New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Hospital Margin Forensics

by hh-health-AI in hh-health-AI/healthcare-equity

This skill should be used when the user asks about "hospital margins", "cost reports", "HCRIS", "payer mix", "occupancy", "uncompensated care", "hospital capex capacity", "will hospitals buy", or…

MITAuto-check passedAI & LLM Engineering

Install Hospital Margin Forensics

skills CLI
$ npx skills add hh-health-AI/healthcare-equity --skill hospital-margin-forensics -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hh-health-AI/healthcare-equity hospital-margin-forensics --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hh-health-AI/healthcare-equity.git skills-src && mkdir -p .claude/skills && cp -r skills-src/modules/provider-economics/skills/hospital-margin-forensics .claude/skills/hospital-margin-forensics && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
hospital-margin-forensics
GitHub stars
101
Token cost
~837 tokens
SKILL.md length
409 words
Files
2 (incl. references)
Skills in repo
72
Repo updated
First seen
Licence
MIT

At a glance

This skill should be used when the user asks about "hospital margins", "cost reports", "HCRIS", "payer mix", "occupancy", "uncompensated care", "hospital capex capacity", "will hospitals buy", or…

  • Works in 8 steps: Define the facility set. For a listed… → Pull and extract… → Compute the panel, per facility per… → …
  • Asks about hospital margins
  • SKILL.md covers Workflow and Not-automatic
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Hospital Margin Forensics is an agent skill from hh-health-AI/healthcare-equity. This skill should be used when the user asks about "hospital margins", "cost reports", "HCRIS", "payer mix", "occupancy", "uncompensated care", "hospital capex capacity", "will hospitals buy", or wants a facility-level read on provider financial health as a cross-read for suppliers. Anchors prompt-library ID SUB-SVC-01.

Its SKILL.md is about 840 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/hcris-codemap.md`).

It sits in AI & LLM Engineering, covering Prompt engineering. The repository describes itself as: Synthesis engine for buy-side healthcare equity research. The licence is MIT.

When your agent uses it

  • Asks about hospital margins
  • Uncompensated care
  • Hospital capex capacity
  • Will hospitals buy

Example prompts

  • “hospital margins”
  • “cost reports”
  • “payer mix”
  • “/hospital-margin-forensics”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Define the facility set. For a listed operator, the set is its CCNs — build it
  2. Pull and extract (scripts/hcris_extract.py). HCRIS ships as three files per
  3. Compute the panel, per facility per fiscal year
  4. Handle the vintage. Mark each report as-submitted or settled, and never mix the
  5. Aggregate carefully. System-level conclusions require rolling up CCNs to the
  6. Cross-read to the supplier thesis. The chain is: hospital operating margin →
  7. Test against the listed operator's own numbers. If a listed operator's reported
  8. Emit the brief.

What it can do on your machine

Read from SKILL.md and the folder at commit 6c7bda8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hospital Margin Forensics loads about 837 tokens when it runs, and up to ~1.6k if it reads all its reference files. Until then it costs about 87 tokens; SKILL.md has 409 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~87
When it runs · the whole SKILL.md, loaded when a task matches
~837
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from hh-health-AI/healthcare-equity at commit 6c7bda8, republished under its MIT licence (© hh-health-AI). 409 words, ~837 tokens.

Download SKILL.mdSave it as .claude/skills/hospital-margin-forensics/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
hospital-margin-forensics
description
This skill should be used when the user asks about "hospital margins", "cost reports", "HCRIS", "payer mix", "occupancy", "uncompensated care", "hospital capex capacity", "will hospitals buy", or wants a facility-level read on provider financial health as a cross-read for suppliers. Anchors prompt-library ID SUB-SVC-01.
metadata.version
0.1.0
metadata.layer
Financial

Hospital margin forensics

Extract facility-level operating economics from Medicare cost reports and turn them into either an operator view or a supplier-demand cross-read.

