3. Data, Science & AI

Expands user queries via semantic variation analysis and sub-question targeting to improve AI visibility and response accuracy in information retrieval.

Provides core patterns for reliable ETL processing including idempotency, checkpointing, and error handling.

Generates llms.txt files to guide AI systems in understanding website structure for accurate citations and improved content retrieval.

Provides advanced SQL patterns including window functions, CTEs, recursive queries, and optimization techniques for efficient data processing.

Enables autonomous AI systems to generate and refine code through iterative loops without human intervention.

Builds structured entity triplets and brand associations to ensure consistent recognition and citation by large language models.

Provides expert guidance for crafting effective system prompts for AI agents using Anthropic's context engineering principles.

Automatically detects and fixes common tabular data issues (headers, encoding, data types) in files like CSV and Excel, returning a clean DataFrame for analysis.

Processes Excel files by reading, analyzing, and generating statistical outputs, then exporting to xlsx format.

Optimizes AI prompts using 57 proven frameworks to improve model responses and task effectiveness.

Reviews code changes for adherence to AI best practices and security standards in AI development workflows.

Analyzes patient health records via SMART on FHIR, enabling review of medical data, lab results, medications, and health trends for personalized insights.

Lists all available AI chains with link counts to discover existing chains before loading or creating new ones.

Designs scalable multi-agent architectures for complex problem-solving through task decomposition and specialized agent roles.

Provides AI-driven repository analysis and RAG-based Q&A for understanding open-source codebases on GitHub, GitLab, and Bitbucket.

Scaffolds AI agents with OpenAI Agents SDK, enabling multi-agent orchestration, tool-calling, and streaming responses for specialized applications.

Enables AI agents to persist state, maintain entity consistency, and reason over structured knowledge via custom memory architectures.

Creates and edits Excel spreadsheets with formulas, formatting, and financial modeling standards for data analysis.

Provides foundational knowledge on context components, mechanics, and constraints in AI agent systems for architecture design, debugging, and optimization.

Builds production RAG systems with semantic chunking, incremental indexing, and context-aware retrieval using vector search.

Simulates cognitive profiles of custom subjects or pre-installed expert personas using AI-driven digital twins.

Generates AI images from text prompts via Doubao SeeDream API, handling API calls and saving to /pic folder.

Assists in creating and configuring AI agents, including writing agent frontmatter and managing subagents.

Manages task sequencing and subagent coordination for continuous multi-step AI workflows.