A practical 20-minute workflow to draft, prompt, and edit a 7-email B2B cold outreach sequence in Claude — with the actual subject lines, send days, and body copy you can adapt.
Why naive prompts produce JSON-LD that fails Google's validator, and the prompt structure plus validation loop that ships schema clean on the first or second pass.
A 5-step workflow to turn 300 orphan pages into a connected graph in one afternoon — by letting Claude read your sitemap and propose contextually anchored internal links.
A step-by-step workflow for using Claude as a co-strategist to map a complete 5-stage lifecycle email flow — Welcome, Activation, Engagement, Conversion, Retention — in one session, with the exact prompts, pushback moves, and failure modes to watch for.
Most influencer briefs are 6 pages of corporate throat-clearing that creators skim in 90 seconds and ignore. Here's the exact Claude prompt, the 5 inputs you need, and the 1-page template that gets 100% brief-completion on mid-tier campaigns.
The exact four-step pipeline I run on every podcast interview — clean recording, Otter transcription, a Claude prompt for show notes, and separate prompts for LinkedIn and Twitter. Time from raw audio to three published assets: about 90 minutes.
Most retargeting ads run the same copy to a 90-day site visitor and a 4-hour cart abandoner. Here's the single-session Claude workflow I use to write cold, warm, and hot variants that match where the user actually is in the funnel.
Two free Google tools give you the rawest data on what your site is doing. Pair them with Claude and you get content decisions in 90 minutes that would take a week in spreadsheets. Here's the exact workflow, the prompt template, and the three questions it reliably answers.
Stop building dashboards backwards. 12 chart types, the question to ask before each, and copy-paste Claude prompts to design Looker Studio dashboards that survive a Monday morning executive review.
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.
A working Claude Computer Use agent that opens your Meta Ads Manager, reviews every ad against a 2-axis rubric (policy + brand consistency), and drops a CSV of red/yellow flags in 12 minutes — the system prompt, the build, and where the false-negative floor sits.
