agentleFS
vcxcviivcxcvii/rainmaker/skills/follow-the-money/SKILL.md

follow-the-money

Skill0 starsChanged 4 months agoMITView on GitHub

Show where effort has actually gone versus where money is actually made, by comparing the share of pages, sessions and key events per tier, and assign every cluster the tier its content should occupy.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 1 is distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    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. Very specific:

    Never refuses outright; degrades.

    line 55
  6. Distinctive:

    Never assert the imbalance is a mistake.

    line 68

≈ “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

follow-the-money

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>/diagnosis.jsontier distribution across all pagesrun rainmaker audit
data/snapshots/<latest>/ga4.jsonsessions and key events per tiercontinue at confidence 0.5, ranking on sessions only
data/state.jsonwhich findings are open, so this is grounded in current staterun rainmaker audit

Produces

clusters[].target_tier (shared owner with pick-my-battles), the revenue narrative section of context/business.md.

Refuses when

Never refuses outright; degrades. With key_events_configured empty, state so in the confidence section, skip every step depending on key events, and rank on sessions with confidence 0.5.

Procedure

  1. Build the tier distribution table from state.json: how many pages sit in each tier.
  2. Join sessions and key events per tier from ga4.json.
  3. Compute, per tier: share of pages, share of sessions, share of key events. The gap between those three shares is the entire point of this skill.
  4. State the imbalance in one sentence with numbers: for example, "Tier 3 is 78 percent of pages and 6 percent of key events."
  5. Map every URL in config.primary_conversion to its measured key events. A declared conversion page with zero key events over the window is the single highest-value finding available here, and it is reported first, above any tier-distribution commentary.
  6. Assign each cluster in strategy.json.clusters a target_tier: the tier its content should occupy, which is often not the tier its existing pages currently sit in.

Decision rules

  • Never assert the imbalance is a mistake. State the numbers and let the reader draw the conclusion; a 78/6 split might be a deliberate content-marketing strategy with a long payback, and this skill's job is to make the tradeoff visible, not to declare it wrong.
  • A zero-key-event declared conversion page is only reported as a finding when key_events_configured is non-empty and the page carries no outbound link to a host in config.offsite_conversion_hosts. Otherwise it is unmeasured, not broken, per spec/false-positives.md section 3.5.
  • target_tier on a cluster may also be set by pick-my-battles; where the two disagree, the more recent write wins and a decisions entry must explain why.

Output

## Revenue map

Tier 0: <n>% of pages, <n>% of sessions, <n>% of key events
Tier 1: ...
...

Declared conversion pages with zero measured key events:
  <url>: 0 key events over <window>d (ga4.json, confidence <c>)

Cluster tier reassignments:
  <cluster id>: currently tier <n>, should be tier <n>, because <reason>

Done when

The output states, in one sentence with numbers, where effort has gone and where money is made, every cluster has a target_tier, and the confidence section states plainly whether key events were configured.

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.