Cma

Skill m-binimran/real-estate-pack/skills/cma

Compliance guardrails, skills, loops & review agents for US residential real estate agents on Claude Code (Fair Housing + fact-accuracy). Not legal advice.

Install

npx -y skills add m-binimran/real-estate-pack --skill cma

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Build a Comparative Market Analysis - select comparable sales, adjust for differences, and produce a defensible price range with rationale. Use when pricing a listing or advising a buyer's offer.

SKILL.md

1.5 KB, as published. Nobody here has run it

cma

A CMA is an opinion of value for pricing - not an appraisal (say so). It must be built on real comps.

Process

Subject profile: location, sqft, beds/baths, lot, condition, age, key features.
Pull real comps: recent (ideally < 6 months) sold properties, same area, similar size/type. Note active + pending for current competition. Use actual MLS/public-record data - never invented addresses/prices.
Adjust each comp to the subject for material differences (sqft, condition, garage, lot, updates, location). Show the adjustment direction and rough magnitude; be conservative and consistent.
Reconcile to a supported price RANGE (not a single false-precision number), weighting the most similar comps.
Explain the rationale so the client understands the range and the market trend.

Output

A comps table (address, sold price, date, sqft, key diffs, adjustment), the suggested range, and a plain-English rationale. Flag any comp data the agent must confirm in the MLS.

Guardrails

Label it clearly: opinion of value for pricing, not an appraisal (only a licensed appraiser appraises).
No fabricated comps or prices (the truth-telling rule). If data is missing, say so - don't fill the gap.
Stay objective; don't anchor to the seller's wish price.