Skip to content
Skills Library
Data & analytics · Conversion & formats

sql-translator

/sql-translator

Translates a plain-English question into a single, safe, read-only SQL query against a known schema, with assumptions made explicit. Use when the user asks for natural-language to sql work, or mentions sql, translator.

Licence
Apache-2.0
Last repository change
26.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
4
Deprecation

No signals detected. Repository changed on 26.10.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

Translates a plain-English question into a single, safe, read-only SQL query against a known schema, with assumptions made explicit. Use when the user asks for natural-language to sql work, or mentions sql, translator.

Original author description

Translates a plain-English question into a single, safe, read-only SQL query against a known schema, with assumptions made explicit. Use when the user asks for natural-language to sql work, or mentions sql, translator.

How it works

  1. Instructions
  2. Always
  3. Never
  4. Examples
  5. Trust & telemetry
Original SKILL.md headings · 87 lines, 366 words
SKILL.md preview
---
name: sql-translator
description: "Translates a plain-English question into a single, safe, read-only SQL query against a known schema, with assumptions made explicit. Use when the user asks for natural-language to sql work, or mentions sql, translator."
version: "0.1.0"
license: "CC-BY-SA-4.0"
homepage: "https://superagentskill.com/marketplace/sql-translator"
source: "Super Agent Skill (SAK)"
---

# Natural-language to SQL

Use this skill when a user asks a data question against a known schema and you
want a safe SELECT they can run as-is. The skill emits exactly one SELECT,
qualifies every column, and lists the assumptions it made (date ranges, NULL
handling, dedup keys) so the user can audit them.

## Instructions

You are a careful data analyst. You receive a plain-English question, a schema
description (DDL or compact form), and a SQL dialect (default postgres).
Produce exactly one SELECT statement — never INSERT, UPDATE, DELETE, or DDL.
Qualify every column with its table or alias. Use SELECT * only when the
intent is an explicit "preview". Then list every assumption made: date range
interpretation, NULL handling, dedup key, timezone. Never invent columns
that aren't in the schema.

## Always

- Emit exactly one SELECT statement.
- Qualify every column with its table or alias.
- List every assumption made.

## Never

- Use INSERT, UPDATE, DELETE, or any DDL.
- Invent columns absent from the schema.

## Examples

### Top customers last quarter

Input:

```
question: "Top 5 customers by revenue last quarter"
schema: "orders(id, customer_id, amount_cents, paid_at)"
dialect: "postgres"
```

Expected output:

```
SELECT o.customer_id, SUM(o.amount_cents)/100.0 AS revenue
FROM orders o
WHERE o.paid_at >= date_trunc('quarter', now()) - interval '3 months'
  AND o.paid_at <  date_trunc('quarter', now())
GROUP BY o.customer_id
ORDER BY revenue DESC
LIMIT 5;
Assumptions: ["last quarter = previous calendar quarter", "amount_cents non-null", "timezone = server default"]
```

### Daily signups

Input:

```
question: "How many signups per day in the last 30 days?"
schema: "users(id, created_at)"
dialect: "postgres"
```

Expected output:

```
SELECT date_trunc('day', u.created_at) AS day, COUNT(*) AS signups
FROM users u
WHERE u.created_at >= now() - interval '30 days'
GROUP BY 1
ORDER BY 1;
Assumptions: ["created_at is signup timestamp", "timezone = server default"]
```

## Trust & telemetry

This skill is graded on the Super Agent Skill network: format, substance and adversarial
(prompt-injection) testing produce a public Trust Score.

- Trust Score & evidence: https://superagentskill.com/marketplace/trust/sql-translator
- Skill page: https://superagentskill.com/marketplace/sql-translator
- Live version (always current) via MCP: https://superagentskill.com/api/mcp

Reinstall or update with `npx skills update`, or pull the live graded version with
`npx super-agent install sql-translator`.

Versions

The database has no other skills named sql-translator.

Database snapshot: 13.11.2026 · package version dced0c80b41f (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100text-translator
    Text Translator. Use when working with source text and target language or locale.
  • 100generating-sql
    Translates business questions into correct, readable SQL for PostgreSQL, BigQuery, Snowflake, SQL Server, MySQL or SQLite, explains the query in plain language and adds validation checks. Also reviews and fixes existing queries. Use when someone asks for a SQL query, a report or…
  • 100dbt-sf-to-bq-translator
    Translates Snowflake dbt SQL models to Standardized BigQuery SQL. Handles SQL compilation, Jinja macro placeholder masking, BigQuery Translation Service migration workflows, AST-based config transformations, explicit type casting, JSON extraction standardization, and…
  • 90rc-sql
    Relational query and schema work — indexes, EXPLAIN, N+1, modeling. Read-only by default. Use when reviewing SQL. Not for infra admin.
  • 90translator
    Translates text between languages. Use this when the user wants to translate a word, phrase, or passage into another language.
  • 90sql-queries
    Apply sql queries in reproducible local data workflows with version-aware APIs, explicit assumptions, and validation. Use when the user chooses sql queries or its strengths fit the task.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.