AI Data Management &amp; Analysis

azure-database-for-postgresql

firecrawl

by @firecrawl

Firecrawl skill provides CLI and agent capabilities, supporting web scraping, content search, and other functions, helping users efficiently acquire and process web data, making it a powerful tool for backend data processing.

4.7(952)

58.9K

data-normalization

normalize

by @pbakaus

This skill uses design language to standardize the processing methods of AI tools in data analysis, ensuring data consistency and standardization, thereby improving the accuracy and reliability of analysis results.

4.7(1.7K)

54.6K

data-extraction

extract

by @pbakaus

This skill focuses on using design language to optimize the data extraction capabilities of AI tools, ensuring efficient and accurate acquisition of required data from various sources, laying a solid foundation for subsequent data analysis.

4.7(1.7K)

53.5K

convex-migration

convex-migration-helper

by @get-convex

Safely migrate database schemas and data in Convex, ensuring data integrity and system stability during structural changes.

4.7(608)

51.2K

web-crawling

firecrawl-crawl

by @firecrawl

Batch extract page content from entire websites or parts of websites, used for crawling sites or document sections.

4.7(108)

43.5K

data-mapping

firecrawl-map

by @firecrawl

Automatically scrapes and lists all URLs on a website, supporting optional deep search, helping users fully understand website structure and content distribution.

4.7(108)

43.3K

file-downloading

firecrawl-download

by @firecrawl

Downloads entire websites as local files, supporting Markdown and screenshot formats, for offline viewing, analysis, and content archiving.

4.7(37)

43.2K

firebase-firestore

firebase-firestore-standard

by @firebase

Provides a comprehensive usage guide for Firestore Standard, covering data models, query optimization, and security rules, empowering backend developers to build applications efficiently.

4.6(77)

36.7K

neon-database

neon-postgres

by @neondatabase

Utilizes Neon Postgres for backend development, enabling AI agents to efficiently manage and operate cloud-native PostgreSQL databases for data storage and retrieval.

4.6(704)

35.8K

azure-postgres

by @microsoft

GitHub Copilot designed for Azure PostgreSQL databases, providing intelligent code assistance to help developers efficiently manage and optimize database operations.

4.6(1.4K)

34.8K

defuddle

by @kepano

Defuddle CLI extracts clean markdown content from web pages, removing clutter and navigation to save tokens. It's ideal for processing online documentation, articles, and blog posts, enhancing efficiency for AI analysis or reading.

4.6(120)

23.7K

网页抓取

baoyu-url-to-markdown

by @JimLiu

Webpage to Markdown: Fetches rendered webpage content via Chrome CDP, converts it to clean Markdown format, and retains an HTML snapshot backup.

4.6(208)

21.2K

markdown-conversion

baoyu-danger-x-to-markdown

by @jimliu

Converts X (Twitter) tweets and articles to Markdown with YAML front matter, requiring user authorization for reverse engineering API.

4.6(504)

19.8K

postgresql-table-design

by @wshobson

Focuses on PostgreSQL database table design, providing intelligent automation and multi-agent orchestration to optimize backend data structures.

4.6(355)

17.7K

sql

sql-optimization-patterns

by @wshobson

Focuses on backend SQL optimization patterns, combining intelligent automation and multi-agent orchestration to improve database query performance and system efficiency.

4.5(279)

13.5K

sql-databases

database-schema-design

by @supercent-io

This skill is used for database schema design for new projects, existing schema migration, performance optimization, data integration, and security considerations, ensuring a logical and efficient database structure.

4.5(484)

12.2K

postgresql-optimization

by @github

PostgreSQL-specific development assistant, focusing on its unique features, advanced data types, and exclusive capabilities, including JSON.

4.5(331)

12.0K

sql-optimization

by @github

General SQL performance optimization assistant, offering comprehensive query tuning, indexing strategies, and database performance analysis.

4.5(315)

11.5K

scrape

by @brightdata

Automatically bypass anti-bot detection and CAPTCHAs using the Bright Data Web Unlocker API, converting any webpage into clean Markdown formatted content.

4.5(4)

10.3K

prisma-orm

prisma-database-setup

by @prisma

Provides configuration guides for Prisma with various database providers, helping users quickly set up and manage database connections.

4.5(62)

9.6K

prisma-client

prisma-client-api

by @prisma

Prisma Client API reference, covering model queries, filters, operators, and more.

4.5(50)

9.0K

entity-framework-core

ef-core

by @github

Provide Entity Framework Core best practices to guide developers in using the framework efficiently.

4.5(293)

8.8K

power-bi-performance

power-bi-performance-troubleshooting

by @github

Systematic Power BI performance troubleshooting prompts for identifying, diagnosing, and resolving performance issues in Power BI models.

