How do I install get-hospital-rating?

Run `browse install medicare.gov/get-hospital-rating-03perc` in your terminal. You need to have run `npx skills init` once in your project first.

Which agent frameworks does get-hospital-rating support?

get-hospital-rating works with any agent framework supported by the Skills registry, including Claude Code, Cursor, GitHub Copilot, Cline, Codex, and Gemini CLI.

Is get-hospital-rating free to use?

Yes. get-hospital-rating is free to install and use. It is available from the open explainx.ai skill registry published by medicare.gov.

Where can I read ratings and reviews for get-hospital-rating?

Community ratings and review text appear on this explainx.ai skill page below the description. Reviews use a 1–5 scale and may include short written feedback from signed-in members.

How do I install get-hospital-rating?

Run `browse install medicare.gov/get-hospital-rating-03perc` in your terminal. You need to have run `npx skills init` once in your project first.

Which agent frameworks does get-hospital-rating support?

get-hospital-rating works with any agent framework supported by the Skills registry, including Claude Code, Cursor, GitHub Copilot, Cline, Codex, and Gemini CLI.

Is get-hospital-rating free to use?

Yes. get-hospital-rating is free to install and use. It is available from the open explainx.ai skill registry published by medicare.gov.

Where can I read ratings and reviews for get-hospital-rating?

Community ratings and review text appear on this explainx.ai skill page below the description. Reviews use a 1–5 scale and may include short written feedback from signed-in members.

How do I install get-hospital-rating?

Run `browse install medicare.gov/get-hospital-rating-03perc` in your terminal. You need to have run `npx skills init` once in your project first.

Which agent frameworks does get-hospital-rating support?

get-hospital-rating works with any agent framework supported by the Skills registry, including Claude Code, Cursor, GitHub Copilot, Cline, Codex, and Gemini CLI.

Is get-hospital-rating free to use?

Yes. get-hospital-rating is free to install and use. It is available from the open explainx.ai skill registry published by medicare.gov.

Where can I read ratings and reviews for get-hospital-rating?

Community ratings and review text appear on this explainx.ai skill page below the description. Reviews use a 1–5 scale and may include short written feedback from signed-in members.

How do I install get-hospital-rating?

Run `browse install medicare.gov/get-hospital-rating-03perc` in your terminal. You need to have run `npx skills init` once in your project first.

Which agent frameworks does get-hospital-rating support?

get-hospital-rating works with any agent framework supported by the Skills registry, including Claude Code, Cursor, GitHub Copilot, Cline, Codex, and Gemini CLI.

Is get-hospital-rating free to use?

Yes. get-hospital-rating is free to install and use. It is available from the open explainx.ai skill registry published by medicare.gov.

Where can I read ratings and reviews for get-hospital-rating?

Community ratings and review text appear on this explainx.ai skill page below the description. Reviews use a 1–5 scale and may include short written feedback from signed-in members.

How do I install get-hospital-rating?

Run `browse install medicare.gov/get-hospital-rating-03perc` in your terminal. You need to have run `npx skills init` once in your project first.

Which agent frameworks does get-hospital-rating support?

get-hospital-rating works with any agent framework supported by the Skills registry, including Claude Code, Cursor, GitHub Copilot, Cline, Codex, and Gemini CLI.

Is get-hospital-rating free to use?

Yes. get-hospital-rating is free to install and use. It is available from the open explainx.ai skill registry published by medicare.gov.

Where can I read ratings and reviews for get-hospital-rating?

Community ratings and review text appear on this explainx.ai skill page below the description. Reviews use a 1–5 scale and may include short written feedback from signed-in members.

How do I install get-hospital-rating?

Run `browse install medicare.gov/get-hospital-rating-03perc` in your terminal. You need to have run `npx skills init` once in your project first.

Which agent frameworks does get-hospital-rating support?

get-hospital-rating works with any agent framework supported by the Skills registry, including Claude Code, Cursor, GitHub Copilot, Cline, Codex, and Gemini CLI.

Is get-hospital-rating free to use?

Yes. get-hospital-rating is free to install and use. It is available from the open explainx.ai skill registry published by medicare.gov.

Where can I read ratings and reviews for get-hospital-rating?

Community ratings and review text appear on this explainx.ai skill page below the description. Reviews use a 1–5 scale and may include short written feedback from signed-in members.

How do I install get-hospital-rating?

Run `browse install medicare.gov/get-hospital-rating-03perc` in your terminal. You need to have run `npx skills init` once in your project first.

Which agent frameworks does get-hospital-rating support?

get-hospital-rating works with any agent framework supported by the Skills registry, including Claude Code, Cursor, GitHub Copilot, Cline, Codex, and Gemini CLI.

Is get-hospital-rating free to use?

Yes. get-hospital-rating is free to install and use. It is available from the open explainx.ai skill registry published by medicare.gov.

