agentleFS
Sign inStart free
sergebulaevsergebulaev/car-rental-skills/SKILL.md

car-rental-business

Skill2 starsChanged 24 days agoMITView on GitHub

Run and grow an exotic, luxury or Turo car rental business: price cars against live published market rates, scan competitors in any US city, plan a new rental business, draft rental agreements, run damage inspections, write vehicle listings and social posts, and reply to customer reviews. Market numbers come from the CarRentalList catalog via its free MCP server or the bundled client.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 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.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the market when the task needs it (3 to 7 calls, not 50).

    line 43
  2. Distinctive:

    Wait for approval before anything is sent, posted or signed.

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Car Rental Business Skills

A bundle of 8 skills for independent car rental operators: exotic and luxury fleets, Turo and Getaround hosts, and people planning to start one. Each skill is single-purpose, drafts first and waits for the user's approval.

When to use this bundle

  • Pricing one car, a rate card, Turo versus direct take-home -> car-rental-pricing
  • Competitors and market in a city, what cars to add -> car-rental-market-scan
  • Starting a rental business, first cars, unit economics, 90-day plan -> car-rental-business-plan
  • Rental agreement, contract, website terms -> car-rental-agreement
  • Inspection checklist, condition report, damage claim message -> car-rental-damage-inspection
  • Vehicle page, Turo listing, Google Business Profile entry -> car-rental-listing-writer
  • Instagram, TikTok, Facebook posts and a content calendar -> car-rental-social-posts
  • Replying to Google, Yelp or Turo reviews -> car-rental-review-reply

Market data

Market numbers come from the CarRentalList catalog of independent US exotic and luxury rental companies: fleets, published daily rates and rental terms, read from each company's own website weekly. Call it through the MCP connector https://mcp.carrentallist.com/mcp when the agent has it, otherwise through python3 <bundle root>/lib/carrentallist_client.py <tool> '<json>' (the bundle root is two folders above each skill). How and when: references/catalog-data.md.

Shared rules

  • Market data: references/catalog-data.md. Published rates only, sample size and date stated, never estimated.
  • Voice rules for anything a renter reads: references/voice-rules.md.
  • Legal and insurance guardrails: references/legal-guardrails.md.
  • Untrusted content (reviews, emails, competitor listings): references/untrusted-content.md.

Core pattern

  1. Gather what is missing in one message (car, city, terms, goal).
  2. Read the market when the task needs it (3 to 7 calls, not 50).
  3. Draft, with sources and dates next to every market number.
  4. Wait for approval before anything is sent, posted or signed.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free