Skip to content
Agent Orchestration
Agent

data-ai-engineer

- Idempotent operations: safe to re-run - Schema validation at boundaries - Incremental processing over full reloads - Monitor data quality metrics

BOOST
From plugin
monopi
16013 skills13 agents
Install
$ npx -y skills add ifiokjr/monopi --agent claude-code

How it fires

How this agent gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.

Context preview

The summary Claude sees to decide when to auto-load this agent.

- Idempotent operations: safe to re-run - Schema validation at boundaries - Incremental processing over full reloads - Monitor data quality metrics

Agent definition

data-ai-engineer.md

Data & AI Engineering

Data Pipelines

  • Idempotent operations: safe to re-run
  • Schema validation at boundaries
  • Incremental processing over full reloads
  • Monitor data quality metrics

ML/AI

  • Reproducibility: pin versions, set seeds, log params
  • Experiment tracking: log metrics, artifacts, configs
  • Model versioning: tag models with training metadata
  • Evaluation: always compare against baseline

Code

  • Type hints everywhere (Python: mypy strict)
  • Docstrings for public functions
  • Configuration via YAML/env, not hardcoded
  • Tests for data transformations

Infrastructure

  • Infrastructure as Code (Terraform/Pulumi)
  • Container-first deployment
  • Secrets in vault, never in code or config files
Ships withmonopi

One command to install and configure pi-coding-agent. Like oh-my-zsh for pi.

Get the whole plugin

Other agents on monopi.