Website Audit Report
Website Audit Report
Turn crawl notes, UX issues and analytics into a prioritised audit a developer can work from.
The Prompt
website-audit-report.md
Write a website audit report. Site: {{site}} Goals of the site: {{goals}} Findings / notes (tech, UX, content, analytics): {{findings}} Audience for the report: {{audience}} Report: 1. Severity-ordered findings (high / med / low) 2. Each finding: evidence, user/business impact, recommended fix, owner type (dev / content / design) 3. Quick wins (under a day) 4. 30-day plan Do not pad with generic "add more content" advice. If my notes are only technical, do not fake a brand audit.
Negative prompt
Included when you copy the prompt
Do not invent UX, brand, or content findings that are not in {{findings}}. Do not pad with generic "add more content" or "improve SEO" advice. Do not fake a brand/visual audit when notes are only technical. Do not leave findings without severity, evidence, impact, fix, and owner type. Do not bury quick wins inside a long narrative with no 30-day plan. Do not recommend tools or rebuilds unrelated to stated {{goals}}.
Fill in your details below - this prompt updates as you type, then copy it.
Fill in your details
0 of 4 filled. Preview updates as you type - then copy the finished prompt (negative prompt included when present).
website-audit-report.md
Prompt preview
Write a website audit report. Site: {{site}} Goals of the site: {{goals}} Findings / notes (tech, UX, content, analytics): {{findings}} Audience for the report: {{audience}} Report: 1. Severity-ordered findings (high / med / low) 2. Each finding: evidence, user/business impact, recommended fix, owner type (dev / content / design) 3. Quick wins (under a day) 4. 30-day plan Do not pad with generic "add more content" advice. If my notes are only technical, do not fake a brand audit.
Examples
Example input
Site: www.fieldkit.tools Goals of the site: Get field-service SMBs to start a 14-day trial; secondary: book a demo for teams >20. Findings / notes (tech, UX, content, analytics): - Lighthouse mobile perf 46; LCP 5.8s on / (hero WebP missing; 2.4MB PNG) - CTA "Start trial" below fold on mobile; heatmap (notes): 62% scroll depth never reach CTA - Pricing page: 3 plans but no annual toggle; sales says >20 seat deals stall without "Talk to us" - 11 broken internal links from old blog to /features/scheduling (now /scheduling) - Trial form: 9 fields including company phone; completion ~22% (analytics note) - Missing meta descriptions on 28 product URLs (crawl) - No evidence on brand voice or visual identity in this pass Audience for the report: Founder + lead engineer
What you should get
1 - 2. Findings (severity order) HIGH - Mobile LCP / hero weight Evidence: Lighthouse mobile 46; LCP 5.8s; hero 2.4MB PNG, WebP missing. Impact: Slow first paint hurts trial starts on mobile SMB traffic. Fix: Compress/replace hero with WebP/AVIF, preload, defer non-critical JS. Owner: dev HIGH - Trial CTA below fold on mobile Evidence: Heatmap note - 62% never reach CTA; CTA below fold. Impact: Intent exits before primary conversion. Fix: Sticky mobile CTA or move primary button into first screen; keep secondary "Book demo". Owner: design + dev HIGH - Trial form friction Evidence: 9 fields incl. company phone; ~22% completion. Impact: Starts abandoned before account creation. Fix: Cut to email + password (+ company size optional); move phone to post-trial. Owner: design + dev MED - Pricing for >20 seats Evidence: No "Talk to us"; sales reports stalls. Impact: Secondary demo goal under-converts. Fix: Add enterprise CTA + short form on Pricing. Owner: content + design MED - Broken internal links (11) to /features/scheduling Evidence: Crawl/blog links to old path; now /scheduling. Impact: Dead ends from content that could feed trials. Fix: Redirect + update links. Owner: dev / content LOW - Missing meta descriptions (28 URLs) Evidence: Crawl. Impact: Weaker SERP snippets; secondary to on-page conversion. Fix: Templates for product URLs. Owner: content 3. Quick wins (<1 day) - 301 /features/scheduling → /scheduling and patch top blog links - Swap hero to compressed WebP - Add sticky mobile "Start trial" button 4. 30-day plan Week 1: Perf hero + sticky CTA; measure mobile trial start rate Week 2: Shorten trial form; A/B or ship-and-watch completion Week 3: Pricing enterprise CTA; fix remaining broken links Week 4: Meta description batch; review trial and demo conversion vs baseline (No brand/visual audit - not in findings.)