Workflow

  1. Define the facility set. For a listed operator, the set is its CCNs — build it from the operator's own facility list and the CMS provider-of-services file. For a supplier cross-read, the set is the facility type that buys the product (academic medical centres, community hospitals, critical-access, IDNs in named states).
  2. Pull and extract (scripts/hcris_extract.py). HCRIS ships as three files per report — RPT (report header), NMRC (numeric values), ALPHA (text) — keyed by worksheet, line and column. Use references/hcris-codemap.md to get the lines; without the codemap the numeric file is unreadable.
  3. Compute the panel, per facility per fiscal year:
    • Total margin and operating margin (exclude investment income — this is the single most common error, and in a strong equity market it turns loss-making hospitals into profitable ones on paper).
    • Payer mix by discharges and by revenue: Medicare, Medicaid, managed care, other.
    • Occupancy, average length of stay, case-mix index.
    • Uncompensated care and charity care (Worksheet S-10).
    • Capital cost as a share of total cost, and the age of plant — the direct capex capacity read that a medtech thesis needs.
  4. Handle the vintage. Mark each report as-submitted or settled, and never mix the two in a trend. Report the fiscal-year end, not the posting date.
  5. Aggregate carefully. System-level conclusions require rolling up CCNs to the parent, which HCRIS does not do for you. Ownership changes mid-year make this genuinely difficult; state your roll-up method.
  6. Cross-read to the supplier thesis. The chain is: hospital operating margin → capital budget → equipment replacement cycle → supplier order book. An ageing plant with improving margin is the bullish medtech setup; a young plant with deteriorating margin is the bearish one. Say which you found and in which facility segment.
  7. Test against the listed operator's own numbers. If a listed operator's reported margin diverges materially from the sum of its facilities' cost reports, that is a finding — usually explained by corporate allocation, non-hospital segments or timing, but occasionally by something else. Hand it to sec-forensics.
  8. Emit the brief.
Show full SKILL.md (50 more words)Show less

Not-automatic

Cost-report margins do not license a quarterly earnings conclusion for a listed operator — the lag is too long and the accounting basis differs from GAAP. They license a structural claim about the direction of provider financial health.

Framework anchor: Cleverley, Essentials of Health Care Finance. Reference: references/hcris-codemap.md. Contract: ../../references/evidence-brief.md.

© hh-health-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in modules/provider-economics/skills/hospital-margin-forensics of hh-health-AI/healthcare-equity.

  • SKILL.md
  • references/hcris-codemap.md

Open the folder on GitHubat commit 6c7bda8

Compare with similar skills

Hospital Margin Forensics next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Hospital Margin Forensics compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hospital Margin Forensics this skillhh-health-AI/healthcare-equity101—~837Automated safety check: PassMIT
Agent Prompt Quality Barmastra-ai/mastra29k—~2kAutomated safety check: PassCustom licence
Prompt Engineer Toolkitborghei/Claude-Skills891—~1.6kAutomated safety check: PassMIT
Prompt LabMathews-Tom/armory329—~2.1kAutomated safety check: PassMIT
Module 1brevdev/workshop-build-an-agent146—~2.7kAutomated safety check: PassApache-2.0
Module 1brevdev/workshop-build-an-agent146—~2.7kAutomated safety check: PassApache-2.0

Similar skills

  • Agent Prompt Quality Bar

    mastra-ai/mastra

    Universal quality bar and final audit rubric for any agent system prompt.

    29k GitHub stars~2k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Prompt Engineer Toolkit

    borghei/Claude-Skills

    Prompt engineering frameworks for building, testing, versioning, and evaluating prompts: chain-of-thought, few-shot, regression testing, and rubrics.

    891 GitHub stars~1.6k tokensUpdated 4 days ago
    AI & LLM EngineeringAuto-check passed

  • Prompt Lab

    Mathews-Tom/armory

    LLM prompt engineering: analyzes failure modes, generates variants (direct, few-shot, CoT), designs rubrics, produces test suites.

    329 GitHub stars~2.1k tokensUpdated 5 days ago
    AI & LLM EngineeringAuto-check passed

  • Module 1

    brevdev/workshop-build-an-agent

    This skill should be used when a learner is working through Module 1 ("Build an Agent") of the Build-an-Agent workshop and wants help understanding the concepts, notebooks, or code — e.g.

    146 GitHub stars~2.7k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed

  • Module 1

    brevdev/workshop-build-an-agent

    This skill should be used when a learner is working through Module 1 ("Build an Agent") of the Build-an-Agent workshop and wants help understanding the concepts, notebooks, or code — e.g.

    146 GitHub stars~2.7k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed

  • Dspy Bootstrap Fewshot

    OmidZamani/dspy-skills

    A skill your agent uses for BootstrapFewShot, bootstrapped demonstrations, teacher-model demos, and low-data DSPy prompt optimization.

