← All runbooks
gooseworks-ai / capabilities-seo-traffic-analyzer

SEO and Traffic Analyzer

Analy

agent codexmodel gpt-5.5snapshot python312-uveval programmatic7 stepsv1.0.0

Deploy SEO and Traffic Analyzer to your jetty.io

One-click installs this runbook into a collection on your Jetty account. You can run it from the Spot dashboard, schedule it, or pipe inputs in via the API.

Deploy on jetty.io →View source
The shape of the run

7 steps · start to finish.

  1. 1
    Step 1

    Environment Setup

    ▶
    1. Create /app/results if it does not exist.
    2. Resolve the target domain and normalize it to a registrable domain without protocol or path.
    3. Initialize /app/results/raw_observations.json with arrays for queries, pages, competitors, keywords, and caveats.
    4. If a required target domain is missing, write validation_report.json with overall_passed=false and stop.
  2. 2
    Step 2

    Gather Search Evidence

    ▶

    Run the source skill's search probes and record every query, result URL, observation, and timestamp in `raw_observations.json`.

  3. 3
    Step 3

    Analyze Rankings and Content

    ▶

    For each target keyword, search for the keyword with and without the brand name. Record whether the target domain appears in visible results, which competitors appear, and what content type is ranking. Treat ranking position as approximate unless an exact search result position i

  4. 4
    Step 4

    Compare Competitors

    ▶

    For every competitor domain provided, repeat the core indexation checks and compare indexed footprint, visible content themes, conversion pages, and apparent positioning. Keep comparisons evidence-backed and cite the query or fetched page that supports each claim.

  5. 5
    Step 5

    Generate Outputs

    ▶

    Write `/app/results/seo_traffic_report.md` with sections for overview, indexation footprint, keyword visibility, traffic estimate context, competitor comparison, content gaps, recommendations, and caveats. Write `/app/results/summary.md` as a concise executive summary for decisio

  6. 6
    Step 6

    Validate Evidence

    ▶

    Check that every material claim in the report is backed by an entry in `raw_observations.json`. If evidence is weak, downgrade the confidence label instead of overstating the conclusion.

  7. 7
    Step 7

    Iterate on Errors (max 3 rounds)

    ▶

    If validation fails, perform at most 3 rounds of targeted fixes: gather the missing evidence, revise unsupported claims, regenerate the affected output file, and rerun validation.