final

Clinic-safe frontend UI/UX audit, planning, and improvement workflow for this medical management app. Use when working on Admin, Doctor, Registrar, Cashier, Lab, dashboard, form, table, route-view, empty/loading/error, accessibility, responsive, visual consistency, or design-system tasks in the clinic frontend.

Project-specific master UI/UX skill for this clinic management frontend. Use for UI/UX audits, visual consistency, design-system convergence, role panels, dashboards, forms, tables, navigation, route views, empty/loading/error/forbidden states, accessibility, responsive behavior, browser visual QA, and safe frontend UI improvements across Admin, Doctor, Registrar, Cashier, Lab, Patient, queue, payment, EMR, and reporting workflows.

Security guidelines for writing secure code. Use when writing code, reviewing code for vulnerabilities, or asking about secure coding practices like 'check for SQL injection' or 'review security'. IMPORTANT: Always consult this skill when writing or reviewing any code that handles user input, authentication, file operations, database queries, network requests, cryptography, or infrastructure configuration (Terraform, Kubernetes, Docker, GitHub Actions) — even if the user doesn't explicitly mention security. Also use when users ask to 'review my code', 'check this for bugs', or 'is this safe'.

Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.

Project-specific workflow for designing or implementing BFF-lite screen/read-model endpoints inside the existing FastAPI backend after SSOT contract repair. Use for FastAPI UI endpoints, screen APIs, read-model services, Registrar workbench, Queue join, Queue board, Lab workbench, Admin audit/dashboard, Telegram admin dashboard, or questions about whether to add BFF-lite versus a separate BFF service.

Project-specific workflow for OpenAPI, API DTO, schema-shape, and frontend/backend contract review in this FastAPI + React clinic system. Use when adding or changing API endpoints, /api/v1/ui screen/read-model DTOs, generated OpenAPI shape, frontend API adapters, contract tests, or schema assertions.

Project-specific workflow for repairing frontend/backend contract leaks before adding BFF-lite endpoints. Use when React appears to make backend-owned decisions such as record_type branching, payment_status normalization, queue ordering, endpoint selection, role policy, EMR/lab/payment/Telegram action rules, or when a task says SSOT contract repair, frontend presentation-only, Registrar/Queue contract, or boundary cleanup.

Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.

Audit a landing page for WCAG alignment, keyboard access, semantic structure, and assistive-technology usability. Use before release and after major UI changes.

Audit a landing page for persuasion quality, trust signals, objection handling, and CTA progression. Use when optimizing toward signup, booking, or lead capture.

Draft and refine section copy, CTAs, and metadata for a landing page from the approved strategy. Use after strategy and before final UI polish or SEO review.

Audit a landing page for visual hierarchy, spacing, contrast, and component consistency. Use after implementation or after major visual changes.

Define design tokens, typography, spacing, and component rules for a landing page. Use before or alongside UI implementation to prevent inconsistent AI-generated design.

Normalize a raw landing-page request into a structured brief, brand constraints, and measurable success metrics. Use when starting a new landing, rebuilding positioning, or when the prompt is still vague and later agents need explicit assumptions.

Inspect and manage an AI Landing Factory run, refresh run-manifest.json, and move the run through intake, build, audit, and release. Use when coordinating multiple landing skills or checking readiness between stages.

Audit a landing page for Lighthouse score, Core Web Vitals, asset weight, and frontend delivery performance. Use before release and after major visual or dependency changes.

Assemble the final landing-page QA scorecard, preview summary, and release checklist from prior audit artifacts. Use when preparing a preview or explicit release candidate.

Audit a landing page for metadata, heading structure, schema coverage, and crawlability. Use before preview or release to keep search-facing quality measurable.

Shape landing-page positioning, offer structure, objections, and section strategy from the normalized brief. Use after intake and before copy or UI implementation.

Implement a landing page in the current frontend stack using the established brief, strategy, and design tokens. Use when building or fixing the actual landing UI.

