Agent skill

Sdud Trx Proxy

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

This skill should be used when the user asks for an "open TRx proxy", "SDUD", "Medicaid utilisation", "script trend without IQVIA", "is the launch tracking", "prescription volume for [brand]", or…

MITAuto-check passedAI & LLM Engineering

Install Sdud Trx Proxy

skills CLI
$ npx skills add hh-health-AI/healthcare-equity --skill sdud-trx-proxy -a claude-code

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

GitHub CLI
$ gh skill install hh-health-AI/healthcare-equity sdud-trx-proxy --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/rx-utilization/skills/sdud-trx-proxy .claude/skills/sdud-trx-proxy && 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
sdud-trx-proxy
GitHub stars
101
Token cost
~940 tokens
SKILL.md length
481 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 for an "open TRx proxy", "SDUD", "Medicaid utilisation", "script trend without IQVIA", "is the launch tracking", "prescription volume for [brand]", or…

  • Works in 7 steps: Resolve the product to NDCs. A brand… → Pull the series. Run… → Handle suppression before computing… → …
  • Asks for an open TRx proxy
  • SKILL.md covers Workflow, Reading the series, Not-automatic (carry into the… and Chaining
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Sdud Trx Proxy is an agent skill from hh-health-AI/healthcare-equity. This skill should be used when the user asks for an "open TRx proxy", "SDUD", "Medicaid utilisation", "script trend without IQVIA", "is the launch tracking", "prescription volume for [brand]", or wants to validate or invalidate a launch trajectory, biosimilar erosion, or share shift using free CMS data. Also triggers on prompt-library IDs SUB-PHA-03, SUB-PHA-04, SUB-PHA-05.

Its SKILL.md is about 940 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/sdud-mechanics.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 for an open TRx proxy
  • Medicaid utilisation
  • Script trend without IQVIA
  • Is the launch tracking

Example prompts

  • “open TRx proxy”
  • “Medicaid utilisation”
  • “script trend without IQVIA”
  • “/sdud-trx-proxy”

Workflow steps

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

  1. Resolve the product to NDCs. A brand maps to many NDC-11s (strengths, pack
  2. Pull the series. Run scripts/sdud_query.py for each NDC across the quarters
  3. Handle suppression before computing anything. Count state-quarter cells
  4. Separate price from volume. Total reimbursed ÷ units gives a Medicaid $/unit
  5. Test the payer-mix assumption. Estimate the brand's Medicaid share from the
  6. Cross-read against Part D. If the drug has meaningful Medicare exposure, run
  7. 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

Sdud Trx Proxy loads about 940 tokens when it runs, and up to ~1.6k if it reads all its reference files. Until then it costs about 98 tokens; SKILL.md has 481 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~98
When it runs · the whole SKILL.md, loaded when a task matches
~940
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). 481 words, ~940 tokens.

Download SKILL.mdSave it as .claude/skills/sdud-trx-proxy/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
sdud-trx-proxy
description
This skill should be used when the user asks for an "open TRx proxy", "SDUD", "Medicaid utilisation", "script trend without IQVIA", "is the launch tracking", "prescription volume for [brand]", or wants to validate or invalidate a launch trajectory, biosimilar erosion, or share shift using free CMS data. Also triggers on prompt-library IDs SUB-PHA-03, SUB-PHA-04, SUB-PHA-05.
metadata.version
0.1.0
metadata.layer
Commercial

SDUD TRx proxy

Build an open prescription-volume series for a brand or molecule from Medicaid State Drug Utilization Data, then state honestly what it can and cannot support.

Workflow

  1. Resolve the product to NDCs. A brand maps to many NDC-11s (strengths, pack sizes, authorised generics). Pull the NDC set from openFDA /drug/ndc.json by brand name and labeller, or from the FDA NDC Directory. Record the labeller code — an authorised generic under a different labeller is a different commercial event and must be tracked as its own series, not folded into the brand.
  2. Pull the series. Run scripts/sdud_query.py for each NDC across the quarters in scope. Aggregate prescriptions, units and total reimbursed by quarter, keeping state granularity in the working table.
  3. Handle suppression before computing anything. Count state-quarter cells returned as suppressed. If suppression exceeds ~20% of contributing states in the earliest quarter of the window, do not report a growth rate off the national sum — compute the trend on a balanced panel of states with continuous non-suppressed history and report it as such.
  4. Separate price from volume. Total reimbursed ÷ units gives a Medicaid $/unit that reflects pre-rebate reimbursement. It is not net price. Track units for volume and treat dollars as a separate, weaker series.
  5. Test the payer-mix assumption. Estimate the brand's Medicaid share from the label's indication and the disease's payer skew. Where the company discloses a channel split in filings or at conferences, use it and cite it. Where it does not, say the assumption is unanchored and cap confidence at 0.5.
  6. Cross-read against Part D. If the drug has meaningful Medicare exposure, run partd-prescriber-share and reconcile direction. Two proxies agreeing on direction is materially stronger evidence than either alone; disagreeing is a finding in itself.
  7. Emit the brief.
Show full SKILL.md (183 more words)Show less

Reading the series

  • Launch curves. Medicaid uptake typically lags commercial by one to two quarters because of state formulary and PA processes. A flat Medicaid series in launch quarter two is weak evidence of a failing launch; a flat series in quarter six is strong evidence.
  • Biosimilar and generic entry. Watch the units split between the reference labeller and entrants, not the aggregate. Medicaid erosion tends to run faster than commercial because state preferred-drug lists switch mechanically.
  • Divergence between prescriptions and units usually means a pack-size or dosing change, not a demand change. Check the NDC set before writing it up as volume.
  • A step change confined to one or two states is a formulary or PDL event, not a demand event. Name the state.

