← ClaudeAtlas

publish-preplisted

Run the finished draft through the full pre-publish check before it goes live. Verifies the SEO basics, the image and link rules, the humanisation and anti-repetition rules, the E-E-A-T and differentiation rules, and fact-checks every number against its named source. Builds the meta, slug, key takeaways, and FAQ-from-real-PAA. Run last in the content pipeline. Produces a publish package and a pass/fail checklist, then stops.
robdasi/skills · ★ 0 · AI & Automation · score 75
Install: claude install-skill robdasi/skills
# Publish Prep A good draft still loses if the title is too long, an image sits right after a table, a stat is unsourced, or the opening matches three other articles on the site. This is the checklist that catches all of it before publish, not after. Read every check, verify it passes, fix the failures. Run last, after `draft-writer`, with the site brief and banks to hand. ## The checks **SEO** - Meta title 60 characters or fewer, focus keyword near the front. Count them. - Meta description 120-160 characters, focus keyword present. Count them. - First heading is `##`. No `#` anywhere in the body. - Primary keyword in the first 1000 characters; density around one per 200 words, at least twice. - Every secondary keyword appears at least once. Check each. - Word count meets or beats the top-three competitor average from the gap analysis. **Images** - One per 350-500 words, minimum two, at least one in the first 500 words. - No image directly after a table, and never two images back-to-back without prose between. - Focus keyword in at least one alt tag; every alt is descriptive, never "screenshot" or "image". - No image reused from another article. Real screenshots or charts with real numbers over generic AI images. **Links** - Max two internal links per section, none in the conclusion, at least one crossing content clusters. - A citation link at the first mention of every named tool, platform, or source. - No duplicate external links to the same URL; roughly 0-3 external