OpenData Skills plugin
Three Claude Code plugins: queries to OpenData public datasets, OpenChart charts and tables, and SVG graphics.
- 153 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The skill calls a network API with a token it reads from the environment and from `~/.config/opendata/auth.json`.
- The other skills create chart and SVG files in the project.
Install
- Works in
Manual install
/plugin marketplace add tryopendata/skillsThen `/plugin install opendata@opendata-skills`. For charts and SVG add `openchart@opendata-skills` and `opendesign@opendata-skills`.
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The skill calls a network API with a token it reads from the environment and from `~/.config/opendata/auth.json`.
- The other skills create chart and SVG files in the project.
This is third-party code. Review the repository files before installing.
What it does
A marketplace of three plugins built on the Agent Skills spec. The `opendata` plugin carries the `opendata-api` skill, which teaches an agent to query Parquet datasets through a DuckDB-backed REST API, filter rows, compute aggregates and join datasets. Responses come back as JSON, with CSV, TSV and XLSX exports. The `openchart` plugin produces specs for charts, tables, graphs and sankey diagrams for the OpenChart library and guides chart type and color choices. The `opendesign` plugin with a single `svg-design` skill creates and edits SVG logos, icons and animation.
Who it is for. Analysts and developers who ask an agent to find open data, chart it or draw an icon.
Good fit when
- You need a series from open data, such as the consumer price index, and the agent writes an aggregation query.
- A CSV table must become a chart or sankey diagram with considered colors.
- The project needs an SVG icon set with animation.
- Several datasets have to be joined on a shared field.
Not a fit when
- The data is private and sits in an internal database.
- You need no-code interactive dashboards.
- The task involves raster images and photos.
Example request
Pull the consumer price index for five years from OpenData, average it by year and draw a line chart.Limitations
The production OpenData API needs a token: the `OPENDATA_API_KEY` variable or a login with `opendata auth login`. The key is issued on tryopendata.ai in the settings section. Installing plugins through `/plugin` targets Claude Code; for other agents the skill folder is copied by hand into `.agents/skills/`. The last commit in the repository dates to July 2026. A local server on port 8000 allows reads without authorization.
How to disable. Run `/plugin uninstall opendata@opendata-skills` for each plugin. Remove the token from the environment and from `~/.config/opendata/auth.json`.
FAQ
How do I install OpenData Skills in Claude Code?
Run `/plugin marketplace add tryopendata/skills`, then `/plugin install` for the plugin you want: `opendata@opendata-skills`, `openchart@opendata-skills` or `opendesign@opendata-skills`.
Do the skills work in Codex and Cursor?
Yes, each skill is a standalone folder with a `SKILL.md`. Copy `plugins/<plugin>/skills/<name>/` into the agent's skills directory, usually `.agents/skills/`.
Which formats does the API return?
JSON by default, plus CSV, TSV and XLSX. For aggregations and joins the skill recommends a SQL query to the `/query` endpoint.
Where do I get the API key?
If no key is found in the environment or `auth.json`, the skill suggests logging in with `opendata auth login`. The fallback is a key from the tryopendata.ai settings page.
Where did svg-design move?
In version 1.0.0 the skill moved from the `openchart` plugin into the new `opendesign` plugin.
Discussion
No questions or reviews yet.
Related
PluginsOpenapi Skills: API marketplace for agents
Openapi Skills
11 Openapi skills for Claude Code: company data, KYC, eIDAS signatures, e-invoices, SMS and PEC behind a single OAuth token
A data visualization skill for agents: turns data into polished interactive HTML charts and full reports with one visual language
DuckDB plugin for Claude Code: SQL over CSV, Parquet and databases, S3 file reading, and search across docs and session logs
A plugin marketplace for Claude Code and GitHub Copilot on Power BI and Microsoft Fabric: semantic models, DAX, TMDL, reports
A plugin and commands for building data portals: the agent scaffolds a portal from a brief and connects datasets from CKAN, GitHub and Frictionless
A Claude Code agent for protein design: target research, antibody and nanobody generation, screening and candidate ranking.
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| OpenData Skills (this card) | yes | 153 | |
| AntV Chart Visualization Skills | no | 529 | focuses on building charts; OpenData Skills adds queries to open datasets and SVG graphics |
| svg-diagram | no | 662 | draws SVG diagrams; the opendesign plugin draws logos and icons, and the other plugins work with data |
README in short
Three plugins, installation for Claude Code and folder copying for other agents. Rules for adding a skill follow: a directory with `SKILL.md`, eval cases and reference files.
README badge
Original SKILL.md
--- name: opendata-api description: Query the OpenData API for data research and analysis. Use when fetching dataset rows, filtering, sorting, aggregating, inspecting columns, composing cross-dataset joins, exploring graph intelligence, or building data pipelines against OpenData endpoints. --- # OpenData Query API Query datasets stored as Parquet files through a REST API backed by DuckDB. The API returns JSON by default, with support for CSV, TSV, and XLSX exports. **Base URL:** `https://api.tryopendata.ai` (production) or `http://localhost:8000` (local dev). Default to use production ## Authentication All endpoints require authentication in production. Before making API calls, resolve a Bearer token using this sequence: 1. **Check env var**: If `OPENDATA_API_KEY` is set, use it. 2. **Check auth.json**: Read `~/.config/opendata/auth.json`. If it exists, extract the token: - `method: "api_key"` -> use the `api_key` field - `method: "clerk"` -> use the `access_token` field (check `expires_at` hasn't passed) - Legacy format (no `method` field, just `api_key`) -> use the `api_key` field