Audit a landing page for user-flow clarity, CTA comprehension, friction, and cognitive load. Use after implementation or when conversion flow feels weak.

Inspect screenshots or live renders for layout regressions, alignment problems, and responsive breakpoints. Use after implementation and after visual fixes.

Use when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling authentication or OAuth, testing accessibility (axe-core), file uploads/downloads, date/time mocking, WebSockets, geolocation, permissions, multi-tab/popup flows, mobile/responsive layouts, touch gestures, GraphQL, error handling, offline mode, multi-user collaboration, third-party services (payments, email verification), console error monitoring, global setup/teardown, test annotations (skip, fixme, slow), test tags (@smoke, @fast, @critical, filtering with --grep), project dependencies, security testing (XSS, CSRF, auth), performance budgets (Web Vitals, Lighthouse), iframes, component testing, canvas/WebGL, service workers/PWA, test coverage, i18n/localization, Electron apps, or browser extension testing. Covers E2E, component, API, visual, accessibility, security, Electron, and extension testing.

Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.

Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.

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.

Vite build tool configuration, plugin API, SSR, and Vite 8 Rolldown migration. Use when working with Vite projects, vite.config.ts, Vite plugins, or building libraries/SSR apps with Vite.

Generate architecture guidelines for the project. Analyzes tech stack from DESCRIPTION.md, recommends an architecture pattern, and creates .ai-factory/ARCHITECTURE.md. Use when setting up project architecture, asking "which architecture", or after $aif setup.

Code quality guidelines and best practices for writing clean, maintainable code. Covers naming, structure, error handling, testing, and code review standards. Use when writing code, reviewing, refactoring, or asking "how should I name this", "best practice for", "clean code".

Analyze project and generate or enhance build automation file (Makefile, Taskfile.yml, Justfile, Magefile.go). If a build file already exists, improves it by adding missing targets and best practices. Use when user says "generate makefile", "create taskfile", "add justfile", "setup mage", or "build automation".

Generate CI/CD pipeline (GitHub Actions / GitLab CI) with linting, static analysis, tests, security. Use when user says "ci", "setup ci", "github actions", "gitlab ci", "pipeline".

Create conventional commit messages by analyzing staged changes. Generates semantic commit messages following the Conventional Commits specification. Use when user says "commit", "save changes", or "create commit".

Prepare and execute deployments with pre-flight checks, release notes generation, and CI/CD integration. NEVER auto-deploy. Use when user explicitly says "deploy", "release", or "go live".

Distill books, documents, folders, or URLs into compact, practical Agent Skills. Use when source material should become either one reusable skill package or a split set of focused skills, each with a concise SKILL.md plus detailed references and examples.

Analyze project and generate Docker configuration: Dockerfile (multi-stage dev/prod), compose.yml, compose.override.yml (dev), compose.production.yml (hardened), and .dockerignore. Includes production security audit. Use when user says "dockerize", "add docker", "docker compose", "containerize", or "setup docker".

Generate and maintain project documentation. Creates a lean README as a landing page with detailed docs pages split by topic in the configured docs directory. Use when user says "create docs", "write documentation", "update docs", "generate readme", or "document project".

Self-improve AI Factory skills based on project context, accumulated patches, and codebase patterns. Analyzes what went wrong, what works, and enhances skills to prevent future issues. Use when you want to make AI smarter for your project.

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

Fix a specific bug or problem in the codebase. Supports two modes - immediate fix or plan-first. Without arguments executes existing FIX_PLAN.md. Always suggests test coverage and adds logging. Use when user says "fix bug", "debug this", "something is broken", or pastes an error message.

Reliability gate for answers. Forces evidence-based reasoning, explicit uncertainty, and “insufficient information” instead of guesses. Use when user says “be 100% sure”, “no hallucinations”, “only if verified”, “grounded answer”, or when stakes are high.