verticals
Skill112 starsChanged 2 months agoMITView on GitHub
Domain knowledge for SMB industry products — the vocabulary, the entities a spec must model, the incumbent to route around, and what a naive build gets wrong — one file per industry, plus local SEO and money-on-a-phone. Read the one file that applies before speccing or building the product.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- Shri-Phnx/claude-skillstheir own version, first seen Oct 13, 2026
- rushindrasinha/youtube-shorts-pipelinetheir own version, first seen Jun 9, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- rushindrasinha/youtube-shorts-pipeline★ 2.3ksame name
- Shri-Phnx/claude-skills★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository35 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- aesthetic-instrumentSkill
- anti-patternsSkill
- anydesignSkill
- archetype-review-baseSkill
- brainstormingSkill
- build-speedSkill
- codex-hostSkill
- committed-aestheticSkill
- cost-modelSkill
- crystallizeSkill
- decision-evalSkill
- deploy-landedSkill
- discoverySkill
- done-blockedSkill
- great_ctoSkill
- lifecycle-messagingSkill
- migration-ready-schemaSkill
- observability-baselineSkill
- opportunity-solution-treeSkill
- outcome-roadmapSkill
- pm-planningSkill
- pre-mortemSkill
- product-economicsSkill
- prose-styleSkill
- quant-validationSkill
- secrets-rotationSkill
- signing-preflightSkill
- skeptical-triageSkill
- stack-baselineSkill
- test-strategySkill
- ui-ux-pro-maxSkill
- vertical-onboardingSkill
- well-architectedSkill
The file
Files
Verticals — read the one that applies
Each file below is the domain brief for one kind of product. They are references, not separate skills: one line in every session's skill list instead of sixteen paragraphs, and the full text only when a product needs it.
| Product is for… | Read |
| HVAC, plumbing, cleaning, landscaping — dispatch, quoting, booking | home-services.md |
| Agencies, consulting, creative — proposals, portals, time + invoicing | professional-services.md |
| Restaurants, cafés — ordering, reservations, loyalty, shifts | restaurants.md |
| SMB storefronts — catalog, inventory, pricing, cart recovery | retail.md |
| Residential real estate — listings, lead CRM, transactions, property management | real-estate.md |
| Studios, gyms, coaches — class booking, membership, content | fitness.md |
| Creators, marketing — scheduling, analytics, monetization, sponsorships | creator.md |
| HR, recruiting — ATS, onboarding, scheduling, surveys | hr-recruiting.md |
| Contractors, field crews — bids, project logs, subcontractors | construction.md |
| Shipping, warehouse-lite, routes, purchase orders | logistics.md |
| Tour and activity operators, small stays, travel advisors — departures, OTAs, itineraries | travel.md |
| Small nonprofits — donations, donor records, grants, volunteers | nonprofit.md |
| Small farms — field and spray records, livestock, shares and direct sales, lot codes | agrotech.md |
| Marinas, boat charter, vessel upkeep, container tracking for small forwarders | maritime.md |
| An app that holds a balance or moves money on a phone (orthogonal to the rows above) | fintech-mobile.md |
| Public pages that must be found in local or product search | local-seo.md |
How to read it
From a great_cto checkout the files sit next to this one (skills/verticals/<file>). From
an installed plugin, resolve the newest cached version:
# <file> is the row that applies, e.g. retail
cat "$(ls ~/.claude/plugins/cache/*/great_cto/*/skills/verticals/<file>.md 2>/dev/null | awk -F'/plugins/cache/' '{split($NF,p,"/"); print p[3], $0}' | sort -V | tail -1 | cut -d' ' -f2-)"Apply what it says to the spec: its vocabulary in the names, its must-model entities in the data model, its "what a naive build gets wrong" list as review items. If no row fits, read nothing — a near-miss vertical imports the wrong rules.
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.