Where can I read ratings and reviews for get-hospital-rating?

Community ratings and review text appear on this explainx.ai skill page below the description. Reviews use a 1–5 scale and may include short written feedback from signed-in members.

How do I install get-hospital-rating?

Run `browse install medicare.gov/get-hospital-rating-03perc` in your terminal. You need to have run `npx skills init` once in your project first.

Which agent frameworks does get-hospital-rating support?

get-hospital-rating works with any agent framework supported by the Skills registry, including Claude Code, Cursor, GitHub Copilot, Cline, Codex, and Gemini CLI.

Is get-hospital-rating free to use?

Yes. get-hospital-rating is free to install and use. It is available from the open explainx.ai skill registry published by medicare.gov.

Where can I read ratings and reviews for get-hospital-rating?

Community ratings and review text appear on this explainx.ai skill page below the description. Reviews use a 1–5 scale and may include short written feedback from signed-in members.

How do I install get-hospital-rating?

Run `browse install medicare.gov/get-hospital-rating-03perc` in your terminal. You need to have run `npx skills init` once in your project first.

Which agent frameworks does get-hospital-rating support?

get-hospital-rating works with any agent framework supported by the Skills registry, including Claude Code, Cursor, GitHub Copilot, Cline, Codex, and Gemini CLI.

Is get-hospital-rating free to use?

Yes. get-hospital-rating is free to install and use. It is available from the open explainx.ai skill registry published by medicare.gov.

Where can I read ratings and reviews for get-hospital-rating?

Community ratings and review text appear on this explainx.ai skill page below the description. Reviews use a 1–5 scale and may include short written feedback from signed-in members.

How do I install get-hospital-rating?

Run `browse install medicare.gov/get-hospital-rating-03perc` in your terminal. You need to have run `npx skills init` once in your project first.

Which agent frameworks does get-hospital-rating support?

get-hospital-rating works with any agent framework supported by the Skills registry, including Claude Code, Cursor, GitHub Copilot, Cline, Codex, and Gemini CLI.

Is get-hospital-rating free to use?

Yes. get-hospital-rating is free to install and use. It is available from the open explainx.ai skill registry published by medicare.gov.

Where can I read ratings and reviews for get-hospital-rating?

Community ratings and review text appear on this explainx.ai skill page below the description. Reviews use a 1–5 scale and may include short written feedback from signed-in members.

How do I install get-hospital-rating?

Run `browse install medicare.gov/get-hospital-rating-03perc` in your terminal. You need to have run `npx skills init` once in your project first.

healthcare

get-hospital-rating▌

medicare.gov/get-hospital-rating-03perc · updated May 21, 2026

MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.

$browse install medicare.gov/get-hospital-rating-03perc

0 commentsdiscussion

summary

Look up a hospital's CMS Care Compare star rating, HCAHPS patient-experience scores, condition mortality/readmission rates, hospital-acquired infections, ED timeliness, and full metadata by CCN, name+state, or Care Compare URL. Supports compare_to for side-by-side hospitals with national + state benchmarks. Read-only.

skill.md

name	get-hospital-rating
title	Medicare.gov Hospital Quality Rating
description	>- Look up a hospital's CMS Care Compare star rating, HCAHPS patient-experience scores, condition mortality/readmission rates, hospital-acquired infections, ED timeliness, and full metadata by CCN, name+state, or Care Compare URL. Supports compare_to for side-by-side hospitals with national + state benchmarks. Read-only.
website	medicare.gov
category	healthcare
tags	- healthcare - hospitals - ratings - cms - medicare - read-only - public-data
source	'browserbase: agent-runtime 2026-05-18'
updated	'2026-05-18'
recommended_method	api
alternative_methods	[]
verified	true
proxies	true

Medicare.gov Hospital Quality Rating

Purpose

Given a hospital reference — CMS provider/CCN ID, hospital name + city/state, or a Care Compare URL — return the hospital's CMS quality ratings as a structured JSON record. Includes the overall 1–5 star rating, the five sub-domain group ratings (mortality, safety of care, readmission, patient experience, timely & effective care), HCAHPS patient-experience composite scores, common-condition mortality/readmission rates (heart attack, heart failure, pneumonia, stroke, COPD), hospital-acquired infection (HAI) Standardized Infection Ratios for CLABSI / CAUTI / SSI / MRSA / C.diff, emergency-department timeliness, full hospital metadata, and the canonical Care Compare URL. Supports a compare_to input that returns multiple hospitals side-by-side plus national and state benchmarks. Read-only; never clicks Save Hospital, Print, Sign In, Compare-cart submit, or any mutation control.

