ChatGPT Prompts for SEO: 25 Prompts That Carry Your Data

Role: You are a senior SEO analyst who works only from evidence.

My data (Google Search Console query export):
[paste your Queries.csv rows]

Task: Group these queries into topic clusters. For each cluster give total impressions, total clicks, impression-weighted average position, and the highest-leverage query.

Constraints: Use only the numbers I pasted. Do not estimate search volume or keyword difficulty; tell me to validate new targets in a keyword tool instead. No cluster smaller than 2 queries.

Format: A table (Cluster | Impressions | Clicks | Weighted position | Top query), then 3 bullets on the biggest opportunity.

Before answering: check your maths on one cluster and show the check. If my paste looks cut off, ask for the rest first.

Role: You are an SEO strategist assigning queries to pages.

My queries:
[paste 10-30 queries]

Task: Classify each query's intent (informational, commercial, transactional, navigational) and the page type that wins it (guide, comparison, product, category, tool, FAQ).

Constraints: If a query is ambiguous, give both readings instead of forcing one. No advice paragraphs.

Format: Table (Query | Intent | Page type | One-line why). Finish with queries that should SHARE one page rather than each getting their own.

Before answering: flag every low-confidence row so I can check the live results myself.

Role: You are an AI search strategist. I want the map of questions an AI engine explores when someone asks about my topic.

My topic:
[your topic or target query]

My audience:
[who searches this and what they are trying to do]

Task: fan this topic out into the related questions an AI engine would pull answers for: comparisons, how-tos, costs, risks, alternatives, "for [situation]" variants. Group them by the single page that should own each group.

Constraints: questions must be ones a real person would ask, in their words. No invented search volumes. If a group is too thin to deserve its own page, fold it into another and say so.

Format: table (Question group | The questions | Page that should own it), then the 3 groups to build first.

Before answering: mark any group you are unsure real searchers ask, so I can validate it before building.

Role: You are a content researcher building a coverage matrix. I am deciding what my page must include to beat the current results for "[target query]".

The ranking pages' content (labelled A, B, C):
[paste the headings or full text of the top 2-3 ranking pages, labelled A, B, C]

Task: build the coverage matrix: every distinct angle, claim, or subtopic those pages cover, classified as consensus (all cover it) or partial (some do). Then add the angles a subject expert would expect that none of them touch.

Constraints: classifications come only from the pasted content, no guessing what a page "probably" says. The missing-angles list is where I will differentiate, so make it specific to this query, not generic "add more examples" filler.

Format: table (Angle | A | B | C | Status), then the missing angles ranked by how much a searcher would care.

Before answering: name any angle where you inferred coverage rather than saw it in the paste.

Role: You are a demand researcher. Below is raw language from my actual customers.

My customer language (anonymised):
[paste sales emails, support tickets, call notes, or reviews, anonymised]

My core topic or service:
[your core topic or service]

Task: extract every question and problem phrasing that relates to my seed topic, deduplicate, and group by funnel stage: still researching, comparing options, ready to act.

Constraints: keep the customers' own wording as the canonical phrasing; do not translate it into marketing language. Flag anything that still identifies a person. No invented questions.

Format: three funnel-stage lists in the customers' words, with a closing call per group: FAQ answer, dedicated page, or a section on an existing page.

Before answering: flag any question that appears only once, so I know it is a single data point rather than a pattern.

Role: You are a content strategist who refuses to produce consensus content.

Target query: "[query]"

The current top 3 pages' headings:
[paste their H2s/H3s]

What I have that they do not:
[2-5 bullets of your real experience, data, or contrarian take]

Task: Build an outline that compresses the consensus and leads with my unique material.

Constraints: Every H2 is a question. My unique material goes in the first third. If my bullets are too weak to differentiate, say so bluntly.

Format: H1 + H2/H3 skeleton, one line under each H2 saying what the section proves. Tag each section [CONSENSUS] or [NEW].

Role: You are a content strategist writing a brief another writer could execute without asking questions.

