Included in Search and SEO skills
Organic Opportunity Map
v4.0.1A sourced page-action queue with commercial fit, current page ownership, concrete edits, rejected topics and a complete research receipt.
Turn search demand, current SERPs and inspected site content into prioritised decisions about which pages to improve or create.
What this Skill does—and does not do
The Skill does not promise rankings, treat sampled keyword absence as proof of a gap, publish content, change a website or expand beyond the approved market and sample sizes.
Inputs
- One public target domain
- One country and language
- Business objective, audience and any excluded topics
Outputs
- Sampled target and competitor evidence
- Prioritised update/create/hold page decisions with concrete edits and acceptance checks
- Rejected topics and unresolved evidence
- Claim-to-source ledger and complete research receipt
How this Skill works
- 1
Share the starting information
Give your agent the inputs listed above and explain the result you need.
- 2
Review the plan
Your agent reviews the proposed tools, inputs and maximum cost before any paid work begins.
- 3
Let your agent run the workflow
After you approve the plan, your agent uses the live Scrollport tools shown on this page and keeps the work inside the agreed limits.
- 4
Review the finished result
After approval, your agent returns the promised output and reports the tools used, final cost and any limitations.
Full instructions your agent receives
Use get_run({ run_id, wait_seconds? }) to read a saved run before any retry; no idempotency key is accepted. Waiting defaults to 50 seconds and accepts 0–120. run_tool starts only and requires tool_id, input and one UUID per paid intent; retain that UUID for an exact retry after an uncertain start. Every state retains run_id.
Organic Opportunity Map
Deliver a defensible queue of page decisions a business can act on. Combine measured search demand, current search results and the site's actual content. A keyword list alone is unfinished.
Use one authorised Scrollport connection through search_tools, inspect_tool, run_tool, get_run, list_apps and get_wallet. Discover by intent and inspect current contracts before spending; never bypass Scrollport to call a supplier directly. Reuse sufficient supplied exports; when new calls are prohibited, work within that evidence and mark missing provenance rather than recollecting it.
Establish the job
Read supplied business context first, including .agents/product-marketing.md when present; context claims still need evidence. Resolve domain, country, language, audience, revenue objective, exclusions and budget from the request. Ask only for a missing choice that would change the recommendations.
Distinguish customer segments, brand aliases and business entities; separate business competitors from domains merely ranking for the same phrase. When the user delegates choices, state assumptions and proceed within scope.
Cost and approvals
How pricing works
Bounded domain samples and keyword validation, current SERPs and selected page extraction.
Your approval points
- Use existing authorisation for the business, market, bounded selection rules and total maximum; obtain missing approval before spending
- Pause for a server confirmation request or a material scope or budget expansion
- No publishing or website writes without explicit scope
Related Resources
SEO agents: tools, workflows and controls
Learn how AI SEO agents use live search data to automate keyword research, SERP analysis and page decisions without automating away human judgment.
How an SEO agent turns noisy keyword data into a defensible content decision
See how an SEO agent used Scrollport to research keyword demand, test a content idea and produce an evidence-backed article under editorial supervision.
Real AI agent workflow examples: practical guides and evidence
Compare practical AI agent workflow guides with field-tested examples backed by reproducible run evidence, observed cost and editorial review.