agentleFS
mardab96mardab96/landing-pages-claude-skills/thank-you-page-opportunity-audit/SKILL.md

thank-you-page-opportunity-audit

Skill2 starsChanged 4 months agoMITView on GitHub

Looks at the page after conversion, where attention is highest and almost nothing is usually asked. Use when a form or purchase flow has just shipped, or when the thank-you page is still the platform default.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 9 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If nobody can say what happens next operationally, that is the first finding.

    line 22
  2. Very specific:

    Not for: reviewing the form that produced the conversion (form-friction-finder), or the offer on the page before it …

    line 24
  3. Distinctive:

    Check whether the page confirms value, sets expectations, routes urgency and offers a qualified next action.

    line 29
  4. Distinctive:

    Only recommend an additional ask when the primary next step is already handled.

    line 39
  5. Distinctive:

    If a no-show or reply rate is quoted by the user, treat it as their claim and say it should be confirmed against the calendar or inbox …

    line 40
  6. Distinctive:

    Do not recommend adding tracking here as the finding.

    line 41
  7. Distinctive:

    Do not add a secondary ask before the confirmation and timing are handled.

    line 66
  8. Distinctive:

    Do not invent the operational process.

    line 67
  9. Distinctive:

    Do not treat a user-quoted rate as measured.

    line 68
  10. Distinctive:

    Do not recommend tracking changes here.

    line 69

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Thank You Page Opportunity Audit

Use this skill when

  • a conversion has just happened and the page or email the user lands on afterwards is available for review.
  • booked calls no-show and nobody has looked at what the page promised about timing.
  • the page after conversion is still whatever the form tool generated by default.

This skill reviews the moment after conversion. The form itself belongs to form-friction-finder.

Required input

  • what the visitor sees immediately after converting: the page, and the confirmation email if there is one.
  • what actually happens next on the business side: who contacts them, from where, within what window.
  • the conversion that just happened, and what the next commitment in the journey is.
  • optional: no-show rate for booked calls, reply rate to the confirmation, whether anyone has ever looked at this page's analytics.
  • If nobody can say what happens next operationally, that is the first finding. A page cannot set an expectation the business has not decided.

Not for: reviewing the form that produced the conversion (form-friction-finder), or the offer on the page before it (offer-clarity-diagnosis).

Analysis workflow

  1. Review the thank-you page, confirmation email and immediate next step after conversion.
  2. Check whether the page confirms value, sets expectations, routes urgency and offers a qualified next action.
  3. Identify missed opportunities: booking, qualification, content, referral, onboarding or tracking.
  4. Compare thank-you behavior with lead quality and sales follow-up needs.
  5. Recommend post-submit improvements without adding friction before the initial conversion.

Decision rules

  • This is the highest-intent moment in the funnel. A page that says only "thanks, we will be in touch" is the finding, and it is a finding about attention wasted rather than a missed upsell.
  • Vague timing is an operational defect, not a copy preference. "We will be in touch" produces no-shows and duplicate enquiries; naming who calls, from what number, and within what window addresses both.
  • Rank by what the next step needs, not by what could be added. One instruction that makes the upcoming call more productive beats three cross-sell modules.
  • Only recommend an additional ask when the primary next step is already handled. A thank-you page that upsells before it confirms is worse than an empty one.
  • If a no-show or reply rate is quoted by the user, treat it as their claim and say it should be confirmed against the calendar or inbox before it anchors a decision.
  • Do not recommend adding tracking here as the finding. That belongs to a tracking review.

Output format

ElementPresentWhat it tells the visitorWhat it should tell themPriority
Confirmation, timing, who contacts them, what to prepare, next useful action, referral or secondary askYes / noQuoted current copy or noneThe specific missing informationHigh / medium / low

End with:

  • What the visitor does not know when they leave: the list
  • Operational gap: anything the business has not decided that the page cannot therefore say
  • Decision: set expectations / add one preparation instruction / add a secondary ask / decide the operational step first
  • User-supplied claims to confirm: any rate quoted rather than measured

Practical example

User: "Thank you page says Thanks, we will be in touch. Nothing else. 190 form submissions a month, and sales says about half of the calls no-show."

Assistant should note: the moment after submitting is the highest-intent moment in the funnel and the page currently uses it to say nothing, which is the finding rather than a missed upsell; "we will be in touch" sets no expectation about when or by whom, and vague timing contributes to no-shows, so the page is part of the problem rather than adjacent to it; nothing on the page moves the person towards being prepared for the call.

Then: naming who calls, from what number, within what window, plus one thing to have ready, is the smallest change that touches the reported no-show rate. What this cannot treat as established is the rate itself: "about half of 190" is a claim from recall, not a measurement, and it should be confirmed against the calendar before it anchors any decision. Whether an additional ask belongs here is also unknown until the confirmation and timing are fixed, so it stays off the recommendation list for now.

Guardrails

  • Do not add a secondary ask before the confirmation and timing are handled.
  • Do not invent the operational process. If it is undecided, say so.
  • Do not treat a user-quoted rate as measured.
  • Do not recommend tracking changes here.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.