beat-my-competitors
Skill0 starsChanged 4 months agoMITView on GitHub
Tear down named competitors on the same tiering rules used for this site, so the comparison is like for like, then produce a joint content-gap table ranked by the tier weight of what is missing.
In this repository26 other files it gives its agents.
- 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
- write-the-pageSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 2 are distinctive, and 5 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.
5
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.
- Distinctive: line 55
No competitors are named anywhere.
- Distinctive: line 72
Never report a third-party domain authority score.
- Very specific: line 74
Every competitor claim in context/business.md carries the domain and the page it came from.
≈ “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
beat-my-competitors
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 |
config.competitors or strategy.json.competitors | who to tear down | ask the user for 3 to 5 domains and stop |
data/state.json | our own tier distribution, for a like-for-like comparison | run rainmaker audit |
data/citation-graph.json | which competitor pages answer engines cite | say the comparison omits AI citation |
Produces
data/competitors.json. Appends benchmark proof points to strategy.json (owner: beat-my-competitors) and the competitor table in context/business.md.
Refuses when
No competitors are named anywhere. Ask for 3 to 5 domains and stop; do not guess competitors from search results.
Concurrency
One agent per competitor, maximum 5. This is one of the three permitted fan-out points in the system.
Procedure
- Per competitor: fetch their sitemap, classify every URL into our own tier rules from
src/analyze/tiering.ts, so the comparison is like for like rather than borrowing their own labels. - Count pages per tier. A competitor with 40 tier 1 pages against our 3 is the finding; their domain rating is not, and is never used.
- Pull their tier 0 and tier 1 pages. Extract positioning language, pricing presence, proof types and named integrations, in their own words.
- Diff
strategy.json.clustersagainst their coverage. A cluster we have not built that they cover becomes a candidate withgap: 'missing'. - Where GSC data exists, mark which of our queries they also rank for.
- Where the citation graph exists, mark which of their pages answer engines cite. A competitor page that owns the answers matters more than one that merely exists.
Decision rules
- Never report a third-party domain authority score. The core spec forbids vendor authority metrics anywhere in scoring or reporting.
- A gap counts only when the competitor's page is tier 0, 1 or 2. Tier 3 blog volume is one summary count, never a page-by-page list.
- Every competitor claim in
context/business.mdcarries the domain and the page it came from.
Output
Per competitor: a tier distribution table, a positioning summary in their own words, and a joint gap table ranked by the tier weight of the missing cluster.
Done when
competitors.json validates against its schema, every gap row has a target tier and a pain point id or an explicit unmapped marker, and no domain authority score appears anywhere in the output.
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.

