ohcnetwork

A brief description of what this skill does

Answers "how was this built?" about an interface. Give it a URL and name the thing you're curious about, and it reads the layers that produce the effect. Reads the whole frontend instead when you don't name a thing. From a screenshot it reconstructs rather…

Answers "which of these?" rather than "is this right?". Builds several genuinely different versions of one piece of UI behind a picker in the real page, so you can flip between them and promote the one that wins.

Use this skill alongside figma-use when the task involves translating an application page, view, or multi-section layout into Figma. Triggers: 'write to Figma', 'create in Figma from code', 'push page to Figma', 'take this app/page and build it in Figma',…

Build or update a professional-grade design system in Figma from a codebase. Use when the user wants to create variables/tokens, build component libraries, create individual components with proper variant sets and variable bindings, set up theming (light/dark…

This skill helps agents use Figma's use_figma MCP tool in the Slides context. Can be used alongside figma-use which has foundational context for using the use_figma tool.

Core frontend coding standards for HTML, CSS, and JavaScript/TypeScript. Use when writing, reviewing, or refactoring any HTML markup, CSS styles, or JS/TS code in this repo. Triggers on phrases like "follow our frontend guidelines", "review this component",…

Write, debug, and run Playwright E2E tests for CARE. Use when: creating new test files, fixing failing tests, adding test coverage, writing assertions, using test helpers, setting up test authentication, or running Playwright commands.

Reconstruct, from the code alone, what a CARE frontend (care_fe) diff does and what requirement it fulfills, and flag where the code fails to make that legible. The intent/legibility lens of /care-review (can run standalone). Use for "what does this change…

Full review of a CARE frontend (care_fe) diff via two parallel lens agents — (1) what problem the change solves + whether the code makes it legible, and (2) whether the approach is the simplest one or overengineered — condensed into one report. Use for…

Review a CARE frontend (care_fe) diff for approach quality — is this the simplest solution to the problem, or overengineered? Suggests simplifications, reuse of existing components/hooks/utils, and minimal refactors. The "approach" lens of /care-review (can…

Review raw SQL for the CARE analytics repo (care_analytics_sql) — hand-written Postgres queries that power Metabase dashboards and run directly against the CARE database's physical tables (emr_*, users_user). Use this whenever reviewing, writing, or debugging…

Reference for creating Jinja2 report templates in the CARE EMR system. Use when creating, editing, or debugging report templates. Covers available context variables, nested data, custom filters, globals, and template patterns.

Use when creating or updating a CONCEPT doc (the "What is…?" plain-language layer) for a Care EMR primitive in the Care docs site. Trigger when adding a concept page for a model/resource, when a Care change affects what a primitive IS or how access to it…

Use when creating or updating a FLOW doc (the "How do I…?" task layer) for the Care docs site. Trigger when adding a walkthrough for a user task (register a patient, close an encounter, dispense a medication), when a Care UI change alters the steps of an…

Use when creating or updating a REFERENCE doc (the "How is it built?" technical layer) for a Care EMR model/resource in the Care docs site. Trigger whenever a Care backend model, Pydantic resource spec, field, enum, choice, validation, or API schema changes —…