3. Data, Science & AI

Extracts text, figures, and citations from PDF documents with markdown conversion capabilities.

Describes ClearML's architecture and extension points for managing and extending machine learning experiment tracking and model management.

Programmatically executes NCBI BLAST (blastn/blastp) sequence similarity searches and returns results in JSON format via BioPython.

Queries COSMIC Cancer Gene Census to check if genes are cancer genes, annotate genes, or retrieve cancer gene properties.

Discovers Mozilla telemetry probes and Glean metrics for Firefox and other Mozilla products to enable data-driven analysis.

Manages persistent workflow state analytics using AgentDB (DuckDB), enabling dependency graph queries, metrics, and checkpoint recovery from TODO markdown files.

Visualizes BAM files in IGV for genomic regions, multi-track comparisons, and WGS batch analysis.

Reads, writes, and manipulates biological sequences in FASTA, GenBank, and FASTQ formats with indexed access.

Executes local DNA sequence alignment against hg38 or CHM13 reference genomes using .2bit files, bypassing UCSC API dependencies.

Automates data extraction from authenticated web pages and APIs by capturing network requests with valid authentication headers.

Builds autonomous AI agents for travel planning workflows using multi-step orchestration and real API integrations like flight searches and hotel bookings.

Analyzes and processes VCF/BCF genomic variant files, enabling statistical calculations, quality-based filtering, and region-specific extraction for bioinformatics workflows.

Coordinates multi-agent systems for complex problem-solving through parallel/sequential processing, dependency management, and result aggregation.

Creates subagents, specialized agents, or custom AI assistants for Claude Code to enhance coding workflows with AI capabilities.

Optimizes prompts for OpenAI's Codex agent to generate high-quality code outputs effectively for task delegation.

Extracts and converts web page content into clean markdown format for structured data processing and analysis.

Manages dynamic creation, personality assignment, and orchestration of AI agents with customizable traits and voices.

Analyzes genomic alignment files (BAM/SAM/CRAM) for WGS/WES data, including region extraction, indel identification, coverage statistics, and JSON export.

Processes PDF documents using Google Gemini API to extract text, images, diagrams, charts, and tables, enabling structured data extraction and content analysis.

Creates economic data analyses and visualizations for higher education stakeholders using FRED data, including dashboards, reports, and API integrations.

Tracks promotional code performance, revenue, conversion rates, and ROI to identify effective marketing channels and attribution sources.

Repomix packages entire repositories into AI-friendly files for efficient codebase analysis, LLM context generation, and security audit preparation.

Comprehensive guide for MongoDB implementation including CRUD operations, aggregation pipelines, schema design, indexing, and deployment configurations.

Guides implementation of Google Gemini API for audio analysis (transcription, summarization) and text-to-speech generation, enabling audio file processing and speech synthesis.