The library

analyst · Exploratory investigation of datasets when the question is broad (profile, compare, find patterns) vs narrow hypothesis testing

data-engineer · Building reliable, tested data infrastructure when source systems are messy or heterogeneous

ml-engineer · End-to-end model development from data to evaluation when baselines and production requirements are specified

weather-analyst · Multi-period weather analysis when hour-by-hour comparisons and extreme event detection beat simple forecasts

causal-inference · Causal inference when observational data and rigorous assumption testing beat correlation studies

kg-agent · Knowledge graph construction from domain-specific structured data when precision is measurable

explorer · Starting a research project when you need to know what data exists and how hard it is to access

academic-researcher · Literature assembly when you need verifiable, locally-cached citations with evidence of download success

metadata-checker · Ensuring UBERON term metadata includes proper creator attribution and citations

fraud-quality · When detecting data quality issues and leakage patterns in fraud datasets.

herddb-k3s-bench · When you need herddb-k3s-bench expertise as a specialist agent.

bear-analyst · Adversarial investment review before capital deployment.

monitor · Real-time on-call alerting with context-aware thresholds.

research-specialist · When you need deep, multi-source research on a topic with citations and expert identification.

data-content-engineer · Specialized subagent work that requires domain expertise and isolated context.

domain-reviewer · When a refactoring needs systematic validation that the code still compiles, passes tests, and maintains API contracts at scale across a large codebase.

trace-pipelines · When understanding end-to-end call chains with explicit intermediate data is critical.