When to Use

"Show me the CMS star rating for Mayo Clinic Rochester."
"How does HCA Florida Citrus Hospital compare to the state average for sepsis mortality?"
A patient-experience research agent benchmarking three named hospitals on HCAHPS composites.
A discharge-planning tool that needs ED timeliness and readmission rates for one hospital plus the national/state benchmark for each metric.
A scheduled job pulling quality data for an entire health-system roster (lookup-by-CCN at scale).

Workflow

The medicare.gov Care Compare UI is a thin Angular SPA over a Kong-gated internal API (https://www.medicare.gov/api/care-compare/*). The exact same per-hospital quality data is also published — at the row level, refreshed quarterly — through the CMS Provider Data Catalog (data.cms.gov) DKAN datastore, which is fully public, auth-free, no anti-bot, and supports per-CCN filtering, contains-matching, multi-condition queries, and joins with state/national benchmark companion datasets. Iter-1 verification across 7 datasets for CCN 240010 (Mayo Clinic Hospital Rochester) returned 100% of the fields the Care Compare card surfaces. Lead with the PDC API. Use the browser flow only when you specifically need the rendered Care Compare card (e.g. for screenshot-in-the-loop tasks). Calling the medicare.gov Kong gateway directly is a confirmed dead end (401 No API key found in request).

1. Resolve the input to a CCN

The CMS Certification Number (CCN) — sometimes called the Provider ID or Facility ID — is the 6-digit primary key across every Hospital Compare dataset.

Input shape	Resolution
6-digit CCN (e.g. `240010`)	Use directly.
Hospital name + state	Query Hospital General Information with `contains` on `facility_name` + `=` on `state`.
Hospital name + city + state	Same as above, then filter by `citytown` client-side (case-insensitive).
`https://www.medicare.gov/care-compare/details/hospital/{ccn}` URL	Extract the trailing 6-digit path segment.
`https://www.medicare.gov/care-compare/results?...` URL	No CCN in URL — extract `zipcode=` + provider type and run a name-keyed PDC query.

# Name → CCN lookup (Hospital General Information = dataset xubh-q36u)
curl 'https://data.cms.gov/provider-data/api/1/datastore/query/xubh-q36u/0?conditions%5B0%5D%5Bproperty%5D=facility_name&conditions%5B0%5D%5Bvalue%5D=mayo&conditions%5B0%5D%5Boperator%5D=contains&conditions%5B1%5D%5Bproperty%5D=state&conditions%5B1%5D%5Bvalue%5D=MN&conditions%5B1%5D%5Boperator%5D=%3D&limit=10'
# → 240010 MAYO CLINIC HOSPITAL ROCHESTER, ROCHESTER, MN, rating=5

2. Pull the per-CCN datasets

Issue one GET per dataset, filtering by facility_id=<CCN>. All 7 datasets share the same authentication-free DKAN datastore endpoint. Field names are stable across quarterly refreshes.

Skill data point	Dataset ID	Title	Key fields returned
Overall 1–5 stars, group measure counts, metadata	`xubh-q36u`	Hospital General Information	`hospital_overall_rating`, `mort_group_measure_count`/`count_of_mort_measures_better/no_different/worse`, same for `safety`/`readm`/`pt_exp`/`te`; address, phone, hospital_type, hospital_ownership, emergency_services, meets_criteria_for_birthing_friendly_designation
HCAHPS patient-experience composites + summary star	`dgck-syfz`	Patient survey (HCAHPS) - Hospital	One row per `hcahps_measure_id`. `H_STAR_RATING` row carries `patient_survey_star_rating` (1–5 summary). `H__STAR_RATING` carries the per-composite stars. `H__LINEAR_SCORE` rows carry the linear-mean numeric score. `H_*_A_P`/`U_P`/`SN_P` give the "Always/Usually/Sometimes-or-Never" percent splits. `number_of_completed_surveys` + `survey_response_rate_percent` for sample quality.
Common-condition mortality, complications, PSI safety	`ynj2-r877`	Complications and Deaths - Hospital	`measure_id` ∈ {`MORT_30_AMI` (heart attack), `MORT_30_HF` (heart failure), `MORT_30_PN` (pneumonia), `MORT_30_STK` (stroke), `MORT_30_COPD` (COPD), `MORT_30_CABG` (CABG surgery), `Hybrid_HWM` (hospital-wide mortality), `COMP_HIP_KNEE`, `PSI_03`–`PSI_15` (safety indicators), `PSI_90` (safety composite)}; `score` (rate per 100/1000), `compared_to_national` ("Better Than"/"No Different Than"/"Worse Than the National Rate"), `denominator`, `lower_estimate`, `higher_estimate` (95% CI).
Unplanned readmissions / ED return-day rates	`632h-zaca`	Unplanned Hospital Visits - Hospital	`measure_id` ∈ {`EDAC_30_AMI`, `EDAC_30_HF`, `EDAC_30_PN` (excess days), `READM_30_*` (readmission rates per condition)}; same `compared_to_national` ternary + denominator + CI.
Hospital-acquired infections (HAI) Standardized Infection Ratios	`77hc-ibv8`	Healthcare Associated Infections - Hospital	Six measure families, each with 6 rows: `_SIR` (the actual SIR — what's surfaced on Care Compare), `_NUMERATOR`, `_DOPC` (device-days denominator), `_ELIGCASES`, `_CILOWER`, `_CIUPPER`. HAI_1 = CLABSI, HAI_2 = CAUTI, HAI_3 = SSI Colon, HAI_4 = SSI Abdominal Hysterectomy, HAI_5 = MRSA Bacteremia, HAI_6 = C.diff. `compared_to_national` carries the four bucket levels: `Better than the National Benchmark`, `No Different than National Benchmark`, `Worse than the National Benchmark`, `Not Available`.
Timely & Effective Care, including ED timeliness	`yv7e-xc69`	Timely and Effective Care - Hospital	Filter on `_condition='Emergency Department'` for ED timeliness: `OP_18a`/`b`/`c`/`d` (median minutes in ED before leaving, by patient class), `OP_22` (% who left before being seen), `OP_23` (% head-CT-results-within-45-minutes), `EDV` (volume bucket: low/medium/high/very high). Other `_condition` values: `Cataract Surgery`, `Colonoscopy`, `Heart Attack or Chest Pain`, `Pregnancy and Delivery`, `Preventive Care`, `Sepsis Care`.
Medicare spending per beneficiary	`nrth-mfg3`	Medicare Hospital Spending by Claim	Hospital vs. state vs. national spending across pre-admission / index-admission / post-discharge windows + claim-type splits.

