technical-audit-prompt — Claude Code prompt: how to install
technical-audit-prompt is a Claude Code prompt for structured SEO audit deliverables using the FLOW framework. It forces the model to separate confirmed facts from unverified assumptions.
MIT ★ 159 updated 2026-11-09
.claude/commands/technical-audit-prompt.mdWhat technical-audit-prompt does
The prompt sets the assistant to act as a senior SEO strategist working strictly from supplied project data. It explicitly forbids fabricating performance metrics, inventing statistics, or borrowing external private examples.
The output arrives as an executable document split into an executive brief, a priority table, copy and layout findings, required evidence, measurement intervals, and a fact-checking checklist.
The instruction requires long-context reasoning models. On smaller models, the workflow breaks unless inputs are trimmed and requested one section at a time.
What it helps with
- generate a prioritized rewrite brief for a weak landing page
- isolate facts from assumptions in search optimization reports
- set up conversion tracking events and review intervals
- identify trust and extraction gaps across target URLs
Example prompts for the agent
- Run a technical audit on this service URL using the attached search console export
- Apply the FLOW audit prompt to our local landing page and draft the priority table
- Audit this campaign query set and list claims requiring verification
How to install technical-audit-prompt
Manually: put the files in place
.claude/commands/technical-audit-prompt.mdHow to use
Paste the text at the start of a chat or into project instructions
Questions about technical-audit-prompt
How to install technical-audit-prompt in Claude Code?
Save the prompt content directly into .claude/commands/technical-audit-prompt.md in your project folder.
What does technical-audit-prompt do?
It guides an LLM to produce a structured SEO deliverable around search intent and concrete evidence while explicitly labeling every unverified assumption.
What is required to run technical-audit-prompt?
You need a long-context reasoning model alongside input assets: site name, target URLs or queries, analytics evidence, and operational constraints.
Source text
technical-audit-prompt.md · MIT
<!-- Source: github.com/AgriciDaniel/flow | License: CC BY 4.0 | Synced: 2026-04-26 --> --- title: "Technical Audit Prompt" description: "Technical Audit Prompt" updated: 2026-04-25 tags: - prompts - optimize --- # Technical Audit Prompt ## Use This When Use this prompt when you need a structured optimize 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 optimize 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