Find a canonical mismatch
Inspect canonical tags across a small group of approved URLs. Record the visible tags and expected destinations so a developer can confirm whether the relationship is intentional.
Find and prioritize search issues using page evidence, supplied search data and the site’s intended indexing rules.
Give the agent approved URLs and search artifacts, then ask for evidence and a retest for each finding.
Provide sample routes, target index state and any authorized search export.
Copy the request into a new Floatboat conversation and provide the required material.
Download FloatboatPreview and copy the request. It is not sent automatically from this page.
Reference: SEO Audit https://github.com/coreyhaines31/marketingskills/blob/main/skills/seo-audit/SKILL.md Read the original documentation and check the current environment and dependencies. Propose any new installation or tool connection before proceeding. My task: Audit these approved product pages for canonical, indexing directive and title issues. Record the observed value and expected behavior for each URL. Rank the fixes and include a retest. Leave the files and search settings alone. Expected deliverable: A ranked audit report with URL-level evidence.
This MIT-licensed Skill guides an agent through technical and on-page search checks. It turns inspected URLs, crawl signals and authorized search data into a prioritized report. Access to private analytics or Search Console depends on the environment.
Choose checks that can be run with the evidence available. Separate observed issues from hypotheses that need search data or additional access.
Inspect canonical tags across a small group of approved URLs. Record the visible tags and expected destinations so a developer can confirm whether the relationship is intentional.
Compare supplied sitemap entries with representative changed routes. Mark unavailable URLs and unintended redirects with an observation date.
Provide authorized Search Console exports and the relevant deployment dates. Group affected pages and explain which causes the data supports and which need additional tests.
Inspect a defined set of commercial pages. For each issue, capture the URL, title or heading evidence, suggested change and a check that can be repeated.
Start with a representative set of URLs and a specific question about discovery or indexing. Pair each finding with the evidence and a way to retest it.
Provide approved URLs, the expected indexing state and any permitted exports. Use the repository’s product-marketing context if the project already has it.
Inspect pages and site signals. Record each observed issue with affected URLs and separate unverified hypotheses.
Rank issues by impact and effort, and attach a retest for each suggested fix.
Read another Skill guide and check its original source before using it.