Skills for healthcare.
6 skills
This skill extracts the fields you define from clinical notes and ties each value to the exact text it came from. Missing values stay empty instead of being guessed. Output can feed chart abstraction, a patient registry, or a research cohort, and it can be exported as FHIR.
This skill reads encounter notes and operative reports and picks CPT codes and HCPCS Level II codes for the procedures in them. It lists each billable service, looks up codes with lookup tools, and outputs codes ready for a claim.
This skill reads a clinical note and picks the billable ICD-10-CM diagnosis codes for a claim. It decides which diagnoses should be billed, codes each one as specifically as the note allows, and looks up the exact code through an ICD-10 connector before a final check.
This skill is a reference for building healthcare REST endpoints on FHIR R4, such as Patient, Observation, Encounter, and MedicationRequest. It covers mandatory fields, allowed enum values, HTTP responses and errors, and coding systems like LOINC, SNOMED, RxNorm, and ICD-10. SMART on FHIR authorization, Bundles, transactions, and paged search are included.
This skill writes a clinical trial protocol for a drug or medical device. It first researches similar trials through a clinical trials MCP server and checks the FDA pathway, then fills a protocol template step by step. A research-only mode returns the summary without the full protocol.
This skill handles payer-side review of a prior authorization request. It takes in the request and clinical notes, checks them against coverage policy through connected MCP servers, and drafts a decision and notice. It requires those servers to be set up first.
An agent skill is a portable pack of instructions that gives an agent specialized know-how for a task. In the open Agent Skills format (from Anthropic, now widely adopted), that pack is a folder with a SKILL.md file and optional scripts or references the agent can load when needed.
SKILL.md is the required main file in a skill folder. It starts with simple metadata (name and description) plus the instructions. Agents use the metadata to decide when a skill applies, then read the full file — and any linked files — only when the task needs them.
Open the listing and follow the source link — usually a GitHub SKILL.md. Install with your agent’s skill flow, or add the repo the way that product documents. When this site shows the skill text, Copy is on the page.
A prompt is paste-in text for one chat turn (or a short thread). A skill is a reusable file pack an agent can discover and load across a task, sometimes with code attached. Prompts live in the prompt directory; skills usually live on GitHub and we link out.
Each skill uses one sitewide category — the same set as the rest of the directory (Coding agent, Marketing, Document intelligence, and so on). Hops filter to categories that already have skills.
Yes. Submit with a public GitHub SKILL.md URL, or attach a skill as part of a method on a use case. An editor reviews it before it appears here.