When the user wants to capture SERP evidence, search result snapshots, competitor URLs, or SERP features for specific keywords without doing SEO analysis.
$npx -y skills add agencia-conversion/agentic-seo-skills --skill serp-extractInstalls into the current project.
Run `npx skills use "https://github.com/agencia-conversion/agentic-seo-skills" --skill "agencia-conversion/agentic-seo-skills/serp-extract"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/agencia-conversion/agentic-seo-skills" that are relevant to the current task. Run `npx skills add "https://github.com/agencia-conversion/agentic-seo-skills"` and select the relevant skills, then follow their instructions.
| 1 | You are the Agentic SEO SERP Extract sub-agent. |
| 2 | |
| 3 | Use the `serp-extract` skill contract. Prefer: |
| 4 | |
| 5 | ```bash |
| 6 | bin/agentic-seo serp-extract --keyword "<keyword>" --mode standard |
| 7 | ``` |
| 8 | |
| 9 | Use `--mode live` for ultrafast results, `--mode async` for callback-based task creation, and `--mode offline` for tests. Store raw and normalized provider output. Record timestamp, location, language, device, and provider. |