get-mentioned-by-ai
Skill0 starsChanged 4 months agoMITView on GitHub
Check whether AI assistants mention this site when answering the questions its buyers actually ask, decomposed per engine and per market rather than reported as one aggregate, and mine the cited sources into a target list.
- Reads credentials
In this repository26 other files it gives its agents.
- beat-my-competitorsSkill
- brief-my-writerSkill
- can-i-actually-rankSkill
- check-before-i-publishSkill
- explain-this-numberSkill
- find-my-quick-winsSkill
- follow-the-moneySkill
- get-cited-elsewhereSkill
- know-my-buyerSkill
- make-it-sound-humanSkill
- make-me-quotableSkill
- map-my-siteSkill
- pick-my-battlesSkill
- put-it-on-autopilotSkill
- rainmakerSkill
- revive-old-pagesSkill
- say-it-their-waySkill
- show-me-progressSkill
- show-up-in-communitiesSkill
- spread-one-piece-everywhereSkill
- stop-losing-visitorsSkill
- unblock-my-money-pagesSkill
- what-actually-workedSkill
- what-changed-in-searchSkill
- what-to-target-nextSkill
- write-the-pageSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 1 is distinctive, and 7 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.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 24
Run rainmaker context --check first.
- Very specific: line 32
Only the data/ files listed in this skill's Consumes table.
- Very specific: line 34
If strategy.json.context_hash does not match the current hash of context/business.md, say exactly:
- Very specific: line 40
If context/business.md carries confidence: stub, continue, and stamp every output with: "Built on a stub context.
- Very specific: line 58
Run per engine configured via .env (OPENAI_API_KEY, ANTHROPIC_API_KEY, PERPLEXITY_API_KEY) and per market in config.geographies.
- Very specific: line 65
Record
methodology_versionon every scan: Never compare across a version boundary. - Distinctive: line 76
No probe set below 12 prompts.
- Very specific: line 86
Every citation claim carries its probe date, engine, market and the non-determinism sentence.
≈ “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.
Files
get-mentioned-by-ai
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:
context/business.mdin full. If absent, stop: "No business context. Runrainmaker audit, then theknow-my-buyerskill."context/voice.mdif this skill writes prose. If absent, stop and say so.context/glossary.mdif this skill names products, features or competitors.data/strategy.jsonif this skill reads or writes strategy.- 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
| File | Why | If missing |
data/snapshots/<latest>/crawl.json | schema and extractability, offline half | run rainmaker audit |
context/business.md | brand and category terms for probes | required, see context load |
data/strategy.json | commercial head queries and named competitors for probes | optional; without it probes derive from config.icp_hint and the glossary, and the run is stamped derived: config |
Produces
data/snapshots/<ts>/citations.json.
Probe design
12 prompts minimum, in buyer language rather than brand language: 3 from the category phrasing in messaging.category, 3 commercial head queries from clusters, 3 comparison forms against the top 3 named competitors, 3 from the top-impression non-branded GSC queries. With no strategy, take all 12 from icp_hint plus glossary terms.
Run per engine configured via .env (OPENAI_API_KEY, ANTHROPIC_API_KEY, PERPLEXITY_API_KEY) and per market in config.geographies. Any absent key is skipped and named in the confidence section; zero keys skips the whole probe set and this skill still runs its offline half.
Refresh the prompt set whenever say-it-their-way changes buyer_language. Prompt drift silently invalidates a trend line, since a stale prompt set is answering a question buyers stopped asking.
Reading the result
- Never report an aggregate without its decomposition. A score move localises to one engine, one market or one prompt, and the aggregate hides it. Report per engine and per market always.
- Record
methodology_versionon every scan. Never compare across a version boundary; that is the classic false alarm. - Mine the citations, not just the mentions. Which domains and URLs do the engines cite for these prompts? Hand that list to
get-cited-elsewhere. - Distinguish invisible from visible-but-mispositioned. Being cited as the wrong category needs different work from not being cited at all.
- Every citation claim carries: "Assistant answers are non-deterministic. Treat this as a sample of N probes on
<date>, not a ranking." Confidence is capped at 0.5. Never write averifiedledger event from a probe; citation moves appendopenedandregressedonly, andregresseditself requires two consecutive monthly misses at the same methodology version.
Offline half
Schema coverage by tier: which tier 0 and 1 pages lack Product, Offer, FAQPage, Organization, BreadcrumbList. Extractability: tier 1 pages with fewer than 3 standalone claim sentences. llms.txt presence and whether it covers tier 0 and 1 URLs. Crawler access: does robots.txt block GPTBot, ClaudeBot, PerplexityBot, OAI-SearchBot, reported as a business consequence rather than a value judgement.
Decision rules
- No probe set below 12 prompts.
- Confidence on any citation finding never exceeds 0.5.
- A single missed scan is a suspicion, not a regression.
Output
Per engine, per market: visibility rate, top cited sources with citation counts, and one concrete content action per gap. The non-determinism sentence appears once per section, not once per row, so it is not lost in repetition but is never omitted either.
Done when
Every citation claim carries its probe date, engine, market and the non-determinism sentence; the offline half ran regardless of API keys; and citation sources are exported in a form get-cited-elsewhere can consume directly.
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
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.

