prompt-rewriting-existing-service-page — Claude Code prompt
prompt-rewriting-existing-service-page is a Claude Code prompt that turns notes on a service page into a rewrite brief: what to fix first and what still needs proof.
MIT ★ 159 updated 2026-11-09
.claude/commands/prompt-rewriting-existing-service-page.mdWhat prompt-rewriting-existing-service-page does
The prompt hands the model a senior SEO strategist role and asks for a single working document on a named site or page. Answers hang on searcher intent, evidence already in hand, gaps that block trust or conversion, edits ranked by priority, measurement events with a review cadence, and claims that need a source before they go live. Invented statistics are off the table, and assumptions sit apart from observations.
Inputs it expects: a business or site name, the target page, profile, query set or campaign, an audience and geography, whatever evidence exists (analytics, search results, calls, reviews), then constraints and required sources.
The file goes to .claude/commands/prompt-rewriting-existing-service-page.md, and Claude Code runs it as /prompt-rewriting-existing-service-page. Long-context reasoning models take the whole brief; on smaller ones the input is narrowed and one output section is requested at a time, which is slower but keeps the answers grounded. In ChatGPT the prompt block is pasted into the chat with the inputs attached.
What it helps with
- rewrite a service page in priority order rather than all at once
- keep assumptions apart from observations in a draft
- list the claims that need a source before publishing
- settle on a conversion event and a review cadence
- reconcile conflicting profile details into one set of facts
Example prompts for the agent
/prompt-rewriting-existing-service-pageRewrite the aircon installation page for Moscow; the inputs are inaudit.md/prompt-rewriting-existing-service-pageBuild the brief fromservice-page.mdand put assumptions in their own section
How to install prompt-rewriting-existing-service-page
Manually: put the files in place
.claude/commands/prompt-rewriting-existing-service-page.mdHow to use
Paste the text at the start of a chat or into project instructions
Questions about prompt-rewriting-existing-service-page
How do I install prompt-rewriting-existing-service-page in Claude Code?
Copy the file to .claude/commands/prompt-rewriting-existing-service-page.md. In Claude Code it is then called as /prompt-rewriting-existing-service-page.
What does prompt-rewriting-existing-service-page do?
It has the model produce a working document on a service page: an executive summary, a priority table, copy and structure changes, a measurement plan and a verification checklist.
What does the prompt need to work?
A business or site name, the target page or query set, an audience and geography, existing evidence such as analytics or reviews, constraints and required sources. It wants long-context reasoning models; smaller ones get narrower input, one section at a time.
Source text
prompt-rewriting-existing-service-page.md · MIT
<!-- Source: github.com/AgriciDaniel/flow | License: CC BY 4.0 | Synced: 2026-04-26 --> --- title: "Prompt : Rewriting Existing Service Page" description: "Prompt : Rewriting Existing Service Page" updated: 2026-04-25 tags: - prompts - local --- # Prompt : Rewriting Existing Service Page ## Use This When Use this prompt when you need a structured local deliverable and want the model to separate observations, assumptions, recommended actions, and claims that need verification. ## AI Compatibility Works with long-context reasoning models. For smaller models, provide narrower inputs and ask for one output section at a time. ## Inputs - Business or website name. - Target page, profile, query set, or campaign. - Audience and geography where relevant. - Existing evidence: analytics, search results, calls, reviews, profile facts, or source notes. - Constraints, exclusions, and required sources. ## Prompt ```text Act as a senior SEO strategist using the FLOW model. Task: create a local deliverable for: [BUSINESS OR ASSET]. Use only the supplied inputs and clearly label any assumption. Do not invent statistics. Do not reuse private examples. Build the answer around: 1. Searcher or buyer intent. 2. Evidence available now. 3. Gaps that block trust, extraction, or conversion. 4. Recommended changes in priority order. 5. Measurement events and review cadence. 6. Claims that require source verification before publication. Return a concise working document the team can execute. ``` ## Output - Executive summary. - Priority table. - Recommended copy, structure, or audit findings. - Evidence needed. - Measurement plan. - Verification checklist. ## Example Input: a local service page with weak proof and inconsistent profile details. Expected output: a prioritized rewrite brief, facts to reconcile, internal links to add, and the conversion event to measure. ## See Also - [Prompt Library](../README.md) - [FLOW Framework](../../flow-framework.md) - [Bibliography](../../bibliography.md) ## Source Note Derived from the Local SEO Knowledge Base structure and rewritten for public use with the repository evidence standard.
© zhtyyx · MIT · zhtyyx/codex-seo