show-up-in-communities
Skill0 starsChanged 4 months agoMITView on GitHub
Find where the buyer's question is already being asked in communities, draft an answer that would stand on its own with the product name removed, and track it honestly given that most community platforms offer no native click-level attribution.
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
- get-mentioned-by-aiSkill
- 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
- 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, 4 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
4
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.
- Distinctive: line 56
Never simulate independent voices: No multiple accounts, no upvoting your own posts from another account.
- Distinctive: line 64
Read the community's posting rules first.
- Distinctive: line 74
Every attribution claim states plainly what could and could not be tracked.
- Distinctive: line 94
Every draft stands without the product name, every disclosure is present, every posted link is tagged and redirect-verified before being …
≈ “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
show-up-in-communities
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/citation-graph.json | which threads already appear in AI answer citations, to rank targets | optional, rank by traffic alone without it |
context/business.md | buyer language and what we will not say | required |
Produces
Draft answers for human review, plus attribution setup notes. Never posts anything itself.
Hard rules: not stylistic, platform-safety
- Read and print the community's rules before drafting anything. Never post promotional content into a community whose rules forbid it.
- Never simulate independent voices. No multiple accounts, no upvoting your own posts from another account. This is the fastest way to get an entire domain banned, and the ban does not respond to an SEO fix.
- Always disclose affiliation. A recommendation of your own product with no disclosure is an advertisement wearing a community member's voice.
- Answer the question that was asked. A comment that only helps if the reader buys is not an answer.
- One link maximum, and only when the link is the answer, not a bolt-on at the end.
Procedure
- Find threads where the category question is being asked. Rank candidates by thread traffic and by whether the thread already appears in
citation-graph.json, since a thread already feeding AI answers is worth more than an equally busy one that is not. - Read the community's posting rules first. Print them before drafting anything.
- Draft an answer that would stand as useful with the product name removed. If it would not, it is not ready.
- Disclose affiliation plainly.
- Tag any posted link with the standard scheme:
?utm_source=<platform>&utm_medium=community&utm_campaign=<campaign>&utm_content=<community>. Verify the parameters survive the platform's outbound redirect chain before trusting any downstream number; some platforms route through intermediaries that strip tags silently. - Where clicks cannot be tracked (most comment-level activity, structurally), correlate mention dates against traffic and signup timing, and label the result as correlation, never as measured conversion.
Decision rules
- A draft is never posted by this skill. It goes to a human for review and manual posting, per invariant: publishing to any community, forum or social platform is never automated.
- A community whose rules forbid promotional content is not worked around with vaguer promotion; it is skipped.
- Every attribution claim states plainly what could and could not be tracked.
Output
## Community targets
<community>: rules: <summary>, posting allowed: <yes/no and why>
Thread: <url>, traffic <estimate>, cited in AI answers: <yes/no>
Draft: <text, product name removable>
Disclosure: <text>
Link: <tagged url or "none, answer stands alone">
## Attribution
Tagged sessions: <n>, redirect survival: <verified / not verified>
Correlation (not measured): <mention dates vs traffic/signup timing>Done when
Every draft stands without the product name, every disclosure is present, every posted link is tagged and redirect-verified before being trusted, and correlation-based claims are labelled as such rather than presented as measured.
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.

