agentleFS
vcxcviivcxcvii/rainmaker/skills/make-me-quotable/SKILL.md

make-me-quotable

Skill0 starsChanged 4 months agoMITView on GitHub

Generate llms.txt and JSON-LD schema from real, sourced facts only, output as a diff against what already exists, and flag schema types competitors use in cited pages that this site is missing.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 2 are distinctive, and 5 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.

  • 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 22
  2. Very specific:

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

    line 30
  3. Very specific:

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

    line 32
  4. Very specific:

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

    line 38
  5. Very specific:

    Add extractability fixes surfaced by get-mentioned-by-ai: standalone claim sentences, a direct answer within the first 100 words of any …

    line 58
  6. Distinctive:

    Every generated field traces to a real value.

    line 63
  7. Distinctive:

    Every generated field traces to a real value, the output is a diff, and any competitor schema gap names the specific competitor page it …

    line 83

≈ “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

make-me-quotable

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>/crawl.jsoncurrent schema coverage per pagerun rainmaker audit
context/business.mdreal facts for llms.txt descriptions, never inventedrequired
data/competitors.jsonschema types competitors use on cited pagesrun beat-my-competitors for full coverage
data/citation-graph.jsonwhich competitor pages are actually citedoptional, sharpens the gap

Produces

llms.txt, JSON-LD blocks, both as diffs against what exists.

Procedure

  1. Generate llms.txt listing tier 0 and tier 1 URLs, with one-line descriptions taken from context/business.md. Never invent a description; where business.md has nothing to say about a page, list the URL with the shortest true statement available (its title) rather than a fabricated summary.
  2. Generate JSON-LD per page type, filling only fields with a real source in the crawl or the context. Never fabricate ratings, prices, or review counts; a missing field is omitted, not guessed.
  3. Output as a diff against what already exists on the page, so the user sees exactly what changes rather than a wholesale replacement they must diff themselves.
  4. Add extractability fixes surfaced by get-mentioned-by-ai: standalone claim sentences, a direct answer within the first 100 words of any question-shaped page, and tables for comparison content, since answer engines quote tables disproportionately.
  5. Flag any schema type present across competitors' cited pages (from citation-graph.json where available, otherwise competitors.json) and absent from this site's own tier 0 and 1 pages.

Decision rules

  • Every generated field traces to a real value. A field with no source is omitted, never fabricated.
  • Output is always a diff, never a wholesale file replacement, so a reviewer can see precisely what changed.
  • llms.txt covers tier 0 and 1 only; do not pad it with every URL on the site.

Output

## llms.txt diff
+ <url>: <one-line description, sourced from business.md>

## Schema diff, <url>
+ "@type": "<Type>"
+ "<field>": "<value>"   (source: <file>, real value)

## Competitor schema gap
<type> present on <competitor cited page>, absent on our tier <n> pages

Done when

Every generated field traces to a real value, the output is a diff, and any competitor schema gap names the specific competitor page it came from.

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.