    123 GitHub stars~1.3k tokensUpdated 3 mo ago
    AI & LLM EngineeringAuto-check passed

More from hh-health-AI/healthcare-equity

All 72 skills in this repo

  • Adcom Label

    hh-health-AI/healthcare-equity

    This skill should be used when the user says "prep the AdCom for [asset]", "what will the advisory committee vote", "analyze the approved label", "label delta vs expectations", or within 48 hours of…

    101 GitHub stars~1.1k tokensUpdated 3 days ago
    Auto-check passed

  • Biomedical Claim Checker

    hh-health-AI/healthcare-equity

    A skill your agent uses to audit whether medical or scientific claims are supported by their citations, verify references, assess AI-generated biomedical text or identify overstatement in a press…

    101 GitHub stars~741 tokensUpdated 3 days ago
    Auto-check passed

  • Biomedical Claim Checker

    hh-health-AI/healthcare-equity

    A skill your agent uses when checking whether a medical or scientific claim is supported by its cited paper, verifying references, auditing an AI-generated biomedical answer or examining…

    101 GitHub stars~816 tokensUpdated 3 days ago
    Auto-check passed

  • Biosimilar Erosion

    hh-health-AI/healthcare-equity

    This skill should be used when the user asks about "biosimilar erosion", "Purple Book", "biologic exclusivity", "interchangeability", "how fast will [biologic] erode", "erosion curve", or needs the…

    101 GitHub stars~753 tokensUpdated 3 days ago
    Auto-check passed

  • Biotech Catalyst Radar

    hh-health-AI/healthcare-equity

    A skill your agent uses for a defined biotech trial watchlist, registry-version comparisons, catalyst calendars or changed enrollment, status and completion estimates.

    101 GitHub stars~760 tokensUpdated 3 days ago
    Auto-check passed

  • Biotech Catalyst Radar

    hh-health-AI/healthcare-equity

    A skill your agent uses to monitor a defined biotech trial watchlist, compare registry versions, build a catalyst calendar or explain changed enrollment, status or completion estimates.

    101 GitHub stars~846 tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Hospital Margin Forensics

What does Hospital Margin Forensics do?

This skill should be used when the user asks about "hospital margins", "cost reports", "HCRIS", "payer mix", "occupancy", "uncompensated care", "hospital capex capacity", "will hospitals buy", or…. Hospital Margin Forensics is an agent skill from hh-health-AI/healthcare-equity. This skill should be used when the user asks about "hospital margins", "cost reports", "HCRIS", "payer mix", "occupancy", "uncompensated care", "hospital capex capacity", "will hospitals buy", or wants a facility-level read on provider financial health as a cross-read for suppliers.

When should I use Hospital Margin Forensics?

Hospital Margin Forensics fits situations like: asks about hospital margins; uncompensated care; hospital capex capacity; will hospitals buy.

How do I install Hospital Margin Forensics in Claude Code?

Run `npx skills add hh-health-AI/healthcare-equity --skill hospital-margin-forensics -a claude-code`. Or copy the skill folder (modules/provider-economics/skills/hospital-margin-forensics in hh-health-AI/healthcare-equity) into .claude/skills/hospital-margin-forensics in your project. Claude Code loads it when a task matches its description.

How do I install Hospital Margin Forensics in Codex?

Run `npx skills add hh-health-AI/healthcare-equity --skill hospital-margin-forensics -a codex`. Or copy the skill folder (modules/provider-economics/skills/hospital-margin-forensics in hh-health-AI/healthcare-equity) into .agents/skills/hospital-margin-forensics in your project. Codex loads it when a task matches its description.

Can I use Hospital Margin Forensics in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hh-health-AI/healthcare-equity --skill hospital-margin-forensics -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hospital-margin-forensics, .gemini/skills/hospital-margin-forensics, .github/skills/hospital-margin-forensics and .opencode/skills/hospital-margin-forensics in your project.

What does Hospital Margin Forensics need to run?

SKILL.md names no scripts, command-line tools or credentials: Hospital Margin Forensics is instructions for the agent only.

Does Hospital Margin Forensics access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Hospital Margin Forensics safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Hospital Margin Forensics use?

Hospital Margin Forensics is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hospital Margin Forensics use?

About 837 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 758 tokens, read only when the agent opens those files.

What are the alternatives to Hospital Margin Forensics?

Skills that share tags, products or a category with Hospital Margin Forensics: Agent Prompt Quality Bar (mastra-ai/mastra, 29k stars), Prompt Engineer Toolkit (borghei/Claude-Skills, 891 stars), Prompt Lab (Mathews-Tom/armory, 329 stars) and Module 1 (brevdev/workshop-build-an-agent, 146 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hospital Margin Forensics?

hh-health-AI (a GitHub user) maintains it in hh-health-AI/healthcare-equity, which has 101 GitHub stars. The repository holds 72 skills in this directory. The repository was last updated on October 8, 2026.

Source: hh-health-AI/healthcare-equity on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.