Assign CPT and HCPCS Level II procedure codes from clinical documentation the way a professional coder builds the claim. Use when users say "code this encounter for procedures", "what CPT codes apply", "assign HCPCS codes", "code this op note", or when turning visit notes or operative reports into claim-ready procedure codes.
npx skills add https://github.com/anthropics/healthcare --skill procedure-coding
Turn one encounter's clinical documentation into the procedure codes a professional coder would submit on the claim: CPT (five digits, or four digits + F for Category II tracking codes) for physician services, procedures, and quality measures, plus HCPCS Level II (letter + four digits) for supplies, devices, and non-physician services CPT does not cover.
Read the documentation and list each distinct billable service performed at this encounter. Work by category:
Leave off the list: services planned but not performed, results referenced from a prior date, and items already bundled into a procedure's global package.
HCPCS Level II codes (one letter + four digits) cover items CPT does not. Check the documentation for these specifically:
Do not output quality-reporting G-codes (G8-/G9- range) or non-covered-item codes. These report participation in a quality program or a coverage determination; whether they belong on the claim depends on the practice's program enrollment and the payer, not on the clinical documentation. A data point appearing in the note (BMI in vitals, medication list reviewed, tobacco status in social history) is not by itself a reason to report the corresponding quality code.
Category II tracking codes are reported when the encounter is part of a quality-reporting workflow, not whenever the data point happens to appear in routine vitals or history. Output a ####F code only when the note shows the measure was deliberately captured for reporting: a quality-measure or health-maintenance section, measure-specific attestation language, or a structured screening result.
For every item on your abstracted list, search before you commit.
HCPCS Level II (letter + four digits): use search_codes for the supply, device, drug, or service name, passing the encounter date as as_of. Confirm with validate_code and the same as_of.
CPT (five-digit and ####F): if a CPT lookup connector is available (cpt_search_codes), use it with the service in plain words taken from the note and confirm with cpt_lookup_code. If no CPT connector is available, propose CPT codes from your knowledge of the current code set and state that they are pending verification against the user's licensed CPT reference — CPT descriptors are AMA-licensed and not bundled with this skill.
One or two searches per item is sufficient. If the right code is not in the first results, refine the query once with more specific wording from the note; then commit or move on. Do not loop on the same item.
After tool calls, output only the codes that belong on the claim, one per line, no other text. List each code once. Do not output J#### or Q#### codes. If a service you abstracted has no matching code in the lookup results and you cannot confidently propose one, omit it rather than guessing.
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API, opentrons-integration may be simpler.
Take anthropics/procedure-coding from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.