Benchmark companion datasets — query without facility_id for national-level benchmark rows, or with state=<2-letter> for state-level benchmark rows. Companion IDs:

Per-hospital dataset	National benchmark	State benchmark	What the benchmark row carries
`xubh-q36u` (overall rating)	— (computed from rollups)	—	n/a
`dgck-syfz` (HCAHPS)	`99ue-w85f`	`84jm-wiui`	`hcahps_answer_percent` and `hcahps_linear_mean_value` for each measure ID across all reporting hospitals nationally / state-wide.
`77hc-ibv8` (HAI)	`yd3s-jyhd`	`k2ze-bqvw`	`score` is the nationally/state-pooled SIR (typically 1.0 for national, varies for state).
`ynj2-r877` (Complications/Deaths)	`qqw3-t4ie`	`bs2r-24vh`	`national_rate`; hospital-count distribution columns (`number_of_hospitals_worse
`632h-zaca` (Unplanned Visits)	`cvcs-xecj`	`4gkm-5ypv`	Same shape as Complications/Deaths benchmarks, with extra `number_of_hospitals_fewer
`yv7e-xc69` (Timely & Effective Care)	`isrn-hqyy`	`apyc-v239`	`score` is the national/state median for each measure.

3. Construct the canonical Care Compare URL

https://www.medicare.gov/care-compare/details/hospital/{ccn}?city=&state={STATE}&zipcode={ZIPCODE}&page=1&from=hospital&type=Hospital

This URL works only when reached through the SPA's in-app router — see Site-Specific Gotchas. Return it as the canonical link anyway; users who click it land on home and search by ZIP.

4. Assemble the unified output

Merge the per-CCN rows from each dataset into one record per hospital (see ## Expected Output for the schema). Map each compared_to_national enum string into a normalized boolean trio {better, no_different, worse} for downstream filtering. Preserve raw score values as strings (CMS does — they signal "Not Available" / "Not Applicable" via string sentinels, not nulls).

5. Handle `compare_to`

When compare_to: [<ccn or name+state>, ...] is set, run steps 1–4 in parallel for each. After all hospitals are resolved, query each national + state benchmark companion dataset once (not per-hospital) and embed the result as a top-level benchmarks.national and benchmarks.state.<state-code> block. The PDC DKAN datastore tolerates ~5 req/s without rate-limiting in our testing; sequential per-hospital fan-out is fine.

6. Browser fallback (only when the user needs the rendered Care Compare card)

Use this when (a) the consumer is a visual workflow that wants a screenshot of the per-hospital card, or (b) the user explicitly requested the medicare.gov UI. Skip otherwise — the API path returns the same data at ~100× lower cost.

Stealth + residential-proxy session is mandatory. Akamai protects the site; bare sessions get challenged.

sid=$(browse cloud sessions create --keep-alive --proxies --verified | jq -r .id)
export BROWSE_SESSION="$sid"

Land on the search-results page directly with full query params — this bypasses the Welcome → Hospital tile → ZIP-input click chain:
```
browse open "https://www.medicare.gov/care-compare/results?searchType=Hospital&page=1&zipcode={ZIPCODE}&sort=closest&radius=25" --remote
```
Wait ≥ 8 seconds after networkidle — hospital cards render lazily after the SPA fires POST /api/care-compare/provider?autoExpand=true.
Click into a card by the hospital's anchor text (not by href pattern — see gotcha below). The SPA navigates to its in-app detail route, which renders the full quality card.
Read off the rendered DOM, then browse cloud sessions update "$sid" --status REQUEST_RELEASE.

