uak

Plugin uak from marketplace upiixia-agentic-kit in JoahanMorales/upiixia-agentic-kit. Commands read from the repo's manifest — yesterday.

Skills (36)

• uak-advise

  Use when you need a strong-model opinion and the advisor tool is unavailable or the session is long: at plan lock (plan), after the same failure twice (stuck), or before shipping a risky diff (done). Run this only when the user invokes it by name ($uak-advise or /uak-advise); never start it on your

• uak-demo

  (sprint) Use in the last hours of an event: freeze, clean rehearsal, plan-B video and the submission checklist. Run this only when the user invokes it by name ($uak-demo or /uak-demo); never start it on your own.

• uak-design-lock

  (sprint) Use before building UI screens: visual directions with screenshots, the human picks one, then the shell, the UI kit and three locked screens every later screen copies from. Run this only when the user invokes it by name ($uak-design-lock or /uak-design-lock); never start it on your own.

• uak-handoff

  Use before closing a session, before compacting, or when context or tokens run low: checkpoint the task and write the handoff the next session resumes from. Run this only when the user invokes it by name ($uak-handoff or /uak-handoff); never start it on your own.

• uak-loop

  Use while implementing a criterion: implement, run Verify, fix, with a budget and stuck detection; for long mechanical fixes it can run unattended with uak loop. Run this only when the user invokes it by name ($uak-loop or /uak-loop); never start it on your own.

• uak-plan

  Use when turning IDEA.md or a spec into tasks: a verifiable backlog graph with Paths, Verify, owners and wave-1 contracts. Run this only when the user invokes it by name ($uak-plan or /uak-plan); never start it on your own.

• uak-retro

  Use after an event or milestone: a data-driven retro from the claims branch that proposes concrete kit and project changes. Run this only when the user invokes it by name ($uak-retro or /uak-retro); never start it on your own.

• uak-review

  Use when a review is assigned to you or uak next says Idle: review: review another task's PR at its exact SHA and record approve or reject. Run this only when the user invokes it by name ($uak-review or /uak-review); never start it on your own.

• uak-secure

  Use before launching a backend: the security audit against the kit's launch checklist; delegates the sensitive review to security-reviewer. Run this only when the user invokes it by name ($uak-secure or /uak-secure); never start it on your own.

• uak-setup

  Use at minute 0 with the human: PROJECT.md, doctor PASS, reviewers registered, schedule from uak clock. Run this only when the user invokes it by name ($uak-setup or /uak-setup); never start it on your own.

• uak-ship

  Use when your task's criteria pass: run Verify, push, open the PR and move the task to REVIEW with uak done (then wait for the verdict with uak wait). Run this only when the user invokes it by name ($uak-ship or /uak-ship); never start it on your own.

• uak-spec

  (marathon) Use before writing code for a product feature: spec, plan with threat model, then tasks. Run this only when the user invokes it by name ($uak-spec or /uak-spec); never start it on your own.

• uak-start

  Use at the start of a session with no task in hand: take the next task (uak next) and get its worktree ready, claim included. Run this only when the user invokes it by name ($uak-start or /uak-start); never start it on your own.

• design-taste-frontend

  Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

• frontend-design

  Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

• karpathy-guidelines

  Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

• landing-story

  Build a landing page (home, portada, pitch page) that makes a stranger get the idea in 5 seconds and want to try it - for a hackathon jury, users or investors. Use when creating or redesigning the product's front page, a project's public page, or the page judges open first. Works from IDEA.md (the o

• mcp-builder

  Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

• product-ui

  Make product screens look designed, not templated - dashboards, a map or canvas with side panels, data views, detail pages, forms and flows, lists, mobile screens. Use whenever you build or change an app screen, a view or a component in web/ (the landing is landing-story; the visual direction is /ua

• redesign-existing-projects

  Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.

• systematic-debugging

  Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

• test-driven-development

  Use when implementing any feature or bugfix, before writing implementation code

• test-first

  Use before writing code for any feature, bug fix or behavior change. Test names first, see the red on an assertion (uak red), Fakes instead of mocks, tests only grow, tests by layer.

• vercel-react-best-practices

  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,

• verification-before-completion

  Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

• webapp-testing

  Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

• stack-ai-agent

  Conventions for the AI agent stack (MCP tools per task, eval cases per tool, offline evals in the gate). Use when adding an MCP tool, an eval case, a prompt or a model call in this repo.

• stack-django

  Conventions for the Django stack (one app per task, auto-included urls, pytest-django, migrations through a human). Use when adding an app, model, view, template, admin or test in this repo.

• stack-expo

  Conventions for the Expo / React Native stack (Expo Router screens per task, components/<f>, lib owners). Use when adding a screen, component, navigation or API call in this app.

• stack-backend

  Backend conventions for the FastAPI + React stack (app/, Python 3.12, FastAPI, uv, pytest). Use when creating or changing endpoints, services, schemas, tests or Python dependencies.

• stack-frontend

  Frontend conventions for the FastAPI + React stack (web/, Vite, React, TypeScript, Tailwind v4, Motion). Use when creating or changing any screen, component or style in web/, deciding visual design, or verifying UI in a browser.

• stack-go

  Conventions for the Go HTTP service stack (internal/<f> packages, init() registry, go test). Use when adding a handler, service, package or test in this repo.

• stack-nextjs

  Conventions for the Next.js App Router stack (src/app/<f>/, route handlers, Tailwind, Playwright). Use when adding a page, an API route, a component or a test in this repo.

• stack-data

  Conventions for the Python data / ML stack (package, analysis/<f>/run.py, reports/<f>/ CSVs, Streamlit pages, pytest). Use when writing an analysis, a model, a report README, a dashboard page or a test in this repo.

• stack-spring-boot

  Conventions for the Spring Boot stack (package by feature, constructor injection, ProblemDetail errors, MockMvc and Testcontainers tests, Flyway). Use when adding a controller, service, repository, migration or test in this repo.

• setup

  Install the UPIIXIA Agentic Kit (uak) into the current Git repository so several AI coding agents (Claude Code, Codex, Cursor, Gemini CLI) can work in parallel with claims, leases, bounded verify-fix loops, reviews and merges. Use when the user wants multi-agent coordination, parallel agents, a hack

Similar plugins