全部能力

Overview of Experimental MVCC feature - snapshot isolation, versioning, limitations

Log management - search, archives, metrics, and cost control.

使用 inlets 和 outlets 为 Airflow 任务添加数据血缘注解。适用于用户希望为任务添加血缘元数据、指定输入/输出数据集，或…

>

Guide Clojure and ClojureScript development using REPL-driven workflow, coding conventions, and best practices. Use when writing, developing, or refactoring…

Generate institutional-quality PDF analysis reports for stocks and ETFs. USE WHEN user mentions generate report, create pdf, stock analysis, ticker report,…

Review Clojure and ClojureScript code changes for compliance with Metabase coding standards, style violations, and code quality issues. Use when reviewing pull…

Create Vega and Vega-Lite visualizations with ES|QL data sources in Kibana. Use when building custom charts, dashboards, or programmatic panel layouts beyond standard Lens charts.

解释 claude-mem 如何捕获观察结果、何时触发记忆注入，以及数据存储在哪里。当用户询问“claude-mem 是如何工作的？”或“什么……”时使用。

首次为 LLM 应用添加 Arize AX 链路追踪。采用双阶段 Agent 辅助流程，先分析代码库，再实施埋点…

Bridge between OpenWork UI and OpenCode runtime

AI coding agent skill for building with EmDash, the full-stack TypeScript CMS built on Astro and Cloudflare

McKinsey顾问式问题解决系统。从商业问题出发,通过假设驱动的结构化分析方法,生成McKinsey风格研究报告和PPT。融合Problem Solving方法论、MECE原则、Issue Tree拆解、Hypotheses形成、Dummy Page设计、智能数据收集和专业PPT生成能力。

Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, review…

Expert in creating charts, dashboards, and data visualizations using modern libraries

竞品广告情报分析，覆盖 Google、Meta、LinkedIn、TikTok、Microsoft 和 Apple Ads。分析竞品广告文案、创意策略、关键词……

获取、存储并可视化 GitHub 仓库流量数据（访问量、克隆数、来源、Star），并提供趋势图表。需要仓库的推送权限。

为重大架构变更创建新的架构决策记录（ADR）文档，使用一致的模板和基于仓库的命名规范…

Design system and guidelines for Claude's built-in generative UI — the show_widget tool that renders interactive HTML/SVG widgets inline in claude.ai conversations. This skill provides the complete Anthropic "Imagine" design system so Claude produces high-quality widgets without needing to call read_me first. Use this skill whenever the user asks to visualize data, create an interactive chart, build a dashboard, render a diagram, draw a flowchart, show a mockup, create an interactive explainer, or produce any visual content beyond plain text or markdown. Triggers include: "show me", "visualize", "draw", "chart", "dashboard", "diagram", "flowchart", "widget", "interactive", "mockup", "illustrate", "explain how X works" (with visual), or any request for visual/interactive output. Also triggers when the user wants to display financial data visually, create comparison grids, or build tools with sliders, toggles, or live-updating displays.

Expert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis, predictive modeling, and business…