My target:
Query: [target query]
Searcher intent: [what the searcher is trying to do]
Audience: [who they are]

My angle:
[2-5 bullets: the experience, data, or position that makes this page different]

Task: produce a complete brief: working title, the angle in one sentence, H2/H3 skeleton with one line per section on what it must prove, entities and terms the page must cover, internal links to include, and the evidence the writer needs to gather before starting.

Constraints: the unique angle leads the brief and the outline's first third. If my angle bullets cannot carry a differentiated page, stop and say what would. State the word range the job needs, no padding for its own sake.

Format: one brief document with labelled sections, ending with a pre-flight checklist for the writer.

Before answering: read the brief back as the writer and list any question they would still have to ask, then answer it in the brief.

Role: You are diagnosing a page whose growth stalled. Here is the page and its search data:

My page copy:
[paste the page copy]

The page's Search Console queries:
[paste the page's queries: query, clicks, impressions, position, ideally this period vs last]

Task: diagnose why the page stopped growing and prescribe the refresh: sections to add, rewrite, or cut, plus any title or heading changes, each tied to a query in the data.

Constraints: every prescription must trace to evidence in the paste. If the data says the page is fine and the topic simply peaked, say "leave it alone" and stop; do not prescribe a rewrite to justify the exercise.

Format: diagnosis in 3 bullets, then a prioritised change list (Change | Evidence | Effort), then the one change to make first.

Before answering: list the queries you could not explain with the current content, so I can decide whether they deserve a new page instead.

Role: You are building a comparison page a reader could fact-check. Here is the real material:

Option A (real specs, pricing, hands-on notes):
[name + real specs, pricing, limits, your hands-on notes]

Option B (same detail):
[the same for the second option]

My context:
[your relationship to the products: affiliate, vendor, neutral, and who the reader is]

Task: structure the comparison: the criteria that actually decide the choice, the comparison table, the honest verdict logic (who should pick A, who should pick B), and where my relationship to the products must be disclosed.

Constraints: use only the pasted specs and mark gaps [NEEDS DATA] instead of filling them. The verdict must follow from the table, so no crowning a winner the criteria do not support. If the options are near-identical, say a comparison page is the wrong format.

Format: page skeleton with the table, the verdict section, and the disclosure placement.

Before answering: list every claim in the skeleton a reader could challenge, with the spec that backs it.

Role: You are a ruthless line editor.

My draft:
[paste it]

Task: Edit so a practitioner believes a human wrote it, preserving every factual claim.

Constraints: Delete sentences that say nothing. Replace hedges with plain claims or cut them. Remove formulaic transitions ("In today's fast-paced world", "It's worth noting"). Add no new facts. Keep my numbers exactly.

Format: The edited draft, then the list of patterns you removed so I stop producing them.

Before finishing: reread and cut a further 10%.

Role: You are restructuring content to be quotable. Here is a section and the query it should answer:

My section:
[paste the section]

The query it targets:
[the question this section targets]

Task: rewrite the section so the first sentence answers the query directly, in the query's own grammar, with the key term in bold. Evidence, nuance, and caveats follow the answer instead of preceding it.

Constraints: keep every fact; move them, do not cut them. The opening answer must stand alone if quoted with nothing around it. No throat-clearing ("When it comes to...").

Format: the rewritten section, then the standalone answer sentence on its own line so I can see exactly what an AI engine would lift.

Before answering: read the first sentence alone. If a searcher who saw only that would still be unsure, rewrite it and show both versions.

Role: You are an editor adding credibility a reader can verify. Here is my draft and my actual experience:

My draft:
[paste the draft]

My real, checkable experience:
[real, checkable material: years doing this, projects or clients, data you gathered, mistakes you made, tools you use daily]

Task: weave the experience into the draft where it does argumentative work: first-person observations attached to the claims they support, real examples replacing hypothetical ones, and the limits of my experience stated plainly.

Constraints: use only what is in my credentials; invented experience is worse than none. Do not bolt on an "about the author" paragraph, the signals belong inside the argument. Flag every claim that still stands on nothing as [NEEDS PROOF].

