AI Agent Workflow Collection

Use when the user asks about ARIA, ARIA roles, ARIA attributes, aria-label, aria-labelledby, aria-describedby, aria-expanded, aria-hidden, aria-live, aria-required, aria-invalid, "WAI-ARIA", "ARIA Authoring Practices", "APG pattern", "accessible name", "accessible description", live regions, custom widgets, dialogs, menus, tabs, accordions, comboboxes, tooltips, tree views, carousels, or is building any custom interactive component that requires ARIA roles and keyboard behavior beyond native HTML elements.

Use when the user asks about accessible forms, form labels, form errors, input accessibility, "aria-required", "aria-invalid", "aria-describedby", fieldset and legend, "form validation accessibility", required fields, error messages, placeholder accessibility, password fields, file uploads, date inputs, select elements, checkbox groups, radio groups, "WCAG 3.3", "label instructions", or is building any form that needs to be screen reader compatible and keyboard accessible.

Use when the user asks about keyboard navigation, keyboard accessibility, focus management, focus trapping, focus ring, focus indicator, ":focus-visible", skip links, "tabindex", "Tab key navigation", "focus order", "focus returns", "orphaned focus", "focus lost", "modal focus trap", "focus after close", "roving tabindex", "keyboard trap", or is building modals, dialogs, drawers, dropdowns, or any component requiring programmatic focus management. Also use when diagnosing why keyboard navigation feels broken.

Use when the user asks about semantic HTML structure, heading hierarchy, landmark regions, div soup, divitis, "which HTML element should I use", "semantic markup", "HTML accessibility", "ARIA landmarks", "page structure", "section vs div", "article vs section", "when to use aside", or is writing HTML templates, page layouts, or component markup that requires accessible structural decisions. Also use when reviewing HTML for screen reader compatibility or document outline correctness.

Use when the user asks about accessibility testing, axe-core, jest-axe, "@testing-library", "@axe-core/playwright", "Playwright accessibility testing", "WAVE", "Lighthouse accessibility", "automated a11y tests", "accessibility CI/CD", "eslint-plugin-jsx-a11y", "a11y linting", "axe DevTools", setting up accessibility tests, writing accessibility tests for React components, integrating a11y checks into a test suite, or understanding what automated tools can and cannot catch. Also use when asked to add automated a11y testing to a project.

Use when the user says "add a billing agent", "add a bookkeeping agent", "set up a support tier-1 agent", "add a recruiting agent", "add a compliance agent", "add a CRM agent", "add a contracts agent", "add an analytics agent", "add a marketing email agent", "add a CMS agent", "scaffold a function-specific agent", or wants to add a single business-function agent backed by a verified-write MCP integration. Each agent ships with explicit scope, "what this will NOT do" constraints, and recommended human-in-the-loop checkpoints.

AEO, AI visibility, AI search optimization, generative engine optimization, LLM seeding, AI citations, answer engine optimization, brand presence in ChatGPT/Perplexity/Google AI Overviews. This skill optimizes the user's OWN content structure and distribution for AI-extractability. It does NOT measure actual AI citation rates — that requires direct AI-platform API integration (Path B).

Use when the user asks about "daily operating rhythm", "agentic operations", "token optimization", "credential rotation", "autonomous agent patterns", "headless mode", "agent failure recovery", "morning briefing", "agent monitoring", "context compaction strategy", "PARA methodology for agents", "Routines", "scheduled agents", or wants guidance on running and maintaining a Claude Code workspace day-to-day.

Use when the user says "check for AI patterns", "does this sound like AI", "AI audit", "ai-audit", "check if this reads as human", "humanize check", "AI tells", "does this pass AI detection", "check for AI slop", "is this AI-written", "AI pattern check", or wants a deep analysis of whether text exhibits AI-generated writing patterns. Reports patterns with measurable scores (computed by scripts/text-stats.py) and located findings (computed by scripts/check-blocklist.py). Does NOT claim to be an AI detector — perfect AI detection is mathematically impossible (arXiv:2509.11915). Works across all 9 writing domains.

Use when implementing accessibility in Astro, WCAG compliance in Astro, Astro ARIA patterns, keyboard navigation in Astro components, screen reader support in Astro, Astro semantic HTML, focus management in Astro, accessible forms in Astro, Astro accessibility testing, axe-core integration with Astro, accessible Astro islands, alt text for Astro images, focus trapping in modals, accessible view transitions, or color contrast requirements.

Use when debugging Astro issues, identifying Astro anti-patterns, fixing common Astro mistakes, troubleshooting Astro errors, resolving "document is not defined" in Astro, resolving "window is not defined" in Astro, diagnosing a component not interactive, fixing content validation errors, investigating why an Astro build fails, debugging hydration issues, solving Astro 5 migration problems, fixing slug vs id errors, resolving render method not found, diagnosing Astro performance problems, reducing too much JavaScript in Astro, fixing Astro routing errors, or addressing form resubmission warnings.

Broken links, 404 errors, dead links, redirect chains, link checker, fix links. Scans the user's codebase for broken internal/external links, redirect chains, mixed-content issues, and unlinked brand mention opportunities. Real code work — no Path B dependencies.