4.5(290)

8.5K

google-bigquery

bigquery-pipeline-audit

by @github

Audit Python + BigQuery pipelines for cost security, idempotency, and production readiness, returning a structured report with precise patch locations.

4.5(290)

8.5K

deep-research

parallel-deep-research

by @parallel-web

Activated only when users explicitly request "deep research" or "detailed," performing comprehensive, in-depth information mining and analysis to provide detailed research reports.

4.5(20)

8.5K

enterprise

wecomcli-contact

by @wecomteam

Retrieve enterprise directory member information and filter locally, supporting name/alias matching, automatically handling candidates with the same name.

4.5(20)

8.1K

web-data-extraction

parallel-web-extract

by @parallel-web

Efficiently extracts content in parallel from any URL (including web pages, APIs, etc.), suitable for large-scale data collection and information processing tasks.

4.5(30)

7.8K

data-extraction

tavily-extract

by @tavily-ai

Focuses on extracting clean, distraction-free Markdown or plain text content from specified URLs for easy reading, analysis, or further processing, improving information retrieval efficiency.

4.5(21)

7.2K

web-crawling

tavily-crawl

by @tavily-ai

Efficiently crawls entire websites, extracts desired content from multiple pages, and supports data saving, providing support for deep data analysis and information gathering.

4.5(82)

6.9K

vector-databases

vector-index-tuning

by @wshobson

Focuses on optimizing and tuning vector indexes, combining intelligent automation and multi-agent orchestration to improve data retrieval performance and accuracy.

4.5(109)

6.6K

prisma

prisma-postgres

by @prisma

Provides integration setup and operational guidance for Prisma with PostgreSQL, optimizing backend database management and development workflows.

4.4(74)

6.0K

postgres-patterns

by @affaan-m

PostgreSQL database patterns for query optimization, schema design, and indexing.

4.4(59)

5.8K

data-extraction

read

by @tw93

Convert any URL or local PDF to clean Markdown format, supporting Feishu documents, agent chains, and automatic degradation, quickly extracting structured content.

4.4(27)

5.1K

by @jamditis

A web scraper with anti-bot bypass, content extraction, undocumented API, and poison pill detection features for extracting content from websites.

4.4(26)

4.9K

database-migrations

by @affaan-m

Provides best practices for database migrations, handling schema changes and data migration to ensure smooth database updates and data integrity.

4.4(36)

4.8K

clickhouse

clickhouse-io

by @affaan-m

Focuses on ClickHouse database schemas, query optimization, and high-performance analytics, suitable for processing large-scale real-time data, enhancing backend data processing capabilities.

4.4(44)

4.7K

jpa

jpa-patterns

by @affaan-m

Provides best practice patterns for JPA/Hibernate entity design, relationship mapping, query optimization, and performance improvement, simplifying database operations.

4.4(25)

4.7K

drizzle-orm

by @bobmatnyc

This skill is Drizzle ORM, a modern TypeScript-first ORM with zero dependencies, offering compile-time type safety and SQL-like syntax.

4.4(51)

4.3K

api-development

shopify-custom-data

by @shopify

Uses Metaobjects and Metafields to define and store custom data models for Shopify stores.

4.4(23)

4.2K

regular-expressions

regex-vs-llm-structured-text

by @affaan-m

Provide a decision framework for choosing between regular expressions or large language models when processing structured text.

4.4(20)

4.1K

database-design

database-schema-designer

by @softaworks

Focuses on designing robust, scalable database schemas for SQL and NoSQL databases, ensuring efficient data storage and management.

4.4(87)

3.8K

data-scraper-agent

by @affaan-m

Build production-grade AI-driven data scraping agents, supporting scheduled runs, LLM data augmentation, database storage, and continuous optimization, usable for scraping any public data source.

4.4(39)

3.7K

sql

sql-pro

by @jeffallan

Optimize SQL queries, design database schemas, and resolve performance issues. AI Agent Skill for improved work efficiency and automation.

4.4(43)

postgres-pro

by @jeffallan

Focuses on optimizing PostgreSQL queries, configuring replication, and high availability, ensuring excellent backend database performance and reliable data security.

4.4(81)

web-crawling

crawl

by @tavily-ai

This skill is used for website crawling, extracting content from multiple pages, suitable for documents, knowledge bases, and full-site content extraction, supporting OAuth authentication.

4.4(20)

kotlin

kotlin-exposed-patterns

by @affaan-m

Use JetBrains Exposed ORM for database access, covering DSL queries, DAO, transactions, and production configuration.

4.4(93)