A 0-100 pre-publish scorecard that scores any post on E-E-A-T, Depth, Freshness, and Structure (25 each), with a single Claude prompt that does all four in one pass plus a remediation list. The 75/100 + no-dimension-below-16 publish gate, the batch-of-10 audit workflow, and the hard reason a rubric beats vibes-based editing when you have 200+ posts and staff turnover.
A 5-step, sprint-based playbook for refreshing a large content archive with Claude and Google Search Console — built around three measurement gates that keep you out of Helpful Content trouble.
Every Monday at 8:14 a.m. a Slack message lands with 4-9 underperforming posts. The n8n + Claude agent that writes it, the prompts that make Claude useful (and the ones that make it noisy), and the three things I changed after six weeks of running it for real.