Not-automatic (carry into the brief)

A SDUD move does not license a national TRx conclusion, a net-revenue conclusion, or a share conclusion against competitors with different payer mixes.

Chaining

a procedure-exposure engine for the denominator · a reimbursement engine where an MFP date sits in the window · your view layer → model-valuation for the revenue line.

Reference: references/sdud-mechanics.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/rx-utilization/skills/sdud-trx-proxy of hh-health-AI/healthcare-equity.

  • SKILL.md
  • references/sdud-mechanics.md

Open the folder on GitHubat commit 6c7bda8

Compare with similar skills

Sdud Trx Proxy 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.

Sdud Trx Proxy compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sdud Trx Proxy this skillhh-health-AI/healthcare-equity101—~940Automated safety check: PassMIT
Prompt Improverseverity1/claude-code-prompt-improver1.9k1 repos~1.7kAutomated safety check: PassMIT
Prompt Engineering Patternsynulihao/AgentSkillOS61814 repos~1.7kAutomated safety check: PassNone
Patch CreationPiebald-AI/tweakcc2.5k—~1.6kAutomated safety check: PassMIT
Senior Prompt Engineermaslennikov-ig/claude-code-orchestrator-kit2603 repos~1.4kAutomated safety check: PassCustom licence
Codex Fable5baskduf/FableCodex437—~1.6kAutomated safety check: PassAGPL-3.0

Similar skills

  • Prompt Improver

    severity1/claude-code-prompt-improver

    This skill enriches vague prompts with targeted research and clarification before execution.

    1.9k GitHub starsUsed in 1 repo~1.7k tokens
    AI & LLM EngineeringAuto-check passed
  • Prompt Engineering Patterns

    ynulihao/AgentSkillOS

    Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production.

    618 GitHub starsUsed in 14 repos~1.7k tokens
    AI & LLM EngineeringAuto-check passed
  • Patch Creation

    Piebald-AI/tweakcc

    Create and register new patches for tweakcc. An agent skill from Piebald-AI/tweakcc.

    2.5k GitHub stars~1.6k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Senior Prompt Engineer

    maslennikov-ig/claude-code-orchestrator-kit

    Provides reference guides and Python scripts for prompt optimization, RAG evaluation, and agent orchestration when building or tuning LLM systems.

    260 GitHub starsUsed in 3 repos~1.4k tokens
    AI & LLM EngineeringAuto-check passed
  • Codex Fable5

    baskduf/FableCodex

    Apply a Claude Fable 5 inspired operating style inside Codex.

    437 GitHub stars~1.6k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed
  • Reference for designing and tuning production LLM prompts: few-shot examples, chain-of-thought, structured outputs, templates and system prompts.

    40k GitHub stars~1.3k tokensUpdated 6 days 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

Questions about Sdud Trx Proxy

What does Sdud Trx Proxy do?

This skill should be used when the user asks for an "open TRx proxy", "SDUD", "Medicaid utilisation", "script trend without IQVIA", "is the launch tracking", "prescription volume for [brand]", or…. Sdud Trx Proxy is an agent skill from hh-health-AI/healthcare-equity. This skill should be used when the user asks for an "open TRx proxy", "SDUD", "Medicaid utilisation", "script trend without IQVIA", "is the launch tracking", "prescription volume for [brand]", or wants to validate or invalidate a launch trajectory, biosimilar erosion, or share shift using free CMS data.

When should I use Sdud Trx Proxy?

Sdud Trx Proxy fits situations like: asks for an open TRx proxy; medicaid utilisation; script trend without IQVIA; is the launch tracking.

How do I install Sdud Trx Proxy in Claude Code?

Run `npx skills add hh-health-AI/healthcare-equity --skill sdud-trx-proxy -a claude-code`. Or copy the skill folder (modules/rx-utilization/skills/sdud-trx-proxy in hh-health-AI/healthcare-equity) into .claude/skills/sdud-trx-proxy in your project. Claude Code loads it when a task matches its description.

How do I install Sdud Trx Proxy in Codex?

Run `npx skills add hh-health-AI/healthcare-equity --skill sdud-trx-proxy -a codex`. Or copy the skill folder (modules/rx-utilization/skills/sdud-trx-proxy in hh-health-AI/healthcare-equity) into .agents/skills/sdud-trx-proxy in your project. Codex loads it when a task matches its description.

Can I use Sdud Trx Proxy 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 sdud-trx-proxy -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sdud-trx-proxy, .gemini/skills/sdud-trx-proxy, .github/skills/sdud-trx-proxy and .opencode/skills/sdud-trx-proxy in your project.

What does Sdud Trx Proxy need to run?

SKILL.md names no scripts, command-line tools or credentials: Sdud Trx Proxy is instructions for the agent only.

Does Sdud Trx Proxy 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 Sdud Trx Proxy 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 Sdud Trx Proxy use?

Sdud Trx Proxy 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 Sdud Trx Proxy use?

About 940 tokens (SKILL.md is roughly 3.8k 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 685 tokens, read only when the agent opens those files.

What are the alternatives to Sdud Trx Proxy?

Skills that share tags, products or a category with Sdud Trx Proxy: Prompt Improver (severity1/claude-code-prompt-improver, 1.9k stars), Prompt Engineering Patterns (ynulihao/AgentSkillOS, 618 stars), Patch Creation (Piebald-AI/tweakcc, 2.5k stars) and Senior Prompt Engineer (maslennikov-ig/claude-code-orchestrator-kit, 260 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sdud Trx Proxy?

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.