Help me start the right SEO Specialists workflow.
Task to use: Cluster Keyword Research: check intent clusters and source data caveats.
Paste current work: Need clusters, intent labels, suggested page type, cannibalization notes, and priority. Do not make up volume or rankings. keyword cluster table with page intent needs the source note, output shape, and review owner in the same pass. The answer should protect the real constraint before polish. a keyword cluster plan should use the note as its source. Before seo specialists run this, separate facts, preferences, and limits so the finished answer does not hide assumptions..
Audience and constraints: SEO operators using ChatGPT to organize research, briefs, metadata, and refresh work..
Who checks it: Send the answer to the owner who can test a structured analysis table with claims, evidence, gaps, and recommended next step, supplied facts, and open assumptions against keyword cluster plan quality, intent clusters and source data caveats, and search-result fit..
Before writing, ask for anything missing that would change the cluster keyword research: check intent clusters and source data caveats output.
Return: The reusable version should keep the fields, rejection rules, and review lens while removing one-time details.
Stop if: Hold the answer if it blurs what is known, what is assumed, and what still needs evidence.
After the first answer
Save what came back, what needs fixing, and the next prompt change before moving to another task.
0No role notes yet
Run the prompt once, check the answer, then save the problem and next try here.
Nothing saved yet
Where ChatGPT helps this role
Turn rough notes into a reviewable asset for a search user, editor, or SEO lead.
Convert a recurring seo specialists workflow into a reusable prompt sequence.
Ask ChatGPT for clarifying questions before committing to tone, format, or evidence.
Create a quick version for routine work and a deeper version for high-stakes work.
Review an existing answer against privacy, accuracy, and role-specific constraints.
Rewrite output for a different audience without changing the underlying facts.
Build a checklist that makes the human review faster and less subjective.
Main Risks
Do not fabricate search volume, rankings, or search result facts; import real data before analysis.
A broad prompt can hide missing source material, so seo specialists should name the exact evidence before asking for output.
Over-polished wording can make weak assumptions look finished; every page links the prompt to a review step.
Copying the same prompt across tasks weakens results because seo specialists need different inputs for planning, review, outreach, and explanation work.
Recommended Workflow
Pick the task page that matches the work to finish, not just the closest job title.
Prepare the source notes, audience, constraints, and forbidden assumptions before copying a prompt.
Run the prompt once for structure, then run a review prompt against facts, tone, and missing context.
Save the final prompt with the human review checklist so the workflow can be reused without becoming automatic.
Choose the first task by situation
Start with Cluster keyword research when the user has source notes but does not yet know the right output structure, then move to Build content briefs or Write title tags only after the audience and review owner are clear.
Choose by situation
Choose Cluster keyword research when the main problem is shaping raw context into something a search user, editor, or SEO lead can inspect.
Choose Build content briefs when the user already has a first version and needs the next artifact in the same seo specialists loop.
Choose Write title tags when the risk is quality control, review consistency, or a clearer handoff to another person.
Open the role guide when the user cannot name the task yet and needs to decide whether to create, revise, review, or sanitize context first.
Avoid starting with
Do not start from a broad role prompt when the user already knows the concrete task.
Do not start from a writing prompt when the missing piece is source material or named human check.
Do not reuse a seo specialists prompt across unrelated tasks without changing inputs, constraints, and review checks.
SEO Specialists pages are organized by the choice a person is trying to make, not by a generic prompt collection. The role page should help the user pick the first useful task, then the task page should carry the details: source material, variable fill, example, stronger prompt, and human review boundary.
Pick the workflow by the work in front of you
Cluster keyword research
Use when the next useful output is a keyword cluster plan and the answer needs a structured analysis table with claims, evidence, gaps, and recommended next step.
Cluster keyword research needs seed keywords, search performance data, page list, intent notes, and business priority; the check focuses on keyword cluster plan quality, intent clusters and source data caveats, and search-result fit, not a generic writing pass.
Build content briefs
Use when the next useful output is a content brief and the answer needs a content brief with named sections, action bullets, and a final reviewer pass.
Build content briefs needs main search phrase, search result notes, audience, angle, outline, and internal links; the check focuses on content brief quality, search result angle and outline logic, and search-result fit, not a generic writing pass.