Use when working on any Chrome extension project or when the user asks about Chrome extension best practices, conventions, or patterns. Trigger when: setting up a new Chrome extension, configuring WXT, asking about MV3 architecture, "Chrome extension project structure", "WXT config", "extension entrypoints", "manifest v3 setup", "when to use content script vs service worker", "extension context boundaries", "Chrome extension build", "wxt.config.ts", "extension packaging", "Chrome Web Store submission", "cross-browser extension".

Use when implementing messaging between Chrome extension components or when the user asks about inter-process communication in extensions. Trigger when: "extension messaging", "chrome.runtime.sendMessage", "chrome.tabs.sendMessage", "content script messaging", "port.postMessage", "runtime.connect", "Protocol Map", "@webext-core/messaging", "message passing", "extension IPC", "sendMessage vs connect", "async message response", "return true onMessage", "typed messaging", "message schema".

Use when working on Chrome extension permissions or Chrome Web Store compliance. Trigger when: declaring extension permissions, "manifest permissions", "activeTab vs tabs", "optionalpermissions", "hostpermissions", "Chrome Web Store rejection", "permission minimization", "over-permissioning", "CWS review", "Purple Potassium", "extension permission audit", "narrowest permission", "permission warnings", "chrome.permissions.request", "permission justification".

Use when working on security aspects of a Chrome extension or when the user asks about Chrome extension security best practices. Trigger when: implementing Content Security Policy in extensions, "extension CSP", "eval in extension", "content script security", "extension XSS", "remote code in extension", "MV3 security", "unsafe-eval", "content script isolation", "DOM safety in extension", "Trusted Types", "extension sandbox", "chrome extension security audit", "innerHTML in extension", "message validation".

Use when working with Chrome extension service workers or background scripts. Trigger when: "service worker lifecycle", "background script", "extension service worker", "chrome.alarms", "offscreen document", "service worker restart", "top-level listener", "service worker idle", "event listener registration", "chrome.offscreen", "service worker termination", "state rehydration", "persistent background", "MV3 background", "service worker wake-up", "keepalive", "setTimeout in service worker".

Use when working with data storage in Chrome extensions or when the user asks about extension storage patterns. Trigger when: "chrome.storage", "extension storage", "storage.local", "storage.sync", "storage.session", "IndexedDB in extension", "extension data persistence", "write-through cache", "storage quota", "unlimitedStorage", "chrome.storage.onChanged", "reactive storage", "WXT storage", "storage.defineItem", "storage migration", "sync vs local storage".

Use when writing or setting up tests for a Chrome extension. Trigger when: "test chrome extension", "extension unit test", "extension e2e test", "Vitest extension", "Playwright extension", "@webext-core/fake-browser", "test content script", "test service worker", "test messaging", "test storage", "extension integration test", "test permission flow", "extension test framework", "mock chrome API", "browser mode testing".

Use when debugging Chrome extension issues, diagnosing Chrome Web Store rejections, or troubleshooting build problems. Trigger when: "extension not working", "CWS rejection", "Chrome Web Store rejected", "Yellow Magnesium", "Purple Potassium", "Blue Argon", "Red Magnesium", "extension build error", "manifest error", "extension debugging", "service worker not waking", "content script not injecting", "message not received", "extension permissions error", "pre-release checklist", "extension review".

Use when building React UI for Chrome extensions or when the user asks about UI patterns in extensions. Trigger when: "React in extension", "extension popup React", "side panel React", "Shadow DOM React", "content script UI", "createShadowRootUi", "extension accessibility", "rem to px extension", "portal in extension", "React popup state", "extension UI patterns", "Radix in extension", "Shadcn extension", "extension keyboard navigation", "ARIA in extension", "focus management extension".

Use when performing operational actions against a Coolify instance using MCP tools — deploying applications, checking deployment status, viewing logs, diagnosing errors, managing environment variables, restarting services, checking server health, or performing any hands-on Coolify management task. Trigger when: "deploy my app", "check Coolify status", "show me Coolify logs", "what's running on Coolify", "restart my app on Coolify", "check server health", "why is my deploy failing", "list my Coolify apps", "add env var to Coolify", "Coolify deployment status", "roll back my deploy", "check my databases", "what resources are on my server".

Use when setting up CI/CD pipelines for Coolify, using the Coolify REST API, triggering deployments from GitHub Actions, configuring webhooks, deploying from GHCR or other registries, setting up PR preview environments, configuring branch-specific deployments, using the Coolify deploy webhook, integrating GitLab CI with Coolify, or managing API tokens. Trigger when: "Coolify CI/CD", "Coolify API", "deploy to Coolify from GitHub Actions", "Coolify webhook", "Coolify deploy trigger", "Coolify API token", "GHCR deploy Coolify", "Coolify PR preview", "Coolify branch deploy", "action-coolify", "GitLab CI Coolify", "Coolify REST API", "automate Coolify deployment".

Use when provisioning databases in Coolify, configuring database backups, restoring database backups, setting up S3-compatible backup storage, managing database SSL/TLS, connecting external clients to Coolify databases, rotating database credentials, running migrations against Coolify databases, tuning database resource limits, or choosing between standalone databases and service databases. Trigger when: "Coolify database", "create database in Coolify", "Coolify PostgreSQL", "Coolify MySQL", "Coolify Redis", "database backup Coolify", "restore database Coolify", "S3 backup Coolify", "connect to Coolify database", "database migration Coolify", "Coolify MongoDB", "Coolify MariaDB", "Coolify ClickHouse", "database credentials", "database SSL Coolify".