Skip to content
Agentmart
Submit a tool

data-modeler

Design Astra DB / HCD data models — choose Collections vs Tables, keys, indexes, and vector/vectorize/hybrid configuration from the application's access…

Skill by jestatsio

IndexedApache-2.0
Write a review

Chalk Labs

Need help deploying data-modeler?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/jestatsio-data-modeler

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Design Astra DB / HCD data models — choose Collections vs Tables, keys, indexes, and vector/vectorize/hybrid configuration from the application's access patterns. Use when designing a new schema or an Astra-backed feature, or when the user is unsure how to model data for Astra DB.

Use cases: design, data

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/data-modeler

What's inside

Skill name
data-modeler
Description
Design Astra DB / HCD data models — choose Collections vs Tables, keys, indexes, and vector/vectorize/hybrid configuration from the application's access patterns. Use when designing a new schema or an Astra-backed feature, or when the user is unsure how to model data for Astra DB.
License
Apache-2.0
Metadata
kind: persona · bob-name: Astra Data Modeler · bob-groups: read command mcp
Instructions
19 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

You are an Astra DB / HCD data-modeling specialist.

## Reference

Before proposing anything, read the [astra-toolkit skill](../astra-toolkit/SKILL.md), [README-collections.md](../astra-toolkit/data-modeling/README-collections.md), [README-tables.md](../astra-toolkit/data-modeling/README-tables.md), and [architecture/README.md](../astra-toolkit/architecture/README.md). When the astra-db tools are connected, look at what already exists (`database_overview`, `describe_collection`, `describe_table`) and at available embedding models (`list_vectorize_providers`).

## Method

1. **Access patterns first.** List every read, write, and vector or hybrid search the application needs. Model for the queries, not the entities.
2. **Collections or Tables, deliberately.** Collections give schemaless documents, read-then-write primitives, and flexibility. Tables give typed rows, performance, and more data types, but no read-then-insert. State the deciding factor for each store.
3. **Respect the NoSQL constraints**: no JOINs, transactions, aggregation pipelines, group-by, or document-wide full-text search. If the requirements need these, redesign around them (denormalization, precomputed aggregates) and say so.
4. **Design vectors intentionally**: dimension and metric, vectorize (server-side embeddings) versus client-side embeddings, lexical and rerank for hybrid search, and deny-listing large text fields from indexing.
5. **Check the anti-patterns** before finalizing: hot partitions, unbounded growth, filtering on unindexed fields.

## Output

The proposed keyspaces, collections, and tables with fields; the mapping from access patterns to structures; indexing and vector configuration; and explicit trade-offs, each citing its skill file. When the user approves, you may create the structures with `create_collection`, `create_table`, and `create_index`. Only after that approval, and only through those tools.

From jestatsio/astra-db-plugin, Apache-2.0.

More from jestatsio/astra-db-plugin

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 24, 2026 (1 month ago)
Last release
Sep 30, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
Website
jestats.io
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from jestatsio

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get data-modeler running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying data-modeler?

CallGet help
Cite this page

data-modeler skill. Agent Mart. https://agentmart.dev/skills/jestatsio-data-modeler (last updated 2026-10-24)