Site-Specific Gotchas

Deep-link /care-compare/details/hospital/{ccn} does NOT work as a plain URL load. Confirmed in iters 1, 2, and 4: a page.goto(detailUrl) from a cold session returns the home-page chrome only (finalUrl: /care-compare/, h1: "Menu"). The SPA's router treats /details/hospital/* as an internal route reachable only through the in-app navigation graph (home → ZIP → Hospital → Search → click result). Construct the canonical URL anyway for output / linking — but never rely on goto for scraping the detail page. Click through from /results?... instead.
/api/care-compare/* is auth-walled. Every endpoint observed (/refresh, /news-updates, /datafeed, /geocode/search, /provider?autoExpand=true) returns 401 {"message":"No API key found in request"} to direct requests. The API key is embedded in the SPA bundle (main.<hash>.js, ~1MB — exceeds Browserbase Fetch 1MB cap). Do not waste cycles trying to reverse this key — the public PDC datastore is the right path.
The SPA bundle exceeds 1MB. browse cloud fetch https://www.medicare.gov/care-compare/en/main.<hash>.js --proxies returns HTTP 502 "response body exceeded the maximum allowed size of 1MB." If you need to inspect bundle internals, do it inside a Browserbase Function (no size cap there) or use page.evaluate to introspect runtime globals.
Akamai bot challenge is solved transparently with --verified --proxies but bare sessions see /DgEq/aOIa/g3e9/o16Ycw/m55OcGf3k5J7rSN9iS/... POSTs (the _abck challenge URL) and a JS-shell HTML on first navigation. Always run with stealth + residential proxy.
Provider-type tile click is fragile. The home page uses mat-list-item tiles, not standard <button>s. page.getByRole("button", { name: /hospital/i }) matched "Menu" instead of the Hospital tile in iter 1. Prefer the direct /results?searchType=Hospital&zipcode={ZIP} deep-link, which does work — it bypasses the tile.
<a href="/care-compare/details/hospital/..."> may not exist. Iter 4 confirmed waitForSelector("a[href*='/care-compare/details/hospital/']") times out at 30 s. Angular's routerLink directives do not always materialize as <a href> in the DOM until hover or focus. Click by visible text instead: page.getByRole("link", { name: /<hospital name>/i }).
hospital_overall_rating: "Not Available" is a real value. Critical-access hospitals, brand-new hospitals, VA hospitals, children's hospitals, and rural emergency hospitals (REH) often lack a star rating. Treat as null in normalized output, surface the raw "Not Available" string in a _raw block. For REH, query the parallel datasets: 97xg-v3wv (Rural Emergency Hospital - Timely and Effective Care) and zez1-ka2w (REH - Unplanned Hospital Visits).
HAI compared_to_national enum capitalization differs from Complications/Deaths. HAI uses Better than the National Benchmark (lowercase "than", and "Benchmark" not "Rate"). Complications/Deaths uses Better Than the National Rate. Normalize before comparison.
HCAHPS rows are one-per-measure-question. Filter to hcahps_measure_id = 'H_STAR_RATING' for the summary star (5-stars at Mayo Rochester), or H_*_STAR_RATING for per-composite stars (Nurse communication, Doctor communication, Cleanliness, Quietness, Discharge information, Communication about medicines, Overall hospital rating, Recommend hospital). H_*_LINEAR_SCORE rows carry the numeric 0–100 linear mean. The _A_P/_U_P/_SN_P triplets sum to 100% and represent the always/usually/sometimes-or-never response distribution.
ED measure IDs OP_18a through OP_18d decompose by patient class. OP_18a = all ED patients, OP_18b = ED patients excluding transferred + psychiatric (the "general" wait time most often quoted), OP_18c = psychiatric/mental health patients, OP_18d = patients transferred to another facility. National median for OP_18b was 161 minutes; Minnesota state median was 130; Mayo Rochester scored 245. Lower is better.
PDC properties filter expects an array, not a comma-string. properties=facility_id,facility_name returns 400 JSON Schema validation failed. Use properties[0]=facility_id&properties[1]=facility_name, or just omit properties and read every column (response sizes are small enough — Hospital General Info is ~5–7 KB per CCN).
PDC SQL endpoint exists at /api/1/datastore/sql?query=... but uses bracket-DSL syntax ([SELECT ...][FROM ...][WHERE ...] — not standard SQL). The query parameter must reference each dataset by its UUID, not its slug. For most use cases the conditions API at /api/1/datastore/query/{slug}/0 is simpler — it handles =, contains, starts with, <>, <, <=, >, >=.
Read-only constraints: do not click Save Hospital, the heart-icon Add to Favorites, Print, Sign In, Compare cart submit, or Send Feedback. These are mutation surfaces with confirmation dialogs but the rule is no-mutation regardless.
Refresh cadence: PDC datasets update quarterly (typical CMS cycle: October release of Care Compare data covers Jul-prior-year through Jun-current-year). Add start_date/end_date to every emitted measure so consumers can detect stale data.

