Skip to content
Agentmart
Submit a tool

ggsql

Writes, modifies, explains, validates, and runs ggsql grammar-of-graphics visualization queries.

Skill by George Stagg (@georgestagg)

IndexedMIT★ 80
Write a review

Chalk Labs

Need help deploying ggsql?

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/edmundmiller-ggsql

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

Writes, modifies, explains, validates, and runs ggsql grammar-of-graphics visualization queries.

Use cases: data, writing

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 and code. 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/ggsql

What's inside

Skill name
ggsql
Description
Writes, modifies, explains, validates, and runs ggsql grammar-of-graphics visualization queries.
License
MIT
Metadata
author: George Stagg (@georgestagg) · upstream: https://github.com/posit-dev/skills/blob/main/ggsql/ggsql/SKILL.md
Instructions
59 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • syntax.md · references/

SKILL.md (first lines)

# ggsql Query Writer

Write valid ggsql visualization queries from natural-language requests. ggsql combines SQL data shaping with a declarative grammar of graphics.

## Use this skill when

- Creating or modifying a ggsql query.
- Converting a chart request into ggsql.
- Explaining, validating, or running ggsql.
- Choosing ggsql layers, mappings, scales, facets, projections, or labels.

Do not trigger for ordinary SQL work that has no visualization component.

## Required reference

Read [references/syntax.md](references/syntax.md) before writing or changing a query. It is the complete upstream language reference and defines the allowed clauses, aesthetics, layers, settings, palettes, and CLI commands.

Never invent ggsql syntax. If the reference does not document a requested feature, say so and offer the closest documented form.

## Workflow

1. Identify the data source, columns, desired visual encodings, grouping, and output.
2. Shape data with SQL or CTEs before `VISUALISE` when necessary.
3. Choose the simplest documented `DRAW` layer and mappings.
4. Add `SCALE`, `FACET`, `PROJECT`, or `LABEL` only when the request needs them.
5. If `ggsql` is available, validate with `ggsql validate`. Render with `ggsql exec ... -v` only when output is requested.
6. Return the complete query, then briefly explain consequential choices.

## Minimal pattern

```ggsql
SELECT category, SUM(value) AS total
FROM 'data.parquet'
GROUP BY category
VISUALISE category AS x, total AS y
DRAW bar
LABEL
  title => 'Total by category',
  x => 'Category',
  y => 'Total'
```

Alternatively, let `VISUALISE` name the source:

```ggsql
VISUALISE bill_len AS x, bill_dep AS y, species AS color
FROM ggsql:penguins
DRAW point
```

## Guardrails

- Use only documented clauses, settings, aesthetics, layers, transforms, and palettes.
- Preserve the user's source names and column names.
- Prefer `ggsql:penguins` or `ggsql:airquality` only when example data is needed.
- Do not claim validation or rendering unless the command actually ran.
- Keep SQL portable unless the selected backend requires a documented dialect feature.

From edmundmiller/dotfiles, MIT.

More from edmundmiller/dotfiles

Signals

Stars
80
Forks
6
Open issues
4
Last commit (this folder)
Aug 1, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from George Stagg (@georgestagg)

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 ggsql 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 ggsql?

CallGet help
Cite this page

ggsql skill. Agent Mart. https://agentmart.dev/skills/edmundmiller-ggsql (last updated 2026-10-24)