Ejecuta cualquier Skill en Manus
con un clic

Ejecuta cualquier Skill en Manus con un clic

sql-query

Estrellas4

Forks2

Actualizado19 de junio de 2026 a las 04:25

Generate, explain, and optimize SQL queries. Use when user asks to write SQL, optimize a query, or explain what a query does.

Instalación

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Ejecutar en Manus

Fuente

deskwand

deskwand/agent

Abrir repositorio de GitHub Ver repositorios del creador

Descarga

Ejecutar en Manus

Ocupaciones relacionadasSOC

Basado en la clasificación ocupacional SOC

Arquitectos de bases de datosOcupaciones informáticas y matemáticas·SOC 15-1243

SKILL.md

readonly

name	sql-query
description	Generate, explain, and optimize SQL queries. Use when user asks to write SQL, optimize a query, or explain what a query does.
version	1.0.0
author	deskwand
license	MIT
metadata	{"tags":["SQL","Database","Queries","MySQL","PostgreSQL","SQLite"]}
allowed-tools	read,shell

SQL Query Tools

Write, review, and optimize SQL queries.

When to use

User asks to "write a SQL query to..."
User has an existing query and wants optimization
User needs to explain or debug a SQL query
User wants to design a schema or add indexes

Query Generation Guidelines

1. Always ask for schema context first

Before writing a query, identify:

Database engine: PostgreSQL, MySQL, SQLite, etc.
Table structure: columns, types, relationships
Data volume: approximate row counts

2. Write safe queries

-- ✅ Parameterized
SELECT * FROM users WHERE id = ?;

-- ❌ String interpolation (SQL injection risk)
SELECT * FROM users WHERE id = '${userId}';

3. Include EXPLAIN for performance

EXPLAIN ANALYZE SELECT ...

4. Common patterns

-- Join with aggregation
SELECT u.name, COUNT(o.id) as order_count
FROM users u
LEFT JOIN orders o ON u.id = o.user_id
GROUP BY u.id, u.name
HAVING COUNT(o.id) > 5
ORDER BY order_count DESC;

-- Window functions
SELECT
  department,
  employee,
  salary,
  RANK() OVER (PARTITION BY department ORDER BY salary DESC) as rank
FROM employees;

-- CTE (Common Table Expression)
WITH monthly_sales AS (
  SELECT DATE_TRUNC('month', created_at) as month, SUM(amount) as total
  FROM orders
  GROUP BY 1
)
SELECT month, total, LAG(total) OVER (ORDER BY month) as prev_month
FROM monthly_sales;

-- Upsert (PostgreSQL)
INSERT INTO users (id, email, name)
VALUES (1, 'a@b.com', 'Alice')
ON CONFLICT (id) DO UPDATE
SET email = EXCLUDED.email, name = EXCLUDED.name;

Query Review Checklist

When reviewing an existing query:

Correctness: Does it return the expected results? Check JOIN conditions, WHERE filters, NULL handling.
Performance: Are there missing indexes? Can subqueries be rewritten as JOINs? Is LIMIT used where appropriate?
Safety: No SQL injection vectors. No SELECT * in production code.
Readability: Proper formatting, meaningful aliases, comments for complex logic.

Engine-Specific Notes

Feature	PostgreSQL	MySQL	SQLite
String concat	`\|\|`	`CONCAT()`	`\|\|`
Limit + offset	`LIMIT n OFFSET m`	`LIMIT m, n`	`LIMIT n OFFSET m`
Current timestamp	`NOW()`	`NOW()`	`datetime('now')`
Boolean type	`BOOLEAN`	`TINYINT(1)`	`INTEGER` (0/1)
JSON support	`JSONB`	`JSON`	`TEXT` + json functions

Constraints

Never execute DROP, TRUNCATE, or DELETE without explicit user confirmation
Always show estimated row impact before UPDATE/DELETE
Generate queries with parameterized placeholders, not literal values

Más de este repositorio

mismo repositorio

image-ocr

deskwand/agent

本地离线 OCR 文字识别，基于 tesseract.js。当用户发图片/截图/扫描件要求提取文字时使用，支持中英文。纯本地运行，无需联网。

2026-06-264

requesting-code-review

deskwand/agent

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

2026-06-264

test-driven-development

deskwand/agent

Use when implementing any feature or bugfix, before writing implementation code

2026-06-264

algorithmic-art

deskwand/agent

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

2026-06-214

brand-guidelines

deskwand/agent

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

2026-06-214

canvas-design

deskwand/agent

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

2026-06-214

name	sql-query
description	Generate, explain, and optimize SQL queries. Use when user asks to write SQL, optimize a query, or explain what a query does.
version	1.0.0
author	deskwand
license	MIT
metadata	{"tags":["SQL","Database","Queries","MySQL","PostgreSQL","SQLite"]}
allowed-tools	read,shell

SQL Query Tools

Write, review, and optimize SQL queries.

When to use

User asks to "write a SQL query to..."
User has an existing query and wants optimization
User needs to explain or debug a SQL query
User wants to design a schema or add indexes

Query Generation Guidelines

1. Always ask for schema context first

Before writing a query, identify:

Database engine: PostgreSQL, MySQL, SQLite, etc.
Table structure: columns, types, relationships
Data volume: approximate row counts

2. Write safe queries

-- ✅ Parameterized
SELECT * FROM users WHERE id = ?;

-- ❌ String interpolation (SQL injection risk)
SELECT * FROM users WHERE id = '${userId}';

3. Include EXPLAIN for performance

EXPLAIN ANALYZE SELECT ...

4. Common patterns

-- Join with aggregation
SELECT u.name, COUNT(o.id) as order_count
FROM users u
LEFT JOIN orders o ON u.id = o.user_id
GROUP BY u.id, u.name
HAVING COUNT(o.id) > 5
ORDER BY order_count DESC;

-- Window functions
SELECT
  department,
  employee,
  salary,
  RANK() OVER (PARTITION BY department ORDER BY salary DESC) as rank
FROM employees;

-- CTE (Common Table Expression)
WITH monthly_sales AS (
  SELECT DATE_TRUNC('month', created_at) as month, SUM(amount) as total
  FROM orders
  GROUP BY 1
)
SELECT month, total, LAG(total) OVER (ORDER BY month) as prev_month
FROM monthly_sales;

-- Upsert (PostgreSQL)
INSERT INTO users (id, email, name)
VALUES (1, 'a@b.com', 'Alice')
ON CONFLICT (id) DO UPDATE
SET email = EXCLUDED.email, name = EXCLUDED.name;

Query Review Checklist

When reviewing an existing query:

Correctness: Does it return the expected results? Check JOIN conditions, WHERE filters, NULL handling.
Performance: Are there missing indexes? Can subqueries be rewritten as JOINs? Is LIMIT used where appropriate?
Safety: No SQL injection vectors. No SELECT * in production code.
Readability: Proper formatting, meaningful aliases, comments for complex logic.

Engine-Specific Notes

Feature	PostgreSQL	MySQL	SQLite
String concat	`\|\|`	`CONCAT()`	`\|\|`
Limit + offset	`LIMIT n OFFSET m`	`LIMIT m, n`	`LIMIT n OFFSET m`
Current timestamp	`NOW()`	`NOW()`	`datetime('now')`
Boolean type	`BOOLEAN`	`TINYINT(1)`	`INTEGER` (0/1)
JSON support	`JSONB`	`JSON`	`TEXT` + json functions

Constraints

Never execute DROP, TRUNCATE, or DELETE without explicit user confirmation
Always show estimated row impact before UPDATE/DELETE
Generate queries with parameterized placeholders, not literal values