菜单
The duckdb cli is installed on this system and is a good choice for ad-hoc data analysis from CSV, parquet or NDJSON files. Use it when the user asks for data values in the context of a specific data file or to join multiple files together.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/owid/owid-claude-plugins --skill duckdb命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Fact-check an article or blog post against Our World in Data. Given a URL, this skill downloads the article, finds statements that OWID data can verify or contextualize, checks each one against real chart data, and produces an annotated copy of the article with color-coded highlights and embedded interactive charts, opened in the user's browser. Use when the user asks to fact-check an article, asks 'what does OWID data say about this article/claim', or wants an article annotated with OWID charts.
Access Our World In Data's published datasets using the owid-catalog Python library. Provides a unified Python API for searching and fetching chart data, catalog tables, and indicators — returning enhanced pandas DataFrames with metadata. Use this as a Python-native alternative to the HTTP-based search-charts and fetch-chart-data skills.
This skill describes how to fetch data for an Our World In Data chart, once the relevant chart URL has been identified. Consult this skill to understand the possible query params to get the best results and to understand the response. Use it you need to fetch data and have already identified the relevant chart URL.
基于 SOC 职业分类
正在显示 SKILL.md
| name | duckdb |
| description | The duckdb cli is installed on this system and is a good choice for ad-hoc data analysis from CSV, parquet or NDJSON files. Use it when the user asks for data values in the context of a specific data file or to join multiple files together. |
| globs | ["*.csv","*.parquet"] |
| allowed-tools | ["Bash(duckdb:*)"] |
When using duckdb for querying single files, use the DESCRIBE SELECT and, optionally, SUMMARIZE SELECT statements to understand the structure beforehand.