Format: the revised draft with the additions in bold, then the [NEEDS PROOF] list.

Before answering: confirm every added first-person statement traces to my credentials paste.

Role: You are rewriting SERP packaging for click-through rate.

The page ranks for "[query]" at position [X]. Current title: [title]. Current meta: [meta].

Task: 5 title options and 3 meta options carrying the query's exact words near the front.

Constraints: Titles under 60 characters, metas under 155. No promise the page cannot keep. No title that is just keywords and a brand pipe.

Format: Numbered options with character counts and a one-line "why this earns the click".

Before answering: flag any option whose promise exceeds the page.

Role: You are writing SERP packaging in batch. Here are my pages:

My pages (one per line: URL | title | primary query | what the page offers):
[one per line: URL | title | primary query | what the page offers]

Task: write one meta description per page that carries the primary query's words early and gives a concrete reason to click.

Constraints: under 155 characters each. No "Learn more about...", no "Welcome to", no promise the page cannot keep. Each meta must differ meaningfully from the others, not one template with swapped nouns.

Format: table (URL | Meta | Character count).

Before answering: recount the characters on the three longest and show the counts. If a page's input was too thin to write an honest meta, flag it instead of padding it.

Role: You are auditing how machines read my page's structure. Here is the page:

My page (headings marked):
[paste the page copy with its headings marked, or just the heading list]

The primary query:
[the primary query the page targets]

Task: audit the heading hierarchy: one H1 that carries the query, H2s phrased as the questions searchers ask, no skipped levels, and sections ordered by importance to the searcher rather than by writing order. Then propose the corrected skeleton.

Constraints: keep headings honest to the content beneath them; never rename a section to promise something it does not deliver. If a section answers no plausible question, recommend cutting it rather than reheading it.

Format: issues list (Issue | Heading | Fix), then the full revised H1-H3 skeleton.

Before answering: under each revised H2, state the search query it now answers. An H2 with no query gets flagged, not defended.

Role: You are a structured-data specialist who marks up only what exists.

My page copy:
[paste the visible content]

Task: Write a 4-6 question FAQ a reader of this page still needs answered, then the matching FAQPage JSON-LD.

Constraints: Every answer must be supported by the pasted content; mark anything unsupported [NEEDS SOURCE] instead of inventing it. The schema text mirrors the visible answers word for word.

Format: FAQ as headings + paragraphs, then one JSON-LD code block.

Before answering: confirm the JSON is valid and each schema answer matches its visible twin.

Role: You are a structured-data specialist who marks up only what exists. Here is my product page:

My product page copy:
[paste the visible product page copy: name, price, availability, description, review content if genuinely on the page]

Task: produce Product JSON-LD with offers, built from the visible values.

Constraints: every value must appear on the page. Missing values become [NEEDS VALUE], never a guess. No aggregateRating unless real review data is in the paste; invented ratings are the fastest route to a manual action.

Format: one JSON-LD block, then the [NEEDS VALUE] gaps and where each value should come from.

Before answering: confirm the JSON parses, then walk each field back to the sentence in my paste it came from.

Role: You are a technical SEO lead defending priorities to a client.

My crawl export:
[paste rows: URL, status, title, meta, canonical, indexability]

Task: Group issues by type, then rank groups by likely traffic impact.

Constraints: Only what is in the data. A 404 nobody links to is not priority one. Separate mechanical fixes from judgement calls.

Format: Prioritised list: issue, count + 3 example URLs, impact reasoning, the fix.

Before answering: name the columns missing from my paste that would change the ranking.

Role: You are a crawler, reading my robots.txt exactly as written. Here it is:

My robots.txt:
[paste your robots.txt]

My concerns (optional):
[optional: what you are worried about, e.g. "is anything blocking AI crawlers?"]

Task: explain what each rule actually does, then flag the gaps between intention and effect: rules that block more than intended, AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended) allowed or blocked without a stated decision, and directives that do nothing.

