say-it-their-way
Skill0 starsChanged 4 months agoMITView on GitHub
Diff the site's messaging against the vocabulary buyers actually use in search and in their own words, then rewrite the one-liner and differentiators using only vocabulary that is actually attested.
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
- 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
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
- Very specific: line 23
Run rainmaker context --check first.
- Very specific: line 31
Only the data/ files listed in this skill's Consumes table.
- Very specific: line 33
If strategy.json.context_hash does not match the current hash of context/business.md, say exactly:
- Very specific: line 39
If context/business.md carries confidence: stub, continue, and stamp every output with: "Built on a stub context.
- Very specific: line 69
Never introduce a claim absent from proof.
- Very specific: line 71
Only this skill and know-my-buyer may write buyer_language.
- Distinctive: line 91
Every proposed phrase carries its source query and impression count, no claim in the rewrite lacks a proof id, and the drift recommendation …
≈ “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
say-it-their-way
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/strategy.json with at least one pain point | the vocabulary to diff against | run know-my-buyer first |
data/snapshots/<latest>/gsc.json | the top 100 non-branded queries | continue, note that drift cannot be measured |
data/snapshots/<latest>/ga4.json | which queries actually convert | optional |
data/citation-graph.json | vocabulary answer engines already use about the category | optional, often ahead of the site's own language |
Produces
messaging (owner), pain_points[].buyer_language and pain_points[].status (shared owner with know-my-buyer and what-actually-worked), and matching prose in context/business.md.
Refuses when
strategy.json has zero pain points. There is nothing to diff against; run know-my-buyer first.
Procedure
- Pull the top 100 non-branded GSC queries by impressions, using
context/glossary.mdbrand tokens to exclude branded ones. Extract the recurring noun phrases. - Where
citation-graph.jsonexists, add the phrasing answer engines use about the category, since it is often ahead of the site's own vocabulary. - Diff that vocabulary against
pain_points[].buyer_languageandmessaging. Report the share of high-impression query language that appears nowhere in the strategy. - Where a phrase appears in search but not in the strategy, propose it as a
buyer_languageaddition, with the query and impression count as evidence. - Where a strategy phrase appears in no query and on no converting page, demote the pain point from
validatedtohypothesis, with adecisionsentry naming why. - Rewrite the one-liner and differentiators using only vocabulary present in
buyer_languageor the top queries. Show the before and after, and name which phrase came from where.
Decision rules
- Never introduce a claim absent from
proof. If the sharpest positioning needs a claim with no source, say so and add it to "Open questions" inbusiness.mdrather than writing it anyway. - 40 percent is the drift threshold from
spec/site-blueprint.mdsection 8 and the core spec's drift-detection rule: if 40 percent or more of converting query language is absent from the strategy, recommend re-runningknow-my-buyer. - Only this skill and
know-my-buyermay writebuyer_language; only this skill andwhat-actually-workedmay writepain_points[].status. Writing anything else inpain_pointsis out of scope for this skill.
Output
## Messaging audit
Vocabulary coverage: <n>% of top-100 query language is attested in strategy.json
Drift: <fired / not fired>, threshold 40%
### Proposed additions
<phrase>: <query>, <impressions> impressions, 28d: add to pain_points.<id>.buyer_language
### Rewritten one-liner
Before: <text>
After: <text>: <which phrase came from where>Done when
Every proposed phrase carries its source query and impression count, no claim in the rewrite lacks a proof id, and the drift recommendation fires or explicitly does not with the measured percentage shown.
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.

