agentleFS
vcxcviivcxcvii/rainmaker/skills/unblock-my-money-pages/SKILL.md

unblock-my-money-pages

Skill0 starsChanged 4 months agoMITView on GitHub

Find what is technically stopping the pages closest to revenue from working, ordered by distance to money rather than by severity. Reads the diagnosis the core already wrote; it never re-crawls.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 2 are distinctive, and 7 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.

  • 7

    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 24
  2. Very specific:

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

    line 32
  3. Very specific:

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

    line 34
  4. Very specific:

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

    line 40
  5. Very specific:

    No diagnosis exists: "No diagnosis yet.

    line 56
  6. Very specific:

    Read diagnosis.json. Group findings by tier, never by check type.

    line 61
  7. Very specific:

    Never report a finding without its tier_source.

    line 72
  8. Distinctive:

    Never recommend a fix whose effort exceeds the finding's own listed hours without saying why the table is wrong.

    line 73
  9. Distinctive:

    Every line names a URL, a measured value, an effort figure and a tier source.

    line 90

≈ “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

unblock-my-money-pages

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.jsonthe findings, already scored"No diagnosis yet. Run rainmaker audit."
data/snapshots/<latest>/crawl.jsonpage-level evidencesame
data/state.jsonwhat is already known and what was shippedrun rainmaker ledger --rebuild

Produces

Nothing. The diagnosis is written by src/, and a skill that re-derives a score is a defect.

Refuses when

  • No diagnosis exists: "No diagnosis yet. Run rainmaker audit. Reading a site I have not measured produces a checklist, not a finding."
  • The latest diagnosis predates the latest crawl: say so, and run rainmaker audit --refresh.

Procedure

  1. Read diagnosis.json. Group findings by tier, never by check type. Tier 0 leads, always.
  2. Within each tier, keep the order the core produced. It is already score descending, id ascending, and reordering it makes two reports of the same data disagree.
  3. Report reachability first: noindex, canonical to an error, canonical chains, 4xx and 5xx. A page in that state cannot earn a score at all, which is the one case where ordering overrides the number.
  4. Then structure: orphans, click depth over 3 for tier 0 and 1, duplication.
  5. Then metadata and content: titles, meta descriptions, H1s, thin pages.
  6. Report suspicions in their own section, each with what would confirm it. Never mix them into the ranked list.
  7. Close with the confidence section: which capabilities were live, and what their absence weakens.

Decision rules

  • A tier 0 page that is unreachable outranks any tier 1 item regardless of score.
  • Never report a finding without its tier_source. A tier from url_pattern is a guess and a reader who cannot see that will read it as measured.
  • Never recommend a fix whose effort exceeds the finding's own listed hours without saying why the table is wrong.
  • Say what is not broken. A reader who only ever sees problems cannot calibrate.

Output

## 1. What changed
## 2. Why it matters
## 3. What to do
  <path>  tier <n>  <check>  <effort>h  score <x>
  <one sentence, the measured value, the file it came from>
## 4. What we are watching
## 5. Confidence

Done when

Every line names a URL, a measured value, an effort figure and a tier source; suspicions are separated; and the confidence section lists the capabilities that were missing.

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.