When to use this prompt
Use it when
- You need help with consultants.
- You need help with agencies.
- You need help with pms.
Skip it when
- You only need a one-line ask with no constraints, format, or context.
- You cannot supply the fill-in details the template asks for.
- A different category or tool-specific workflow fits the job better.
How to get a good result
Done when
1 - 2. Findings (severity order) HIGH - Mobile LCP / hero weight Evidence: Lighthouse mobile 46; LCP 5.8s; hero 2.4MB PNG, WebP missing. Impact: Slow first paint hurts trial starts on mobile SMB traffic. Fix: Compress/replace hero with WebP/AVIF, preload, defer non-critical JS. Owner: dev HIGH - Trial CTA below fold on mobile Evidence: Heatmap note - 62% never reach CTA; CTA below fold. Impact: Intent exits before primary conversion. Fix: Sticky mobile CTA or move primary button into first screen; keep secondary "Book demo". Owner: design + dev HIGH - Trial form friction Evidence: 9 fields incl. company phone; ~22% completion. Impact: Starts abandoned before account creation. Fix: Cut to email + password (+ company size optional); move phone to post-trial. Owner: design + dev MED - Pricing for >20 seats Evidence: No "Talk to us"; sales reports stalls. Impact: Secondary demo goal under-converts. Fix: Add enterprise CTA + short form on Pricing. Owner: content + design MED - Broken internal links (11) to /features/scheduling Evidence: Crawl/blog links to old path; now /scheduling. Impact: Dead ends from content that could feed trials. Fix: Redirect + update links. Owner: dev / content LOW - Missing meta descriptions (28 URLs) Evidence: Crawl. Impact: Weaker SERP snippets; secondary to on-page conversion. Fix: Templates for product URLs. Owner: content 3. Quick wins (<1 day) - 301 /features/scheduling → /scheduling and patch top blog links - Swap hero to compressed WebP - Add sticky mobile "Start trial" button 4. 30-day plan Week 1: Perf hero + sticky CTA; measure mobile trial start rate Week 2: Shorten trial form; A/B or ship-and-watch completion Week 3: Pricing enterprise CTA; fix remaining broken links Week 4: Meta description batch; review trial and demo conversion vs baseline (No brand/visual audit - not in findings.)
Common mistakes
- Leaving site, goals, findings vague - the model then invents placeholders.
- Asking ChatGPT or Claude for a shorter answer after a long structured prompt - that throws away the format rules.
- Stopping when the first draft appears instead of checking it against the success criteria below.
FAQ
- What do I fill in before I copy this prompt?
- Replace these placeholders with your details: site, goals, findings, audience. Required fields are marked on the page. The prompt text updates as you type.
- Which AI tools is this prompt written for?
- It works best with ChatGPT, Claude. Copy the filled prompt and paste it into the tool you already use.
- What should a good result look like?
- 1 - 2. Findings (severity order) HIGH - Mobile LCP / hero weight Evidence: Lighthouse mobile 46; LCP 5.8s; hero 2.4MB PNG, WebP missing. Impact: Slow first paint hurts trial starts on mobile SMB traffic. Fix: Compress/replace hero with WebP/AVIF, preload, defer non-critical JS. Owner: dev HIGH - Trial CTA below fold on mobile Evidence: Heatmap note - 62% never reach CTA; CTA below fold. Impact: Intent exits before primary conversion. Fix: Sticky mobile CTA or move primary button into first …
- What are common mistakes with this prompt?
- Leaving site, goals, findings vague - the model then invents placeholders. Asking ChatGPT or Claude for a shorter answer after a long structured prompt - that throws away the format rules. Stopping when the first draft appears instead of checking it against the success criteria below.
Best for
- Consultants
- Agencies
- PMs
Related Prompts
More prompts like this — same topic and style.
