ds vs quick-start
ds is a plugin bundle for AI coding tools published by Andika Rachman. Marketplaces we read that list it: 1 (Community GitHub marketplaces). quick-start is a plugin bundle for AI coding tools published by ScaleVector GmbH. Marketplaces we read that list it: 1 (Community GitHub marketplaces). As of our marketplace pass on 2026-10-22. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.
Where each is published
| Marketplace |  ds |  quick-start |
|---|---|---|
| Community marketplace andikarachman/data-science-plugin | Listed Version: 2.6.0 Forks (GitHub): 2 Stars (GitHub): 14 Not marked · First seen |
Not listed |
| Community marketplace dlt-hub/dlthub-ai-harness | Not listed | Listed Version: 0.1.1 Forks (GitHub): 5 Stars (GitHub): 63 Not marked · First seen |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | ds | quick-start |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | 14 (worse) | 63 (better) |
| Forks (GitHub) (differs) | 2 (worse) | 5 (better) |
| Last release | Not published | Not published |
| Where it runs (differs) | Remote server (mcp.context7.com/mcp) | Installs as a plugin bundle |
| Transport (differs) | Streamable HTTP | Not stated |
| Tools it declares | Not published | Not published |
| Environment variables it asks for | Not published | Not published |
| Parts of the bundle (differs) | 28 | 3 |
| Licence (differs) | MIT | https://github.com/dlt-hub/dlthub-ai-workbench/blob/master/LICENSE |
| Repository (differs) | github.com/andikarachman/data-science-plugin | github.com/dlt-hub/dlthub-ai-harness |
| Changes in the last 7 days (differs) | 0 | 2 |
| First seen (differs) | 2026-10-14 | 2026-10-16 |
| Endpoint at the last check (differs) | Responded 2 days ago | no remote endpoint we check |
Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.
What each says it does
ds
Data science and ML workflow tools. 9 agents, 8 commands, 19 skills, 9 templates for problem framing, preprocessing, validation, EDA, experimentation, review, deployment, and knowledge compounding.
quick-start
Full-path guided start: ingest → visualize → transform → deploy in 3-5 prompts. Routes to the right entry skill based on a chosen depth.
How to run each
ds As a Claude Code plugin
/plugin marketplace add andikarachman/data-science-plugin
/plugin install ds@data-science-pluginquick-start As a Claude Code plugin
/plugin marketplace add dlt-hub/dlthub-ai-harness
/plugin install quick-start@dlthub-ai-workbenchCommands built only from what the marketplaces declare; the full set for every client is on each card.
Only ds has a remote endpoint we check. How we check endpoints
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
Neither one's marketplaces publish the settings it asks for.
What it can do: ds · What it can do: quick-start · Compare two other plugins
Data comes from public marketplace files in GitHub repositories of their authors. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.