← ClaudeAtlas

quick-winslisted

Turn Search Console data into a ranked list of the 10 best next actions with effort and the arithmetic behind each estimate. Combines striking distance (positions 4-20 with real impressions), under-clicked rows against your own CTR curve, the branded versus non-branded split, and pages that lost clicks (decay). Estimates use only the site's own median CTR by position, shown step by step; no traffic forecasts are invented. Use when the user asks 'quick wins', 'where do I start with SEO', 'what should I fix first', 'low hanging fruit', 'pages close to page one', 'what to work on this month', or has Search Console exports and wants priorities.
sitetiller/ai-visibility-skills · ★ 0 · AI & Automation · score 75
Install: claude install-skill sitetiller/ai-visibility-skills
# Quick wins from Search Console Goal: a ranked list of 10 actions the user can do this month, each with the evidence row, the effort, and an estimate that shows its arithmetic. The estimate is a scenario computed from the site's own past CTR. It is not a forecast, and the skill never uses an industry CTR table. ## Inputs - Search Console data for the same date range in every file, at least 28 days: a Queries export and a Pages export (or `gsc` API output written to CSV, see `gsc-bing` and `setup`). - For decay: a Pages export from an earlier period of equal length. - Brand terms, so branded queries do not distort the curve. - Pages the user owns and may edit. ## Steps 1. Export the data: ```bash npx sitetiller gsc example.com --start 2026-08-12 --end 2026-11-09 --dims query --out queries.csv npx sitetiller gsc example.com --start 2026-08-12 --end 2026-11-09 --dims page --out pages.csv npx sitetiller gsc example.com --start 2026-05-14 --end 2026-08-11 --dims page --out pages-before.csv ``` 2. Split brand from non-brand first. Brand clicks usually come from people who already know the site, so they say little about what SEO work earns: ```bash npx sitetiller brand queries.csv --terms "acme,acme.com" --json ``` Read `branded` and `nonBranded` (`queries`, `clicks`, `impressions`, `ctr`, `avgPosition`), `brandedClickShare` and `gscRegex` (paste it into a Search Console query filter set to "Custom (regex)" to check the split by hand). Report non-brand