Expected Output

Single-hospital response shape (the compare_to shape is identical with a hospitals: [...] array and a top-level benchmarks block):

{
  "ccn": "240010",
  "name": "MAYO CLINIC HOSPITAL ROCHESTER",
  "care_compare_url": "https://www.medicare.gov/care-compare/details/hospital/240010?city=&state=MN&zipcode=55902&page=1&from=hospital&type=Hospital",
  "metadata": {
    "address": "1216 SECOND STREET SOUTHWEST",
    "city": "ROCHESTER",
    "state": "MN",
    "zip_code": "55902",
    "county": "OLMSTED",
    "phone": "(507) 255-5123",
    "hospital_type": "Acute Care Hospitals",
    "hospital_ownership": "Voluntary non-profit - Church",
    "emergency_services": true,
    "teaching_hospital": null,
    "birthing_friendly": true
  },
  "overall_rating": {
    "stars": 5,
    "footnote": null,
    "as_of": "2024-07-01_to_2025-06-30"
  },
  "domain_ratings": {
    "mortality":          { "measure_count": 8,  "better": 6, "no_different": 2, "worse": 0 },
    "safety":             { "measure_count": 8,  "better": 6, "no_different": 2, "worse": 0 },
    "readmission":        { "measure_count": 11, "better": 4, "no_different": 7, "worse": 0 },
    "patient_experience": { "measure_count": 15, "better": null, "no_different": null, "worse": null },
    "timely_effective":   { "measure_count": 9,  "better": null, "no_different": null, "worse": null }
  },
  "hcahps": {
    "summary_star": 5,
    "completed_surveys": 3895,
    "response_rate_percent": 38,
    "composites": {
      "nurse_communication":         { "star": 5, "linear_mean": 94, "always_percent": 84 },
      "doctor_communication":        { "star": 4, "linear_mean": 94, "always_percent": 84 },
      "staff_responsiveness":        { "star": null, "linear_mean": null, "always_percent": null },
      "communication_about_medicines": { "star": 4, "linear_mean": 81, "always_percent": 64 },
      "discharge_information":       { "star": 5, "linear_mean": 91, "yes_percent": 91 },
      "cleanliness":                 { "star": 4, "linear_mean": 89, "always_percent": 75 },
      "quietness":                   { "star": 4, "linear_mean": 88, "always_percent": 68 },
      "overall_hospital_rating":     { "star": 5, "linear_mean": 94, "rated_9_or_10_percent": 85 },
      "recommend_hospital":          { "star": 5, "linear_mean": 95, "definitely_yes_percent": 88 }
    }
  },
  "common_conditions": {
    "MORT_30_AMI":     { "name": "Death rate for heart attack patients",      "score": "8.4", "compared_to_national": "Better Than the National Rate",     "denominator": 1234, "ci": ["6.2","10.9"] },
    "MORT_30_HF":      { "name": "Death rate for heart failure patients",     "score": "7.6", "compared_to_national": "Better Than the National Rate",     "denominator": 987,  "ci": ["6.0","9.4"] },
    "MORT_30_PN":      { "name": "Death rate for pneumonia patients",         "score": "11",  "compared_to_national": "Better Than the National Rate" },
    "MORT_30_STK":     { "name": "Death rate for stroke patients",            "score": "10.1","compared_to_national": "Better Than the National Rate" },
    "MORT_30_COPD":    { "name": "Death rate for COPD patients",              "score": "7.1", "compared_to_national": "No Different Than the National Rate" },
    "EDAC_30_AMI":     { "name": "Hospital return days for heart attack patients", "score": "-23.3", "compared_to_national": "Fewer Days Than Average per 100 Discharges" },
    "EDAC_30_HF":      { "name": "Hospital return days for heart failure patients", "score": "-17.1", "compared_to_national": "Fewer Days Than Average per 100 Discharges" },
    "EDAC_30_PN":      { "name": "Hospital return days for pneumonia patients",     "score": "-6.9",  "compared_to_national": "Average Days per 100 Discharges" }
  },
  "infections": {
    "CLABSI":      { "measure_family": "HAI_1", "sir": 0.377, "compared_to_national": "Better than the National Benchmark", "numerator": 28, "predicted": 74.245, "device_days": 69774, "ci": [0.256, 0.538] },
    "CAUTI":       { "measure_family": "HAI_2", "sir": 0.676, "compared_to_national": "Better than the National Benchmark", "numerator": 50, "predicted": 73.964, "device_days": 51687, "ci": [0.507, 0.884] },
    "SSI_colon":   { "measure_family": "HAI_3", "sir": 0.822, "compared_to_national": "No Different than National Benchmark", "ci": [0.578, 1.135] },
    "SSI_hyst":    { "measure_family": "HAI_4", "sir": null,  "compared_to_national": "No Different than National Benchmark" },
    "MRSA":        { "measure_family": "HAI_5", "sir": null,  "compared_to_national": null },
    "C_diff":      { "measure_family": "HAI_6", "sir": null,  "compared_to_national": null }
  },
  "ed_timeliness": {
    "volume_bucket": "very high",
    "median_minutes_in_ed_general":          { "measure_id": "OP_18b", "score": 245, "national_median": 161, "state_median": 130 },
    "median_minutes_in_ed_all_patients":     { "measure_id": "OP_18a", "score": 252 },
    "median_minutes_in_ed_psychiatric":      { "measure_id": "OP_18c", "score": 310 },
    "percent_left_without_being_seen":       { "measure_id": "OP_22",  "score": 3 },
    "percent_head_ct_results_within_45_min": { "measure_id": "OP_23",  "score": 63 }
  },
  "data_currency": {
    "general_info_window": "2024-07-01_to_2025-06-30",
    "complications_deaths_window": "2024-07-01_to_2025-06-30",
    "hai_window": "2024-07-01_to_2025-06-30",
    "hcahps_window": "2024-07-01_to_2025-06-30",
    "fetched_at": "<iso8601-utc>"
  }
}

