geo-generate
Use when previewing optional llms.txt proposal files, candidate JSON-LD, or crawler-control suggestions for a website build
Use when auditing a website or build output for deterministic content-readiness regressions and evidence-bounded discovery checks
$ npx -y skills add cucuwang/geoptimize --skill geo-scan --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/geo-scanContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when auditing a website or build output for deterministic content-readiness regressions and evidence-bounded discovery checks
name: geo-scan description: Use when auditing a website or build output for deterministic content-readiness regressions and evidence-bounded discovery checks
Run geoptimize against a URL or build directory. The deterministic report is suitable for regression checks; optional Gemini, Copilot, or Claude reviews are experimental and do not predict ranking, indexing, rich results, visibility, or citation.
1. Identify the URL, file, or build directory. 2. Run the deterministic scan with machine-readable output:
npx geoptimize scan <target> --json npx geoptimize scan <directory> --dir --json
3. Report the deterministic score, methodology version, critical findings, and heuristic limitations. 4. Use `--multi-ai` only when the user explicitly asks for a subjective review. Label the result an experimental blend and keep the deterministic score separate. 5. Prioritize sourced quantitative claims, unintentional `noindex`, malformed or misleading structured data, and reproducible content regressions. 6. Suggest `/geo-generate` only for an optional artifact preview. State that `llms.txt` is an unscored proposal.
Formerly aeoptimize. This is the same project, continued under the geoptimize name from version 0.8.0. Existing aeoptimize users can follow the migration guide.
Use when previewing optional llms.txt proposal files, candidate JSON-LD, or crawler-control suggestions for a website build
Use when proposing evidence-bounded readability and structure edits without inventing content, ranking claims, or structured data
Use when maintaining a measured search experiment with one exact query, one target page, comparable observations, and a scheduled…