write-the-page
Skill0 starsChanged 4 months agoMITView on GitHub
Write a draft from a brief, matching the site's real voice samples rather than a description of the voice, covering every standalone claim, and passing the slop check on itself before returning.
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
- 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
The file
We split this skill into the rules it gives an agent
11 rules. About 0 are common, 4 are distinctive, and 7 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.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
Run rainmaker context --check first.
- Very specific: line 28
Only the data/ files listed in this skill's Consumes table.
- Very specific: line 30
If strategy.json.context_hash does not match the current hash of context/business.md, say exactly:
- Very specific: line 36
If context/business.md carries confidence: stub, continue, and stamp every output with: "Built on a stub context.
- Very specific: line 52
No brief exists for the requested slug: "No brief for <slug>.
- Very specific: line 56
Read the voice samples in context/voice.md before writing a sentence.
- Distinctive: line 57
Write to the brief's standalone claims first, then build the piece around them, so the extractable sentences are load-bearing rather than …
- Distinctive: line 58
Every claim that is not common knowledge carries a proof id from the brief or a link.
- Distinctive: line 59
Use the quoted buyer language verbatim at least once in the first 200 words.
- Very specific: line 61
Run the slop check from skills/_shared/voice-rules.md against your own draft before returning it.
- Distinctive: line 65
Never invent a number, a statistic, or a customer detail.
≈ “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
write-the-page
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 |
briefs/<slug>.md | everything the draft must cover | "No brief for <slug>. Run brief-my-writer first." |
context/voice.md | real samples to match | required, see context load |
data/strategy.json | proof ids to verify against | run know-my-buyer |
Produces
drafts/<slug>.md.
Refuses when
No brief exists for the requested slug: "No brief for <slug>. Run brief-my-writer first. Writing without a brief produces content nobody can defend at review."
Procedure
- Read the voice samples in
context/voice.mdbefore writing a sentence. Match their sentence-length distribution and paragraph rhythm, not a description of the voice. - Write to the brief's standalone claims first, then build the piece around them, so the extractable sentences are load-bearing rather than bolted on.
- Every claim that is not common knowledge carries a proof id from the brief or a link. Unsourced claims get removed, not softened into a vaguer unsourced claim.
- Use the quoted buyer language verbatim at least once in the first 200 words.
- Include every internal link the brief named, from the source page the brief specified.
- Run the slop check from
skills/_shared/voice-rules.mdagainst your own draft before returning it. Fix violations, then report what was fixed.
Decision rules
- Never invent a number, a statistic, or a customer detail. If the brief did not supply it and it is not common knowledge, the sentence does not survive.
- The em-dash rule applies to your own output, not just to review comments about it.
- A draft that ignores a standalone claim from the brief is incomplete; go back and include it rather than noting the omission.
Output
The draft itself, in Markdown, plus a short note:
Draft written: <word count> words.
Slop check: <passed / fixed n issues before returning>
Buyer language used: "<quote>" (first 200 words: yes/no)
Brief claims covered: <n> of <n>Done when
The slop check passes, every brief claim is covered or explicitly flagged as cut and why, the buyer-language quote appears early, and every internal link the brief named is present.
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.