For compare_to: ["360180", "Cleveland Clinic Florida + FL"] the top level becomes:

{
  "hospitals": [ { "ccn": "240010", ... }, { "ccn": "360180", ... }, { "ccn": "100247", ... } ],
  "benchmarks": {
    "national": {
      "HAI_1_SIR": { "score": 1.0 },
      "MORT_30_AMI": { "national_rate": "12.6" },
      "OP_18b":     { "score": "161" },
      "H_STAR_RATING": { "hcahps_answer_percent": "3-star national distribution baseline" }
    },
    "state": {
      "MN": { "HAI_1_SIR": { "score": 0.563 }, "OP_18b": { "score": 130 } },
      "OH": { "HAI_1_SIR": { "score": 0.812 }, "OP_18b": { "score": 152 } },
      "FL": { "HAI_1_SIR": { "score": 1.057 }, "OP_18b": { "score": 178 } }
    }
  },
  "fetched_at": "<iso8601-utc>"
}

When the requested hospital is not found in the PDC (CCN doesn't exist or is for a non-Hospital provider type — nursing home, dialysis facility, home health agency), return:

{ "success": false, "reason": "ccn_not_a_hospital", "looked_up": "240010", "available_provider_types": ["NursingHome", "HomeHealth"] }

When the input was a hospital name that returned multiple matches in the target state:

{ "success": false, "reason": "ambiguous_name", "matches": [
  { "ccn": "240010", "name": "MAYO CLINIC HOSPITAL ROCHESTER", "city": "ROCHESTER", "state": "MN" },
  { "ccn": "240018", "name": "MAYO CLINIC HEALTH SYSTEM IN RED WING", "city": "RED WING", "state": "MN" },
  { "ccn": "240043", "name": "MAYO CLINIC HEALTH SYSTEM - ALBERT LEA AND AUSTIN", "city": "ALBERT LEA", "state": "MN" }
] }

When the hospital exists but is not publicly rated (critical access, brand-new, VA — hospital_overall_rating: "Not Available"):

{ "ccn": "241333", "name": "MAYO CLINIC HEALTH SYSTEM

how to use get-hospital-rating

How to use get-hospital-rating on Cursor

AI-first code editor with Composer

Prerequisites

Before installing skills in Cursor, ensure your development environment meets these requirements:

›Cursor installed and configured on your development machine
›Node.js version 16.0+ with npm package manager (verify with node --version)
›Active project directory or workspace where you want to add get-hospital-rating

Execute installation command

Execute the skills CLI command in your project's root directory to begin installation:

$browse install medicare.gov/get-hospital-rating-03perc

The skills CLI fetches get-hospital-rating from GitHub repository medicare.gov/get-hospital-rating-03perc and configures it for Cursor.

Select Cursor when prompted

The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:

◆ Which agents do you want to install to?

│

│ ── Universal (.agents/skills) ── always included ────

│ • Amp

│ • Antigravity

│ • Cline

│ • Codex

│ ●Cursor(selected)

│ • Cursor

│ • Windsurf

Verify installation

Confirm successful installation by checking the skill directory location:

.cursor/skills/get-hospital-rating

Reload or restart Cursor to activate get-hospital-rating. Access the skill through slash commands (e.g., /get-hospital-rating) or your agent's skill management interface.

