map-my-site
Skill0 starsChanged 4 months agoMITView on GitHub
Turn the keyword plan into the whole intended site as a tree: one intent per URL, a parent for every node, titles and metas generated as a consistent set, permutations gated against doorway-page risk, and a publish rate bounded by what the site has demonstrated it can get indexed.
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
- 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
10 rules. About 0 are common, 2 are distinctive, and 8 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
8
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 57
No keyword plan exists yet, or config.revenue_model is unset.
- Very specific: line 61
Run rainmaker blueprint --build.
- Very specific: line 67
Run rainmaker blueprint --tree to print the tree, the collision list, the authority budget (derived from the site's own measured indexation …
- Distinctive: line 73
No node of tier 0, 1 or 2 below depth 3.
- Distinctive: line 74
No permuted node without all four gates passing.
- Very specific: line 75
No cohort exceeding the authority budget from src/blueprint/budget.ts, which is itself clamped to the floor whenever the site has published …
≈ “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
map-my-site
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 keyword_plan and clusters | what the tree is built from | run what-to-target-next first |
data/snapshots/<latest>/crawl.json | existing pages, matched before planning new ones | run rainmaker audit |
SERP verdicts from can-i-actually-rank | page type follows what actually ranks | unchecked nodes are written but flagged, never briefed |
config.revenue_model | selects the spine and permutation axis | required in rainmaker.config.yml |
Produces
data/blueprint.json via rainmaker blueprint --build, monthly cohorts via rainmaker blueprint --tree.
Refuses when
No keyword plan exists yet, or config.revenue_model is unset. Both are required to select a spine; run what-to-target-next and check rainmaker.config.yml first.
Procedure
- Run
rainmaker blueprint --build. This assembles nodes fromkeyword_planandclusters, matches each againstcrawl.jsonby normalised path (settingstatus: liveon a match), and runs collision detection deterministically in code. Do not re-derive collisions by hand, and never allow two nodes to share a head query. - Select the spine and permutation axis for
config.revenue_modelfromspec/site-blueprint.mdsection 5:sales-ledroots in solutions and comparisons,local-servicesroots in services and areas,ecommercein categories and collections, and so on. - For every candidate permutation (
[service] in [area],[product] for [industry]), check all four gates before it becomes its own URL: measured demand, three or more substance fields that genuinely differ from every sibling, a proof point specific to the permutation, and remaining capacity inside the authority budget. Usesrc/blueprint/permutation.ts checkPermutation, which enforces the substance comparison byte for byte; do not eyeball it. A node failing any gate becomes a section on its parent, never its own URL. - Assign a parent to every node. A category node needs 3 or more children to exist as its own page; fewer, and the children attach directly to the grandparent.
- Enforce the depth ceiling: no tier 0, 1 or 2 node sits deeper than 3 clicks from the root.
- Generate titles (60 chars) and meta descriptions (155 chars) for the whole node set together, so duplicates are caught across the set rather than per page.
- Run
rainmaker blueprint --treeto print the tree, the collision list, the authority budget (derived from the site's own measured indexation rate, never assumed), and the monthly cohorts. - Report how many permutations were refused and why. A blueprint that produces many nodes and refuses none is a defect: it means the gates were not actually applied.
Decision rules
- One intent, one node, one URL, enforced by
detectCollisions, not by judgment. - No node of tier 0, 1 or 2 below depth 3.
- No permuted node without all four gates passing.
- No cohort exceeding the authority budget from
src/blueprint/budget.ts, which is itself clamped to the floor whenever the site has published at volume with a low indexed rate, so past failure never earns a bigger budget.
Output
The tree, then the cohorts, then the refusal counts:
/ home tier 0 live
├── /services/ category tier 1 planned
│ └── /services/lobby-displays/ service tier 1 live
Nodes: <n> planned, <n> live
Permutations refused: <n> (<reason breakdown>)
Collisions: <n>
Authority budget: <n> pages per month (indexed_rate <x>, published_last_90d <n>)
Cohort 1: <node ids>Done when
Collision detection ran and is reported, every permuted node passed all four gates or was demoted to a section, no tier 0-2 node sits below depth 3, and cohorts respect the computed authority budget.
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.

