find-my-quick-wins
Skill0 starsChanged 4 months agoMITView on GitHub
Find the rankings closest to paying off: striking-distance queries, pages competing with each other, and impressions that are not converting into clicks. Reads Search Console snapshots the core already pulled.
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
- 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, 3 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 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.
- Distinctive: line 57
No Search Console data exists.
- Distinctive: line 69
Never report an average position change under 1.0 as a change.
- Distinctive: line 80
Every recommendation names one winning URL and one query.
≈ “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
find-my-quick-wins
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/snapshots/<latest>/gsc.json | queries, positions, impressions | "No Search Console data. Run rainmaker doctor to see why, then rainmaker fetch --source gsc." |
the previous gsc.json | movement needs two windows | report the current window only, and say a trend needs a second |
data/state.json | tiers, so a win is framed by distance to money | run rainmaker audit |
context/glossary.md | brand tokens, to exclude branded queries | say so: cannibalisation findings will be less reliable |
Produces
Nothing.
Refuses when
No Search Console data exists. Opportunity sizing without it is a flat constant, and calling that a quick win would be inventing a number.
Procedure
- Striking distance: queries at position 4 to 15 with 100 or more impressions in 28 days. Rank by impressions multiplied by the CTR gap to position 3, using the curve in
src/analyze/scoring.ts. - Cannibalisation: only when all four hold. Non-branded query, two or more URLs each holding 5 percent of its impressions, both inside position 30, and the overlap present in two consecutive windows.
- Clicks that are not arriving: impressions with zero clicks inside position 10 across two windows. That is a title and snippet problem, not a ranking problem, and saying so saves the wrong month of work.
- Movement: position deltas between the two most recent snapshots, only where both windows carry 50 or more impressions.
- Join every row to its tier. Collapse tier 3 and 4 movement into one summary line.
Decision rules
- Never report an average position change under 1.0 as a change. Position is an average of averages, and smaller deltas are noise.
- Always 28 days. Never 30.
- Where
config.geographiesis set, filter to those markets before computing position. Otherwise say the position is blended across markets and drop confidence to 0.5. - A striking-distance query on a tier 3 page is reported below a smaller opportunity on a tier 1 page, and the ordering is explained.
Output
Report spine. Section 3 lists each opportunity as: query, URL, tier, current position, impressions, estimated click gap. The cannibalisation table names the URL to keep and the ones to consolidate into it, never just the pair.
Done when
Every recommendation names one winning URL and one query. Nothing says "improve the content" without naming the query, the position and the gap.
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.