⚠

Security & Verification Notice

We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.

Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.

Additional Resources

›View source code on GitHub ›Skills CLI documentation ›Learn more about Cursor ›What are agent skills?

List & Monetize Your Skill

Submit your Claude Code skill and start earning

GET_STARTED →

Use Cases▌

Task Automation & Efficiency

Automate repetitive workflows and reduce manual effort

Example

Generate reports, summarize documents, draft communications

✓

Save 3-5 hours per week on routine tasks

Knowledge Enhancement

Learn new skills, understand complex topics, get expert guidance

Example

Explain concepts, provide examples, suggest learning resources

✓

Accelerate learning and skill development by 2x

Quality Improvement

Enhance output quality through reviews, suggestions, and refinements

Example

Review drafts, suggest improvements, catch errors

✓

Improve work quality by 30-40% with less effort

Implementation Guide▌

Prerequisites

›Claude Desktop or compatible AI client with skill support
›Clear understanding of task or problem to solve
›Willingness to iterate and refine outputs

Time Estimate

15-45 minutes depending on use case complexity

Installation Steps

1.Install skill using provided installation command
2.Test with simple use case relevant to your work
3.Evaluate output quality and relevance
4.Iterate on prompts to improve results
5.Integrate into regular workflow if valuable

Common Pitfalls

⚠Expecting perfect results without iteration
⚠Not providing enough context in prompts
⚠Using skill for tasks outside its intended scope
⚠Accepting outputs without review and validation

Best Practices▌

✓ Do

+Start with clear, specific prompts
+Provide relevant context and constraints
+Review and refine all outputs before using
+Iterate to improve output quality
+Document successful prompt patterns

✗ Don't

−Don't use without understanding skill limitations
−Don't skip validation of outputs
−Don't share sensitive information in prompts
−Don't expect skill to replace human judgment

💡 Pro Tips

★Be specific about desired format and style
★Ask for multiple options to choose from
★Request explanations to understand reasoning
★Combine AI efficiency with human expertise

When to Use This▌

✓ Use When

Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.

✗ Avoid When

Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.

Learning Path▌

1Familiarize yourself with skill capabilities and limitations
2Start with low-risk, non-critical tasks
3Progress to more complex and valuable use cases
4Build expertise through regular use and experimentation

Discussion

Product Hunt–style comments (not star reviews)

No comments yet — start the thread.

general reviews

Ratings

4.5★★★★★64 reviews

★★★★★Carlos Flores· Dec 28, 2024
Useful defaults in get-hospital-rating — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
★★★★★Amelia White· Dec 20, 2024
We added get-hospital-rating from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
★★★★★Aisha Chawla· Dec 12, 2024
get-hospital-rating reduced setup friction for our internal harness; good balance of opinion and flexibility.
★★★★★Carlos Shah· Dec 8, 2024
Registry listing for get-hospital-rating matched our evaluation — installs cleanly and behaves as described in the markdown.
★★★★★Chen Okafor· Dec 8, 2024
Keeps context tight: get-hospital-rating is the kind of skill you can hand to a new teammate without a long onboarding doc.
★★★★★Chaitanya Patil· Dec 4, 2024
Keeps context tight: get-hospital-rating is the kind of skill you can hand to a new teammate without a long onboarding doc.
★★★★★Carlos Sethi· Dec 4, 2024
Registry listing for get-hospital-rating matched our evaluation — installs cleanly and behaves as described in the markdown.
★★★★★Maya Garcia· Dec 4, 2024
get-hospital-rating fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
★★★★★Maya Thomas· Nov 27, 2024
get-hospital-rating fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
★★★★★Naina Johnson· Nov 27, 2024
Useful defaults in get-hospital-rating — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

showing 1-10 of 64

1 / 7

get-hospital-rating▌

Medicare.gov Hospital Quality Rating

Purpose

When to Use

Workflow

1. Resolve the input to a CCN

2. Pull the per-CCN datasets

3. Construct the canonical Care Compare URL

4. Assemble the unified output

5. Handle compare_to

6. Browser fallback (only when the user needs the rendered Care Compare card)

Site-Specific Gotchas

Expected Output

How to use get-hospital-rating on Cursor

Prerequisites

Execute installation command

Select Cursor when prompted

Verify installation

Security & Verification Notice

Additional Resources

List & Monetize Your Skill

Use Cases▌

Task Automation & Efficiency

Knowledge Enhancement

Quality Improvement

Implementation Guide▌

Prerequisites

Time Estimate

Installation Steps

Common Pitfalls

Best Practices▌

✓ Do

✗ Don't

💡 Pro Tips

When to Use This▌

✓ Use When

✗ Avoid When

Learning Path▌

Discussion

Ratings

5. Handle `compare_to`