Please do an SEO report for Plunkett Homes last month.

Routes when a Jessie-assigned Asana task asks for SEO, organic search, Search Console, rankings, backlinks, or organic movement reporting.

• Expanded forensic Plunkett smoke on 2026-05-19 produced plunkett-homes-april-2026-forensic-seo-report.html.
• Hosted evidence included GSC, GA4, DataForSEO SERP, Semrush backlink, and Browser Run crawl signals where available.
• DataForSEO Backlinks API remains disabled until the subscription is active; Semrush supplies backlink evidence.

---
name: seo-reporting
description: Agency OS Channel Skill for SEO reporting tasks. Use when an agent is asked to review SEO performance, explain organic search changes, draft consultant-facing reporting, recommend SEO follow-up work, write source-backed evidence, or propose reviewed context updates for a client such as the Plunkett SEO Operating Slice.
---

# SEO Reporting

Use this skill to produce a consultant-facing SEO reporting draft from an approved client context pack and a dated SEO data snapshot.

## Operating Rules

- Treat Asana as the task surface and review trail.
- Treat the client context pack as bounded context, not unrestricted client memory.
- Treat Search Console as the primary SEO visibility source.
- Treat GA4 as the source for organic traffic and conversion context.
- Use a universal SEO intent taxonomy first: Brand, Commercial category, Product/service, Location, Comparison/consideration, Price/cost, Informational, Navigational/support, Competitor, and Unknown / needs review.
- Derive client-specific query clusters from source data and context; do not require client-specific clustering rules for each rollout.
- Use DataForSEO SERP checks and Semrush backlink reports as supporting evidence unless the task explicitly asks for deeper keyword, SERP, or link research.
- Treat explanations as evidence-backed hypotheses, not hard attribution. SEO work, backlinks, crawl/indexation changes, and SERP movement can influence results with a same-period or lagged effect.
- When a likely cause is stated, include the supporting evidence, confidence, expected lag, and the next follow-up needed to confirm or reject it.
- Route model drafting through Cloudflare AI Gateway using OpenAI `gpt-5.5`.
- Limit Cloudflare AI Gateway custom metadata to five primitive values.
- Keep evidence writes separate from trusted context changes.
- Propose durable context updates for review; do not silently rewrite trusted context.
- Do not publish client-facing reports, create external tasks, change websites, change tracking, or alter strategy without human approval.

## Inputs

Require these before drafting:

- Asana task with brand, report period, audience, questions, and expected outputs.
- Client context pack manifest with trusted `brief/`, `rules/`, and current `work/` or priorities context.
- SEO data snapshot with source metadata, date range, freshness, caveats, Search Console metrics, and GA4 organic metrics.
- Optional supporting snapshots for rank/SERP movement, backlinks/referring domains, page changes, crawl/indexation checks, and completed agency work.
- Approval gates for client-facing action, external system writes, and new secrets or credentials.

Use `fixtures/plunkett-seo-reporting-input.example.json` as the current synthetic contract fixture.

## Workflow

1. Validate the task request, context pack manifest, data snapshot, model policy, and approval gates.
2. If required fields or guardrails are missing, ask for clarification instead of drafting.
3. Summarise Search Console visibility movement.
4. Cluster query and page movement using the universal SEO intent taxonomy.
5. Connect GA4 organic sessions and conversions to the visibility movement.
6. Add rank-tracking or SERP evidence only when supplied in the snapshot.
7. Add backlink/referring-domain and crawl/indexability evidence only when supplied in the snapshot.
8. Build cross-source movement clusters that join page-level Search Console, GA4, SERP URL, backlink page, and crawl evidence where available.
9. Drill into major movements, candidate causes, confidence, time lag, and next inspection steps.
10. Draft findings with explicit evidence references and confidence.
11. Recommend next actions for consultant review.
12. Write or plan an evidence artifact under `evidence/`.
13. Plan any durable context changes under `proposed-updates/` for review.

## Output Shape

Return:

- Executive summary.
- Evidence-backed findings.
- Cross-source movement clusters for the highest-priority page movements.
- Candidate cause hypotheses with confidence, same-period or lagged timing, and follow-up checks.
- Recommended next actions.
- Data quality notes.
- Evidence write plan.
- Proposed context update plan.
- Approval-gated actions not taken.
- AI Gateway model-call plan.

Target consultant delivery format:

- Generate a detailed internal HTML report page for easy consultant consumption.
- Attach the HTML file to the source Asana task, or link the Asana task to a stable hosted artifact.
- Keep client-facing rollup reports as a later approved output derived from the internal forensic report.

## References

- Read `references/plunkett-pilot.md` for the current pilot boundary and open decisions.
- Read `../../docs/plunkett-seo-reporting-agent-skill-proposal.html` for the reviewed proposal.

• Forensic Plunkett Seo Report decisions/forensic-plunkett-seo-report.md
• Team Agent Work Intake docs/runbooks/team-agent-work-intake.md
• Plunkett Seo Reporting Skill docs/runbooks/plunkett-seo-reporting-skill.md