content-brieflisted
Install: claude install-skill sitetiller/ai-visibility-skills
# Content brief from evidence
Goal: a brief a writer can follow, where every requirement traces to a query the site already gets, a result the user observed, or a line in Google's guidance. Search volume is never invented. Search Console shows impressions for the user's own site, and that is the only demand number used. If the user has a third-party volume figure, they supply it and the brief labels it with its source.
## Inputs
- The topic, and Search Console access (see `gsc-bing`) or a Queries/Pages export.
- The live results page for the main query, pasted by the user with the date: titles, URLs, features seen (AI overview, video, forum threads). The CLI does not scrape Google results and this skill does not either.
- Whether the page is new or replaces an existing one (run `cannibalization` first).
## Steps
1. Pull the site's own data, 90 days if available:
```bash
npx sitetiller gsc example.com --start 2026-08-12 --end 2026-11-09 --dims query,page --out qp.csv
npx sitetiller gsc example.com --start 2026-08-12 --end 2026-11-09 --dims query --out queries.csv
```
Filter rows to the topic by text match and group them by meaning (`topic-clusters`). Note which page each query lands on today and at what position. Related queries at positions 4-20 show relevance the site already has:
```bash
npx sitetiller striking queries.csv --json
```
2. If an existing page already receives these queries, decide with `cannibalization` whether to extend it instead o