Write title tags
Use when the next useful output is title tag options and the answer needs copy options grouped by angle, audience, supporting detail, and revision note.
Write title tags needs page topic, primary keyword, search intent, brand rule, and character target; the check focuses on title tag options quality, primary query placement and intent match, and search-result fit, not a generic writing pass.
Write meta descriptions
Use when the next useful output is meta description options and the answer needs copy options grouped by angle, audience, supporting detail, and revision note.
Write meta descriptions needs page value, main search phrase, call to action, intent, and length constraint; the check focuses on meta description options quality, searcher value and length control, and search-result fit, not a generic writing pass.
Plan internal links
Use when the next useful output is an internal linking plan and the answer needs an internal linking plan organized by context, output, caveats, and the next human action.
Plan internal links needs site sections, destination pages, anchor ideas, page priority, and crawl constraints; the check focuses on internal linking plan quality, target URL priority and anchor context, and search-result fit, not a generic writing pass.
Refresh existing content
Use when the next useful output is a content refresh brief and the answer needs a content refresh brief with copy-ready parts, needs-checking parts, and reuse fields.
Refresh existing content needs current page copy, performance data, search result changes, stale facts, and conversion goal; the check focuses on content refresh brief quality, stale sections and ranking loss, and search-result fit, not a generic writing pass.
Analyze search results intent
Use when the next useful output is a search result intent analysis and the answer needs a structured analysis table with claims, evidence, gaps, and recommended next step.
Analyze search results intent needs top result pages, result types, query modifiers, user intent clues, and content gaps; the check focuses on search result intent analysis quality, result type mix and intent split, and search-result fit, not a generic writing pass.
Outline schema markup
Use when the next useful output is a schema markup plan and the answer needs a schema markup plan organized by context, output, caveats, and the next human action.
Outline schema markup needs page type, visible content, entity details, required properties, and validation target; the check focuses on schema markup plan quality, visible content match and entity properties, and search-result fit, not a generic writing pass.
The keyword cluster plan prompt set keeps a keyword cluster plan, intent clusters, source data caveats, page mapping, and priority, and the final check tied to the same source note. It is built to reduce polished but unsupported answers.
Turn seed keywords, search performance data, page list, intent notes, and business priority into a keyword cluster plan for a search user, editor, or SEO lead.
Bring first
Need clusters, intent labels, suggested page type, cannibalization notes, and priority. Do not make up volume or rankings. keyword cluster table with page intent needs the source note, output shape, and review owner in the same pass. The answer should protect the real constraint before polish. a keyword cluster plan should use the note as its source. Before seo specialists run this, separate facts, preferences, and limits so the finished answer does not hide assumptions.
Reject if
Hold the answer if it blurs what is known, what is assumed, and what still needs evidence.
Move from a rough content brief request to a content brief with named sections, action bullets, runnable prompts and revision rules. The page shows when to reject the answer and what to save for reuse.
Turn main search phrase, search result notes, audience, angle, outline, and internal links into a content brief for a search user, editor, or SEO lead.
Bring first
Need H2 outline, search intent, must-answer questions, internal links, metadata angle, and what not to claim without local pricing data. The first human check for content brief work has to compare the answer with the supplied note. A useful version should keep the task boundary visible. Start the content brief from the rough request before shaping a content brief. A usable starting note for content brief work includes what is known, what is uncertain, and what the reviewer must verify.
Reject if
Ask for a correction if it ignores the original notes and answers from general knowledge instead.
Use this when title tag options has real source material but still needs review. The page turns page topic, primary keyword, search intent, brand rule, and character into title tag options and shows what to keep, question, revise, or discard.
Turn page topic, primary keyword, search intent, brand rule, and character target into title tag options for a search user, editor, or SEO lead.
Bring first
Need 10 options for water heater repair page, primary query near front, under 60 characters if possible, no fake 24/7 claim. In title tag options work, the rough note has to lead because role-level advice would flatten the situation. A reviewer needs those notes kept separate from assumptions. Carry the source note into title tag options. For title tag options work, paste the source as bullets, constraints, and audience notes so the model has enough shape for copy options grouped by angle, audience, supporting detail, and revision note.