Constraints: read the file literally, as a crawler would, without assuming what I meant. Distinguish "blocked from crawling" from "blocked from indexing", because robots.txt only controls the first.

Format: rule-by-rule table (Rule | What it does | Risk), then a corrected file if changes are needed.

Before answering: state which user-agents you were unsure how to match, rather than guessing their behaviour.

Role: You are building a redirect map for a migration. Here are the URL sets:

Old URLs (one per line, ideally with titles):
[paste the current URLs, one per line, ideally with titles]

New URLs (one per line, ideally with titles):
[paste the new site's URLs, one per line, ideally with titles]

Task: map every old URL to the new URL that serves the same intent. Where no equivalent exists, assign the best parent category or recommend a 410, and say which.

Constraints: match by intent, never by URL similarity alone. No chains (old to old to new), and no mapping everything to the homepage, which throws away the equity the map exists to keep.

Format: CSV-ready table (Old URL | New URL | Type: exact / intent / parent / 410 | Note), then the unmapped list ranked by traffic risk.

Before answering: count both lists and confirm every old URL appears in the output exactly once.

Role: You are hunting the cheapest wins on the board.

My queries ranking 4-15 (query, page, impressions, position):
[paste]

Task: Choose the 5 highest-leverage rows and prescribe each one's packaging fix: the title change, the heading to add, or the paragraph that answers the query directly.

Constraints: Leverage = impressions x closeness to page one. Prescriptions must be paste-ready, never "improve the content".

Format: For each: query, page, one-line diagnosis, the fix ready to paste.

Before answering: where two queries compete on one page, pick the winner and say why.

Role: You are an internal-linking strategist.

My pages (URL + title, one per line):
[paste]

My new page:
[URL + 2-line summary]

Task: 3-5 existing pages that should link TO the new page, with the exact sentence and anchor for each, plus 2-3 outbound links the new page should carry.

Constraints: Anchor text matches the target page's title language. Only links a reader would follow. No footer/sidebar placements.

Format: Table (From page | Sentence with anchor | Why).

Before answering: check no anchor competes with the source page's own target query.

Role: You are a digital PR strategist who only pitches real stories.

What I have:
[your data, survey results, odd observations from your work, or a defensible contrarian position]

Task: 5 story angles a journalist would open, each anchored to my material.

Constraints: No fake surveys, no invented statistics, no "study reveals" without a study. If my material is too thin, say so and specify the data that would fix it.

Format: For each: the headline a journalist would write, the hook sentence, the outlet type, the asset it uses.

Before answering: mark any angle that needs data collection before it can be pitched honestly.

Role: You are writing a Google Business Profile from verified facts. Here they are:

My business facts:
[services, service area, years operating, real differentiators, themes from genuine reviews]

Task: write the business description within Google's 750-character limit, front-loading what matters because only the opening shows before the "More" link. Then list the services with a one-line description each, and 5 Q&A pairs seeded from questions customers genuinely ask.

Constraints: every claim traces to my facts. No superlatives I did not earn ("best", "#1") and no keyword-stuffed sentences a human would wince at; the description is read by the person deciding whether to call.

Format: the description with its character count, the services list, then the 5 Q&As.

Before answering: list anything in my facts you left out, and why.

Role: You are deciding whether a local landing page deserves to exist, then outlining it. Here is the situation:

Service + location:
[the service + the location, e.g. "emergency plumbing in Footscray"]

My local proof for this exact location:
[real material for THIS location: jobs completed, local reviews, local staff, area-specific knowledge, pricing differences]

Task: first judge whether my local proof can carry a page genuinely different from my other location pages. If yes, outline it: locally specific H2s, where each proof point goes, and the questions residents of this area actually ask. If no, say so and list the proof to gather first.

Constraints: nothing in the outline may be reusable for another suburb by swapping the place name; that is the doorway-page pattern that gets sites penalised. No invented local details.

Format: verdict first (build / do not build yet), then the outline or the proof-gathering list.

Before answering: for each H2, state which proof point makes it specific to this location.