iridium

Verify Linear backlog tickets against the actual codebase before anyone implements them — extract each ticket's checkable claims, grep the code to confirm or refute, classify by scope, and leave an evidence-backed triage comment. Use when the user says "triage the backlog", "comb through Linear tasks", "verify these tickets", "/linear-triage", or on a schedule. Not for implementing fixes (use linear-to-pr on tickets triaged valid), and never changes ticket state beyond commenting unless explicitly told to.

Verify any UI-affecting change end-to-end before declaring it done — boot the app, interact with the change via Playwright, capture before/after screenshots (light/dark, desktop/phone), check console errors, and attach the evidence. Use after implementing or reviewing any change to components, routes with visible output, layouts, styling, or theming. Triggers include "verify this UI change", "did the banner/button/layout change work", or finishing any *.tsx edit that alters rendered markup or classes. Not for server-only changes (models, API routes, env plumbing), docs, or pure test edits.

Explore the running Iridium app like a curious, destructive user and file GitHub issues for confirmed bugs. Picks an exploration charter (auth, notes, chat, settings, admin, mobile), drives the app with Playwright, reproduces every finding twice, dedupes against open qa-explorer issues, and files structured reports with repro scripts. Use when the user says "qa sweep", "explore the app for bugs", "run the qa explorer", "hunt for bugs", or "do some exploratory testing". Not for implementing fixes (use github-issue-to-pr on the filed issues), not for deterministic regression tests (those live in tests/), and never against production.

Drive a GitHub issue to an open pull request. Fetches the issue with gh, self-assigns, creates a linked branch via gh issue develop, implements the change, runs validation plus targeted Playwright e2e tests, captures screenshots of UI changes and links them from the PR body, and opens the PR with a closing "Fixes

Drive a Linear issue to an open GitHub pull request. Fetches the issue, branches using Linear's suggested branch name, implements the change, runs validation plus targeted Playwright e2e tests, captures screenshots of UI changes and links them from the PR body, opens the PR with gh, and moves the issue to a review status. Use when the user says "work on ABC-123" (any Linear issue identifier), "take this Linear issue to a PR", "implement this ticket", "linear to pr", or pastes a linear.app issue URL to be implemented. Not for creating or triaging Linear issues, and not for reviewing or merging existing PRs.

MANDATORY color usage rules for daisyUI 5

Configuration options for daisyUI 5

Installation notes for daisyUI 5

Official daisyUI component library skill. The mandatory UI library for Tailwind CSS. TRIGGER when generating any HTML or JSX code even if the user does not explicitly ask for this skill.

MANDATORY usage rules for daisyUI 5

Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.

Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Triggers on: convert this prd, turn this into ralph format, create prd.json from this, ralph json.

Auto-commit changes after a Spec Kit command completes

Create a feature branch with sequential or timestamp numbering

Initialize a Git repository with an initial commit

Detect Git remote URL for GitHub integration

Validate current branch follows feature branch naming conventions

Build validated forms in this Iridium app using React Hook Form v7 + Zod v4, useFetcher submission, and DaisyUI v5 markup. Use when adding any user-input form (login, signup, settings, create/edit pages, contact, etc.), composing fieldsets with accessible error messages, wiring client + server validation against a shared schema, displaying form-level or field-level errors from an action, or editing a *.tsx file that contains a <form> or imports react-hook-form, @hookform/resolvers/zod, or zod. Do NOT use for the chat input (uses @ai-sdk/react useChat), for the existing Better Auth login/register flows, or for pure search/filter forms (use <Form method="get"> directly).

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

Generate a custom checklist for the current feature based on user requirements.

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.

Execute the implementation plan by processing and executing all tasks defined in tasks.md

Execute the implementation planning workflow using the plan template to generate design artifacts.

Create or update the feature specification from a natural language feature description.

Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.

Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".

This skill should be used when the user wants to add a database (Postgres, Redis, MySQL, MongoDB), says "add postgres", "add redis", "add database", "connect to database", or "wire up the database". For other templates (Ghost, Strapi, n8n, etc.), use the templates skill.

This skill should be used when the user wants to push code to Railway, says "railway up", "deploy", "deploy to railway", "ship", or "push". For initial setup or creating services, use new skill. For Docker images, use environment skill.

This skill should be used when the user wants to manage Railway deployments, view logs, or debug issues. Covers deployment lifecycle (remove, stop, redeploy, restart), deployment visibility (list, status, history), and troubleshooting (logs, errors, failures, crashes, why deploy failed). NOT for deleting services - use environment skill with isDeleted for that.

This skill provides guidance and enforcement rules for implementing secure email and password authentication using Better Auth.

This skill should be used when the user says "setup", "deploy to railway", "initialize", "create project", "create service", or wants to deploy from GitHub. Handles initial setup AND adding services to existing projects. For databases, use the database skill instead.

This skill should be used when the user wants to list all projects, switch projects, rename a project, enable/disable PR deploys, make a project public/private, or modify project settings.

This skill should be used when the user asks about Railway features, how Railway works, or shares a docs.railway.com URL. Fetches up-to-date Railway docs to answer accurately.

Build full-stack React applications using React Router's framework mode. Use when configuring routes, working with loaders and actions, handling forms, handling navigation, pending/optimistic UI, error boundaries, or working with react-router.config.ts or other react router conventions.

This skill should be used when the user asks about service status, wants to rename a service, change service icons, link services, or create services with Docker images. For creating services with local code, prefer the `new` skill. For GitHub repo sources, use `new` skill to create empty service then `environment` skill to configure source.

This skill should be used when the user asks "railway status", "is it running", "what's deployed", "deployment status", or about uptime. NOT for variables ("what variables", "env vars", "add variable") or configuration queries - use environment skill for those.