Skills

A coding agent cannot hold every piece of specialist know-how in its standing instructions; they would grow too long to follow. A skill is know-how it loads only when a task needs it, by matching the skill's name and description. A run that changes no UI never loads the UI skills.

The run itself

What a /wettaq run loads along the way: mapping the repository, checking the UI in a browser, the independent review and the pull request.

Skill	Why	What it does
commit-pr-writing	A pull request you have to reverse-engineer from the diff costs more time than the agent saved.	Write outcome-focused commit messages, pull-request titles, and concise pull-request descriptions from completed work and its evidence.
implement-review	A review only helps if its findings are fixed and confirmed once, not argued over in an endless loop.	The independent review gate, review remediation and the follow-up path of /wettaq.
rendered-qa	Code and stylesheets cannot show what a page actually looks like; a real browser and screenshots can.	Exercise a running UI hands-on and capture evidence — viewports, motion, hydration, scrolling, interaction, keyboard, touch targets, console — then report findings with a severity.
repo-context	An agent that changes code before it understands the repository breaks the patterns already there.	Inspect a repository and report a concise, evidence-based map of its stack, structure, observed patterns, testing, CI/CD, and infrastructure.
test-design	Agents write tests that pass whatever the code does, so a green suite with hundreds of tests can still protect nothing.	Decide which tests a change needs and write tests that can actually fail.

UI work

Design judgement and tests for interfaces, loaded when a change has a UI. Some are for one stack only.

Skill	Why	What it does
angular (optional: Angular repositories only)	Angular has its own patterns, and generic advice gets them wrong.	Angular engineering guidance for meaningful component, form, data-access, state-management, testing, or architecture work.
frontend-design	Generated interfaces tend to look the same, templated and generic.	Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one.
playwright-tests (optional: Repositories that keep Playwright UI tests)	Browser tests with brittle selectors break on every harmless change.	Write and maintain Playwright UI tests with resilient selectors, reusable helpers, and AAA structure.
ui-designer	Interface code written without design judgement works, but is hard to use.	Practical UI design reasoning for creating, implementing, improving, or refactoring application interfaces and flows.
ux-principles	Without written UX principles, every agent decides interface questions its own way.	Define, generate, or refine a product's UX_PRINCIPLES.md through repository-informed discovery and adaptive product-owner questions.

Setup

Installing, repairing and upgrading mexxi itself.

Skill	Why	What it does
ibda	Installing one workflow into three different agents by hand is fiddly and easy to get wrong.	Install, set up, repair or upgrade mexxi, the coding-agent workflow in github.com/alexportelli12/mexxi, on this machine.

Working on mexxi

For changing mexxi: its docs, its rules and its skills.

Skill	Why	What it does
docs-writing	Docs written for insiders lose newcomers, so mexxi's pages need one plain voice that says why before how.	Write or edit the Markdown that people read in the mexxi repository, such as its README, hand-written docs pages and landing page copy.
skill-creator (optional: Writing and testing your own skills)	A skill that never loads, or loads at the wrong time, is worse than none.	Create new skills, modify and improve existing skills, and measure skill performance.
workflow-for-alex (optional: Changing the workflow itself with /sewwi)	A change to one part of the workflow can quietly contradict another.	Design and evolve Alex's global coding-agent workflow configuration.