agentleFS
vcxcviivcxcvii/rainmaker/skills/get-cited-elsewhere/SKILL.md

get-cited-elsewhere

Skill0 starsChanged 4 months agoMITView on GitHub

Drill from cited domains to the specific URLs driving citations to the actual quoted answer text, then turn every finding into an action with an honest plausibility by how editable the placement actually is.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 1 is distinctive, and 6 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.

  • 6

    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:

    Check every existing Presence row against context/business.md: category, one-liner, ICP, pricing model, named integrations.

    line 59
  6. Distinctive:

    Never stop at domain aggregates.

    line 63
  7. Very specific:

    Every action names a URL, not just a domain, every plausibility is justified by its editability class, and every existing presence was …

    line 82

≈ “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

get-cited-elsewhere

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>/citations.jsonthe raw citation scans from get-mentioned-by-airun get-mentioned-by-ai first
data/competitors.jsoncompetitor context for cited pagesrun beat-my-competitors for full coverage
context/business.mdthe source of truth to check every existing mention againstrequired

Produces

data/citation-graph.json.

Procedure

  1. Level 1, domains. Pull the domains that co-occur with the brand or category in AI answers, with citation counts and type (review platform, community, media, competitor, directory). This gives the shape, not the action.
  2. Level 2, URLs. Drill into each heavyweight domain for the specific pages driving its citations. Concentration is the finding: one page out-citing every other page on its domain 14 to 1 means that page owns the answer, not the domain.
  3. Level 3, answers. Open the full AI responses behind the key citations: what is quoted, and for what (a comparison table, a pricing figure, a one-line verdict). This dictates what a competing or replacement page must actually contain. Never recommend an action from domain aggregates alone.
  4. Convert every level-3 finding into one Gap with a named action (claim_listing, earn_review, answer_thread, pitch_inclusion, build_better_page, correct_record) and an honest plausibility by editability class: self_serve around 0.9, pitch 0.3 to 0.5, earned around 0.3, closed 0.1 with the only action being build_better_page.
  5. Check every existing Presence row against context/business.md: category, one-liner, ICP, pricing model, named integrations. A mismatch becomes a correct_record gap and outranks new-placement gaps of equal score, since fixing a wrong description you already own is cheaper and faster than earning a new mention.

Decision rules

  • Never stop at domain aggregates. "Review sites matter" is not an action; "this one comparison post drives 14 times the citations of the rest of its domain" is.
  • Plausibility is honest, not optimistic. A hit-list where everything is 0.9 has not been checked; a hit-list where everything is 0.1 is a list of excuses.
  • Will not do: outreach at volume, link exchanges, paid link schemes, guest-post spam. These buy a short-term signal and a long-term liability.

Output

## Citation graph

Domain: <domain> (<type>), <n> citations
  URL: <url>, <n> citations, cited for: <what>
    Action: <type>, plausibility <x>, effort <h>h

Correct-record gaps (existing mentions that misdescribe us):
  <url>: says "<wrong claim>", business.md says "<correct claim>"

Done when

Every action names a URL, not just a domain, every plausibility is justified by its editability class, and every existing presence was checked against business.md.

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.