spread-one-piece-everywhere
Skill0 starsChanged 4 months agoMITView on GitHub
Repurpose a proven page into two derivative formats, bounded so it never becomes a content treadmill: only pages that are live, indexed, past their verification window, and inside a cluster above 40 percent completeness.
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
- 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 22
Run rainmaker context --check first.
- Very specific: line 30
Only the data/ files listed in this skill's Consumes table.
- Very specific: line 32
If strategy.json.context_hash does not match the current hash of context/business.md, say exactly:
- Very specific: line 38
If context/business.md carries confidence: stub, continue, and stamp every output with: "Built on a stub context.
- Distinctive: line 62
Every derivative links back to the canonical blueprint node.
- Distinctive: line 69
No derivative of a page still inside its verification window.
- Distinctive: line 70
No derivative of a page in a cluster below 40 percent completeness.
- Distinctive: line 88
All three gates are confirmed rather than assumed, exactly two formats were produced, each links back to the canonical page, and any video …
≈ “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
spread-one-piece-everywhere
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/ledger.jsonl | whether the source page is past its verification window | run rainmaker ledger --rebuild |
data/blueprint.json | the source page's cluster and its completeness | run map-my-site |
data/snapshots/<latest>/gsc.json | confirms the page is indexed and getting impressions | run rainmaker audit |
Produces
Derivative drafts (video script, social breakdown, newsletter section, etc.), plus an entry in data/citation-graph.json under our_presence for each.
Refuses when
- The source page is not yet live and indexed, per
gsc.json. - The source page is still inside its own verification window from
src/ledger/types.ts VERIFICATION_WINDOWS. Repurposing an unproven page multiplies a guess rather than amplifying a result. - The page's cluster is below 40 percent completeness. Repurposing effort belongs where authority is already being built, not where the cluster itself is still a spot hit.
Procedure
- Confirm all three gates above pass; if not, name which one failed and the date it will clear.
- Pick exactly two derivative formats, not more, from: a community answer, a short video with transcript, a newsletter section, a social breakdown, a slide or graphic asset, a podcast talking point.
- Every derivative links back to the canonical blueprint node.
- Video and audio derivatives require a transcript on the canonical page; an untranscribed video is invisible to both search and answer engines.
- Record each derivative in
data/citation-graph.jsonunderour_presence.
Decision rules
- Two formats per source page, never six. A repurposing plan that touches every format every time is a treadmill, not a strategy.
- No derivative of a page still inside its verification window.
- No derivative of a page in a cluster below 40 percent completeness.
Output
## Repurposing: <source url>
Gates: live+indexed <yes/no>, past verification window <yes, cleared <date> / no, clears <date>>, cluster completeness <n>% (<pass/fail>)
Chosen formats: <format 1>, <format 2>
<format 1>: <draft or outline>, links to <canonical url>
<format 2>: <draft or outline>, links to <canonical url>
Transcript required: <yes, attached / no>Done when
All three gates are confirmed rather than assumed, exactly two formats were produced, each links back to the canonical page, and any video or audio derivative has a transcript on that page.
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.

