agentleFS
vcxcviivcxcvii/rainmaker/skills/stop-losing-visitors/SKILL.md

stop-losing-visitors

Skill0 starsChanged 4 months agoMITView on GitHub

Find where arriving traffic leaks before it converts, using behavioural data the core already pulled, and rank the leaks by how close the page sits to revenue rather than by how dramatic the metric looks.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run rainmaker context --check first.

    line 23
  2. Very specific:

    Only the data/ files listed in this skill's Consumes table.

    line 31
  3. Very specific:

    If strategy.json.context_hash does not match the current hash of context/business.md, say exactly:

    line 33
  4. Very specific:

    If context/business.md carries confidence: stub, continue, and stamp every output with: "Built on a stub context.

    line 39
  5. Distinctive:

    Never assert that a UX metric caused a revenue outcome.

    line 68
  6. Distinctive:

    Every flagged page carries two measured failures, its percentile within this site, and a cause a developer can go and look at.

    line 77

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

stop-losing-visitors

Context load

Run rainmaker context --check first. It prints what exists, what is stale, and exits 1 if anything this skill requires is missing.

Then read, in this order:

  1. context/business.md in full. If absent, stop: "No business context. Run rainmaker audit, then the know-my-buyer skill."
  2. context/voice.md if this skill writes prose. If absent, stop and say so.
  3. context/glossary.md if this skill names products, features or competitors.
  4. data/strategy.json if this skill reads or writes strategy.
  5. Only the data/ files listed in this skill's Consumes table. Never crawl or call an API the core already covers.

If strategy.json.context_hash does not match the current hash of context/business.md, say exactly:

"Business context was edited after the strategy was written. Re-run know-my-buyer, or run rainmaker context --sync to accept the prose as authoritative."

Then stop.

If context/business.md carries confidence: stub, continue, and stamp every output with: "Built on a stub context. Nothing in it came from a buyer. Run know-my-buyer to replace it."

Consumes

FileWhyIf missing
data/snapshots/<latest>/clarity.jsonbehavioural metrics"No Clarity data. Set CLARITY_TOKEN, then rainmaker fetch --source clarity."
data/snapshots/<latest>/ga4.jsonsessions and key eventssay which conclusions are unavailable without it
data/snapshots/<latest>/crawl.jsonforms, CTAs and word count, so a finding names a probable causerun rainmaker audit

Produces

Nothing.

Refuses when

Clarity data is absent, or the page has under 100 sessions in the window. Below that there is no distribution to compare against, and every percentage moves several points on a single visitor.

Procedure

  1. Rank pages by sessions multiplied by tier weight. Take the top 20.
  2. For each, pull engagement rate, rage clicks per 1000 sessions, dead clicks per 1000, scroll depth and exit rate.
  3. Flag a leak when a tier 0 or 1 page sits in the worst quartile on two or more of those five, measured against this site's own distribution and never against an industry benchmark.
  4. Join to crawl.json so the finding names a probable cause: no form, one CTA below the fold, 4,000 words on a page meant to convert.
  5. Report the affected session count beside every leak, so the reader can size it.

Decision rules

  • Minimum 100 sessions. Below that, report "insufficient sample" and nothing else.
  • Never assert that a UX metric caused a revenue outcome. State the tier, the leak, and the traffic affected.
  • A high exit rate on a tier 4 page is not a leak. Some pages are meant to be the end.

Output

Report spine. Each flagged page names two failing metrics, its own site percentile for each, the session count, and the probable cause from the crawl.

Done when

Every flagged page carries two measured failures, its percentile within this site, and a cause a developer can go and look at.

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.