing reading notes from books, articles, or papers into structured summaries and knowledge maps. Helps extract key insights, connect ideas acr...

PubMed EDirect searches and retrieves literature from PubMed and other NCBI databases using NCBI's EDirect command-line tools.

Notebook is a local-first knowledge base built around user-defined object types.

Builds a local index of personal documents across identity, finance, property, medical, work, and legal categories, recording references and expiry information for quick retrieval.

google-web-search uses Gemini's google_search tool to run real-time web searches that ground answers with citable sources.

local-rag-search guides web research through the mcp-local-rag server.

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).

baidu-search documents Baidu AI search with a browser fallback.

Notion Integration uses the API to read and search Notion pages and databases explicitly shared with the integration, and can create entries, update properties, or append page content.

A full-featured MCP skill for the Lexiang knowledge base, supporting search, write, edit, files, configuration, comments, drafts, and smartsheet operations.

将培训、会议、研讨、访谈和操作演示类录音转写、字幕或口语记录整理成忠于原文的结构化笔记、纪要和行动清单；支持不同详细程度、混合场景、超长文本、结构化 JSON 及正式 Word 输出。用于用户提供口语转写并要求整理、提炼、纠错、生成纪要或制作 Word；不用于直接转录音频，也不用于普通书面材料润色。

抖音视频内容结构化萃取智能体。当用户提供抖音链接（v.douyin.com 或 douyin.com）并要求提取/萃取/整理视频内容为笔记/知识卡片/Markdown时触发。 触发词：萃取抖音、提取抖音内容、抖音视频笔记、抖音内容整理、抖音知识卡片、整理抖音视频、从抖音提取、分析这个抖音视频。

Get tutoring and study support through CellCog.

transcribee transcribes YouTube videos and local audio or video with speaker labels through ElevenLabs.

通用微信群聊/联系人文字总结（无图版）。用户调用时给出日期范围，以及群名或联系人名称，本技能读取对应聊天在该日期范围内的内容并用 AI 生成纯文字总结，不生成任何图片或长图。适用于「总结一下 X 群/和张三 9月1日到9月2日的聊天」「把某群上周的聊天整理成文字」等场景。

Search locally indexed Markdown with qmd keyword, vector and hybrid retrieval.

把文档库、课程库、素材库或题库整理成可检索、可追溯、可调用的知识库案例，按 L0-L5 分层推进和验收。

This skill should be used when the user wants to generate a course knowledge graph, concept graph, knowledge map, relationship graph, or stage-two visualization output from structured JSON data. It produces a single-file interactive D3.js force-directed HTML page, static graph image prompt, Mermaid code, Graphviz DOT code, Markdown hierarchy, and reusable raw JSON.

Wechat Article Search finds public-account articles by keyword.

Fetch RSS feeds, triage posts, and create digests with the feed CLI

Turn important events and problem-solving into structured memory documents.

file-summary extracts local document text for summaries and analysis through an OpenClaw language model.