Reject if
Restart the prompt if it adds citations, policies, credentials, or outcomes outside the source notes.
This meta description options workflow is for seo specialists who already have page value, main search phrase, call to action, intent and need copy options grouped by angle, audience, support point, and revision. It keeps the source, audience, review step, and handoff in one place.
Turn page value, main search phrase, call to action, intent, and length constraint into meta description options for a search user, editor, or SEO lead.
Bring first
Need options around 150 characters, include who the page helps, avoid best/guaranteed claims, and mention comparison criteria. description variants with value and limit checks would be weak without the source details, so the evidence has to stay attached. The prompt should keep the approval point close to the output. SEO Specialists should use the note as the base for meta description options. Before seo specialists run this, separate facts, preferences, and limits so the finished answer does not hide assumptions.
Reject if
Do not use the answer if it hides unsupported claims about real search data, visible page content, and query intent or treats uncertainty as fact.
Start the internal linking plan run with the working case, then copy prompts that preserve target URL priority, anchor context, crawl depth, and topical. The review pass checks real search data, visible page content, and query intent before anything gets reused.
Turn site sections, destination pages, anchor ideas, page priority, and crawl constraints into an internal linking plan for a search user, editor, or SEO lead.
Bring first
Use page list with URLs, target pages, current anchors, and intent notes. Need link opportunities, anchor suggestions, and cannibalization warnings. In internal linking plan work, the rough note has to lead because role-level advice would flatten the situation. The working copy should expose what is known and unknown. Carry the source note into an internal linking plan. For internal linking plan work, paste the source as bullets, constraints, and audience notes so the model has enough shape for an internal linking plan organized by context, output, caveats, and the next human action.
Reject if
Restart the prompt if it adds citations, policies, credentials, or outcomes outside the source notes.
Use this content refresh brief page when the job is a content refresh brief, not broad advice. It gives source prep, examples, prompts, and a short review path for content refresh brief quality, stale sections and ranking loss.
Turn current page copy, performance data, search result changes, stale facts, and conversion goal into a content refresh brief for a search user, editor, or SEO lead.
Bring first
Need refresh brief from current page, GSC queries, competitor notes, outdated claims, internal links, and what not to change. refresh brief with stale-section notes needs the source note, output shape, and review owner in the same pass. A practical answer should keep the handoff choice visible. a content refresh brief should use the note as its source. Before seo specialists run this, separate facts, preferences, and limits so the finished answer does not hide assumptions.
Reject if
Hold the answer if it blurs what is known, what is assumed, and what still needs evidence.
SEO Specialists can move from top result pages, result types, query modifiers, user intent clues to a search result intent analysis without treating the first answer as finished. The workflow adds a messy-note example, answer checks, and a follow-up prompt for search result intent analysis quality, result type mix and intent.
Turn top result pages, result types, query modifiers, user intent clues, and content gaps into a search result intent analysis for a search user, editor, or SEO lead.
Bring first
Need result type summary, recurring sections, PAA themes, missing support, local intent clues, and content risks. No volume or rank claims. search results pattern table with page-type gaps would be weak without the source details, so the evidence has to stay attached. A usable first pass has to preserve those constraints. SEO Specialists should use the note as the base for a search result intent analysis. Before seo specialists run this, separate facts, preferences, and limits so the finished answer does not hide assumptions.
Reject if
Do not use the answer if it hides unsupported claims about real search data, visible page content, and query intent or treats uncertainty as fact.
Use this workflow when the schema markup plan job starts with page type, visible content, entity details, required properties, and validation and needs a clear output shape. The result can be checked before it reaches a search user, editor, or SEO lead.
Turn page type, visible content, entity details, required properties, and validation target into a schema markup plan for a search user, editor, or SEO lead.
Bring first
Need schema recommendation, required fields, visible-content match check, JSON-LD example, and validation checklist. Do not invent reviews. In schema markup plan work, the rough note has to lead because role-level advice would flatten the situation. The answer should show which details still need checking. Carry the source note into a schema markup plan. For schema markup plan work, paste the source as bullets, constraints, and audience notes so the model has enough shape for a schema markup plan organized by context, output, caveats, and the next human action.
Reject if
Restart the prompt if it adds citations, policies, credentials, or outcomes outside the source notes.