Code Review — Senior Engineer Pass
Reviews a diff for correctness, then security, then readability — in that order, with severity tags and a fix per finding.
Edits a 3,000-word draft for structure before style: argument order, missing evidence, dead sections. Returns a diff plan.
Generated with this exact template on claude. No retouching.
You are a senior editor. Do a structural pass on the draft: diagnose argument order, flag unsupported claims, identify sections that can be cut, then propose a revised outline. Do not rewrite prose yet.
The full template is 3× longer than this preview, and includes every variable with its tested example.
Licence : usage commercial du résultat, revente du texte interdite.
| Variable | What to put in it | Example used |
|---|---|---|
| draft | Paste the full draft | (your 2,000–5,000 word draft) |
Line editing a draft whose argument is broken is wasted work, and that is the default failure of AI editing: it polishes sentences that should not exist. This prompt forbids prose changes entirely and forces a structural diagnosis first.
The useful move is step 1 — stating the thesis as the draft actually argues it. Writers are routinely surprised by the gap between intent and what is on the page, and that gap explains most rejected pitches. Step 3's load-bearing rating tells you which unsupported claim is actually holding the piece up, so you fix that one instead of sprinkling citations everywhere. Works on essays, reports, and 3,000-word SEO pages alike.
Example output
Generated with this template — full output shown on the listing.
Sam Okafor @promptsmith
Copy chief turned prompt engineer. Long-form editing, SOPs, productivity systems.
The full claude template with all 1 variables, the example values we tested with, and permanent access from your dashboard. Outputs you generate are yours to use commercially.
Yes. You get commercial rights to anything the prompt produces. You may not resell or republish the prompt text itself, or pass it off as your own listing.
Request a refund within 24 hours of purchase. We compare the listing against your result — if the prompt does not do what this page claims, you get your money back.
Reviews a diff for correctness, then security, then readability — in that order, with severity tags and a fix per finding.
Turns a topic into a 10-chapter architecture with reader transformation, chapter jobs, and a page budget.
Turns a messy process into an SOP with preconditions, decision points, rollback, and an owner per step.
Sorts a batch of emails into reply-now, reply-later, delegate, archive — with the reply drafted for the first group.