Business Intelligence

Intelligent chart generation and data analysis skill. Reads user-supplied data files (CSV/Excel/JSON), analyzes data characteristics with LLM assistance, auto-recommends and generates interactive ECharts visualizations. Use when the user asks to analyze data, generate charts, create visualizations,

Web search via Tavily API (alternative to Brave). Use when the user asks to search the web / look up sources / find links and Brave web_search is unavailable...

中国金融机构数据爬取与分析综合 Skill v7.7.0。全量机构名单（2334家，43大类）、 全网舆情（4 类 60+ 商业财经媒体源 + RSS 直连 + akshare 兜底）、A股报告/公告/研报、 结构化市场数据（期货/宏观/Shibor/港股美股）、深度类人浏览器爬取、真实风险指标分析、 定期报告解读（财报自动解读/同比环比/亮点风险/评分评级）。 🆕 v7.7.0 四模块优化：爬取自适应（早停/降并发/死域跳过+耗时统计）、知识库语音指令接线、 下载断点续传+sha256 校验+并发批量、分析指标扩展（Sortino/胜率）与 nav_trend_analysis 趋势分析。 v7.6.0（承接）知识库总结同步（IMA/Dify/Obsidian/本地）与反向校对；v7.5.0（承接）编码检测链/下载加固/SSL 降级。 v7.3.0（承接）：机构名单完善、智能多级爬取、网页内容识别、数据分析汇总、语音交互。 v7.2.0 爬取硬化（承接）：软拦截检测接线、Retry-After 遵从、URL 去重器（跨进程持久化）。 v7.1.0 定期报告解读（承接）：财报自动解读，纯规则零依赖。 v7.0.0（承接）：机构名单完成、网络拦截 API 挖掘、操作宏录制回放、异步并发标签池。 v6.0.0（承接）：数据源商业化、浏览器深度类人化、真实 PDF/HTML 报告导出、zip 增量打包。 触发词：爬取机构、舆情爬取、全网舆情、网页爬取、智能爬取、内容识别、表格识别、 汇总分析、语音交互、语音爬取、公告下载、券商研报、批量爬取、定时爬取、文档分析、 东方财富、龙虎榜、北向资金、监管动态、搜索引擎、网页归档、类人爬取、数据回测、 结构化数据、期货、宏观经济、港股美股、风险指标、组合复刻、夏普比率等（完整触发词见下方 auto_trigger）。

Analyze stocks and cryptocurrencies using Yahoo Finance data. Supports portfolio management, watchlists with alerts, dividend analysis, 8-dimension stock scoring, viral trend detection (Hot Scanner), and rumor/early signal detection. Use for stock analysis, portfolio tracking, earnings reactions, crypto monitoring, trending stocks, or finding rumors before they hit mainstream.

Manage and monitor a personal stock watchlist with support for adding, removing, listing stocks, and summarizing their recent performance using data from 10jqka.com.cn. Use when the user wants to track specific stocks, get performance summaries, or manage their watchlist.

全球智能投研工具 v9.8 — 主流知识库全覆盖（12 适配器双向交互）， 叠加 v9.6 标红限制固化 + v9.5 大佬圆桌，全资产量化 + 真实数据源。覆盖 12 个全球市场，零依赖核心（纯 stdlib）。 🆕 v9.8 知识库 12 适配器（双向：存档 + 回读离线量化）： - 本地：本地兜底库/Obsidian/思源笔记/Logseq；云端：IMA/语雀/飞书知识库/Notion；RAG：Dify/RAGFlow/FastGPT/MaxKB - 存档 --kb-save <code>（内嵌机读 JSON），回读 --kb-quant <词> 离线量化预测；--kb-target 与语音均可指定适配器 - 凭证走环境变量（RAGFLOW/FASTGPT/MAXKB/YUQUE/FEISHU/NOTION/SIYUAN/LOGSEQ 前缀），零新依赖零明文落盘；IMA/Dify 沿用 v9.7 变量名 v9.6 标红限制固化：国内直连代理防护（导入即装直连 opener）+ 评分≠盈利保证免责声明；行情+K线并行提速 v9.4 高级量化统计 + 语音交互：advanced_stats 一站式体检（滚动/回撤/仓位/统计检验/归因）+ 零依赖语音指令 v9.3 量化预测增强：历史形态匹配预测（股票/基金/期货通用）+ 基金 NAV 预测 + 期货置信区间/仓位/展期收益 v9.0 三大支柱：深度板块（RPS/宽度/离散度/主题/轮动周期）+ 深度指数（体制/波动率/结构/内含/真实PE-PB分位） + 体制感知预测（体制条件化权重/信号共识/宏观情景概率加权/校准），regime="auto" 一键开启 数据源：腾讯 + 东方财富（免费无 Key）+ akshare（可选）。测试 691。 触发词：股票、基金、行情、分析、预测、涨跌、指数、板块、商品、黄金、债券、可转债、 货币基金、全球市场、量化、技术指标、组合优化、风险平价、夏普、回测、价值投资、蒙特卡洛、VaR、 相对强度、RPS、市场体制、波动率体制、指数估值、情景分析、预测校准、自上而下、形态匹配、净值预测、 语音交互、语音查询、语音预测、高级统计、Kelly仓位、回撤剖析、滚动夏普、跟踪误差、信息比率、JB检验、 大佬、圆桌、大师共识、索罗斯、费雪、达利欧、马克斯、神奇公式、利弗莫尔、反身性、批量并行、 知识库、IMA、Dify、Obsidian、RAGFlow、FastGPT、MaxKB、语雀、飞书、Notion、思源、Logseq、分析存档、回读量化、笔记同步

Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...

Create, inspect, and edit Microsoft Word documents and DOCX files with reliable styles, numbering, tracked changes, tables, sections, and compatibility check...

Create, inspect, and edit Microsoft Excel workbooks and XLSX files with reliable formulas, dates, types, formatting, recalculation, and template preservation...

Create, inspect, and edit Microsoft PowerPoint presentations and PPTX decks with reliable layouts, templates, placeholders, notes, charts, and visual QA. Use...

Automates, tests, and debugs browsers with Playwright: locators, auto-waiting, traces, CI runs, and MCP browser control. Use when a test is flaky, times out, or fails only in CI or headless; when a locator matches multiple elements or the wrong one (strict mode violation); when clicks need force, waits become sleeps, or networkidle never settles; for storageState and login setup, request mocking and HAR replay, uploads and downloads, iframes and shadow DOM, popups and dialogs, screenshot diffs that change per machine, trace and report artifacts, sharding a slow suite, device and permission emulation, accessibility checks, driving a real browser through Playwright MCP, extracting data from JS-rendered pages, or porting a Cypress, Puppeteer, or Selenium suite to Playwright. Not for maintaining an existing Cypress or Puppeteer suite (cypress, puppeteer) or for work a plain HTTP request answers (http).