Turns customer feedback into structured output
The source asks the model to group, classify, answer, or prioritize review feedback rather than treating every comment as an isolated case.
SEO Audit is an ecommerce AI skill for Corey Haines (marketingskills), built for teams working with Codex, Claude Code, OpenClaw. Use it to you are investigating why…
You are investigating why a product, category, or landing page is missing expected organic traffic. Do not change every step at once: test Diagnosing why organic traffic dropped after a Google algorithm update alongside Running a pre-launch SEO health check on a new marketing… Start with a small test around “Diagnosing why organic traffic dropped after a Google algorithm update”, then check whether “Running a pre-launch SEO health check on a new marketing site” fits the way your team actually works.
The source asks the model to group, classify, answer, or prioritize review feedback rather than treating every comment as an isolated case.
The source covers product or listing copy alongside SEO-related fields such as keywords, metadata, or image text when those fields are requested.
The source asks for analysis, classification, ranking, or scoring before it reaches a conclusion or next action.
This instruction refers to file or tabular input. Prepare the requested file and confirm that the model you use can read it.
The complete source is shown below. Copy it from the top right to use it.
You are an expert in search engine optimization. Audit the site in five priority areas: 1) Crawlability & Indexation — check robots.txt, XML sitemaps, canonicals, noindex tags, redirect chains, and crawl budget for large sites; 2) Technical Foundations — verify HTTPS, mobile-friendliness, Core Web Vitals (LCP <2.5s, INP <200ms, CLS <0.1), URL structure, and site speed; 3) On-Page Optimization — review title tags (50-60 chars), meta descriptions, H1/H2/H3 hierarchy, image alt text, internal linking, and keyword targeting; 4) Content Quality — assess uniqueness, search intent match, E-E-A-T signals, and thin content risks; 5) Authority & Links — evaluate backlink profile and internal link equity distribution. Never report 'no schema found' based on web_fetch alone — use browser tools or Google Rich Results Test for JS-injected JSON-LD. Deliver a prioritized action plan with Critical/High/Medium/Low impact levels and specific remediation instructions.Starter prompts for the main use cases—copy and use them directly.
Do not begin with a store-wide rollout. Pick one reversible task where SEO Audit can help you create, localize, or check product content and visual assets. Use this when the input boundary, owner, and one primary measure from factual corrections, editing time, approval rate, and conversion quality are written down.
Use the Skill above to help me with this task: Start with one real task.
Task details: [TASK_DETAILS]
Constraints or policies to follow: [CONSTRAINTS]
Do not begin with a store-wide rollout. Pick one reversible task where SEO Audit can help you create, localize, or check product content and visual assets.
Return a practical result and clearly flag anything that needs human review.[TASK_DETAILS][CONSTRAINTS]Collect only the verified product facts, source images, brand rules, target channel, and prohibited claims needed for this test. Remove unrelated personal data and state which actions must never run automatically. Use this when every input has a known source, sensitive fields are minimized, and the approver knows what the trial can read or change.
Use the Skill above to help me with this task: Prepare the input and guardrails.
Task details: [TASK_DETAILS]
Constraints or policies to follow: [CONSTRAINTS]
Collect only the verified product facts, source images, brand rules, target channel, and prohibited claims needed for this test. Remove unrelated personal data and state which actions must never run automatically.
Return a practical result and clearly flag anything that needs human review.[TASK_DETAILS][CONSTRAINTS]Read the source, installation method, and permission notes before adding SEO Audit to a separate test project. Keep commands and Skill text exactly as published. Use this when you have a product-content draft that a responsible operator can inspect, and it stayed inside the approved boundary.
Use the Skill above to help me with this task: Inspect the source Skill, then run it.
Task details: [TASK_DETAILS]
Constraints or policies to follow: [CONSTRAINTS]
Read the source, installation method, and permission notes before adding SEO Audit to a separate test project. Keep commands and Skill text exactly as published.
Return a practical result and clearly flag anything that needs human review.[TASK_DETAILS][CONSTRAINTS]Do not judge the result by fluency. Compare it with source data, the current SOP, and the pre-test baseline; record factual errors, omissions, and editing time. Use this when factual corrections, editing time, approval rate, and conversion quality has a pre-test baseline, and errors and exceptions are logged separately.
Use the Skill above to help me with this task: Review it against a baseline.
Task details: [TASK_DETAILS]
Constraints or policies to follow: [CONSTRAINTS]
Do not judge the result by fluency. Compare it with source data, the current SOP, and the pre-test baseline; record factual errors, omissions, and editing time.
Return a practical result and clearly flag anything that needs human review.[TASK_DETAILS][CONSTRAINTS]When this instruction drafts marketing or product content, review specifications, comparisons, performance claims, and testimonials against approved evidence before publishing.
The instruction can group and prioritize feedback, but repeated wording is not proof of a product defect or customer-wide preference. Check the underlying sample before changing a product, policy, or campaign.
Creator of Marketing Skills, an open-source collection of reusable agent skills for content, SEO, conversion, launch, and growth work.
Review third-party permission scopes before providing store data. Never paste payment credentials, customer passwords, or unnecessary personal data into a model. Outputs must be checked by the operator responsible for the workflow.
Content checked:
No reviews yet.