3. Data, Science & AI

Processes documents by extracting and transforming content from various file formats for data analysis and integration.

Extracts social media and e-commerce data from platforms like Twitter, Instagram, and Amazon using Apify actors for business intelligence.

Provides 240+ prompt patterns for AI-driven content analysis, transformation, and insight extraction including summaries and threat modeling.

Processes Excel spreadsheet files (xlsx) for data extraction, transformation, and integration tasks.

Framework for testing, benchmarking, and verifying behavior of AI agents in LLM-based systems.

Enables initiating AI-driven voice conversations through the Pipecat MCP server for voice application development.

Programmatically queries, edits, and replaces CAD geometry nodes in atomCAD for atomic/molecular structure design and CSG shape creation.

Creates ServiceNow-based reports, dashboards, and data visualizations for analytics and scheduled data exports.

Handles ServiceNow data import, transformation, field mapping, CSV processing, and LDAP integration for data source management.

Enables development and implementation of machine learning models for predictive analytics, classification, and similarity tasks within ServiceNow.

Enables creation of KPIs, performance indicators, and dashboard widgets for ServiceNow Performance Analytics to monitor business metrics.

Provides data import/export capabilities for ServiceNow, supporting XML, Excel, CSV, and bulk data migration tasks.

Enables semantic document search and knowledge base features using RAG and vector search implementation.

Builds production-grade GenAI systems, agentic architectures, advanced RAG implementations, and evaluation pipelines.

Provides LangGraph-based integration for AI agents and graph-based workflows in SEPilot Desktop, ensuring infrastructure compatibility and streaming patterns.

Optimizes Snowflake SQL queries by identifying performance bottlenecks and suggesting targeted improvements for faster execution.

Identifies and ranks expensive Snowflake queries by cost, data scanned, and performance, providing optimization recommendations.

Converts legacy SQL code to modular dbt models, breaking monolithic queries into layered transformations while validating against existing project conventions.

Automates creation and modification of dbt models adhering to project conventions, with built-in validation via dbt build.

Systematically debugs and resolves dbt errors including compilation, database issues, and test failures in data transformation workflows.

Analyzes downstream dependencies before refactoring dbt models to ensure safe restructuring of data transformation pipelines.

Analyzes Snowflake query performance using query ID, identifies bottlenecks, and provides optimized SQL with expected improvements.

Adds schema tests and data quality validation to dbt models, ensuring integrity via unique, not_null, and relationship checks.

Legacy skill for creating and maintaining AI agents via Agentforce's Agent Script syntax with 100-point scoring system.