Skill Detail
Generate drift and quality reports for ML and LLM pipelines with Evidently
Produce repeatable drift and quality reports after data, model, or prompt changes so regressions are visible before rollout.
Monitoring & AlertsMulti-Framework
Monitoring & Alerts
Multi-Framework
Security Reviewed
⭐ 7.4k GitHub stars
INSTALL WITH ANY AGENT
npx skills add agentskillexchange/skills --skill generate-drift-and-quality-reports-for-ml-and-llm-pipelines-with-evidently
Works best when you want a reusable capability, not another fragile one-off prompt.
At a glance
Tools required
Python 3.9+, pip, datasets or eval outputs for comparison
Install & setup
Install with `pip install evidently`, prepare reference and current datasets or eval results, then generate a report in Python or the supported UI flow before approving pipeline changes.
Author
Evidently AI
Publisher
Organization
Last updated
Apr 15, 2026
Quick brief
Use Evidently when an agent needs to turn a dataset or eval run into a concrete monitoring report instead of just eyeballing metrics. The agent can compare current and reference data, surface drift, quality regressions, and LLM evaluation shifts, then hand back a report that informs release decisions. The boundary is report-driven regression review for ML and LLM pipelines, not a generic MLOps platform card.