workoutTracker

Deep research on a technical problem using parallel subagents for web docs, Stack Overflow, and codebase exploration, saving a markdown report to brain/reference/research/. Use when the user says "research X", "investigate X", "find out how X works", or needs evidence-based recommendations before implementing.

Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes

Review current code changes by dispatching parallel specialized review agents (Vue, TypeScript, a11y, performance, security, tests). Use proactively before committing or opening a PR, or when the user asks to "review", "check", "audit", or "look over" their changes.

Inspect GitHub Actions / CI status for the current branch and plan fixes when checks fail. Use proactively after pushing, or when the user mentions "CI", "pipeline", "GitHub Actions", "failing checks", "build failing", or asks "why is CI red".

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Run ESLint across the project and fix reported errors and warnings. Use when the user asks to "lint", "fix lint errors", "run eslint", or before committing/shipping to ensure a clean lint pass.

Squash-merge the current PR into main, delete the branch, pull latest, and start a new feature branch. Use when the user says "merge this PR", "merge and start new branch", or is done with a PR and ready to start the next task.

Mutation testing patterns for verifying test effectiveness. Use when analyzing branch code to find weak or missing tests. Triggers: "mutation testing", "test effectiveness", "would tests catch this bug", "weak tests", "are my tests good enough", "surviving mutants".

Generate or update a structured pull request with summary, user impact, acceptance criteria, QA scope, risk areas, and executable test scenarios, then open it with GitHub CLI.

Product Owner / Business Analyst toolkit for product planning tasks. Use when the user wants to: - Write or refine user stories, epics, or acceptance criteria - Create or review PRDs (Product Requirement Documents) - Prioritize backlog items (RICE scoring, MoSCoW, etc.) - Plan sprints or releases - Create or update product roadmaps - Conduct competitive analysis or user research - Write release notes or stakeholder updates MANDATORY TRIGGERS: user story, epic, PRD, backlog, sprint planning, roadmap, acceptance criteria, product requirements, prioritize, story points, PO, BA, product owner, business analyst

Fetch CodeRabbit review comments on the current PR, validate each against project conventions, implement valid fixes, and reply to resolve each conversation. Use proactively when CodeRabbit leaves review comments, or when the user says "review coderabbit", "address coderabbit feedback", or "fix coderabbit comments".

End-to-end delivery: commit staged changes, push to remote, and open a pull request in one flow (runs /push then /pr). Use when the user says "ship it", "ship this", "ship the changes", or wants to go from working tree to open PR in one step.

Systematic debugging framework for any bug, test failure, or unexpected behavior. Use BEFORE proposing fixes. Triggers: "bug", "test failure", "flaky test", "debugging", "root cause", "investigate", "why is this failing", "unexpected behavior", "not working", "broken", "error", "fix this", "what's wrong".

Compute the next semver version from Conventional Commits since the last tag (major/minor/patch), create an annotated git tag, and push it. Use when the user says "tag a release", "bump version", "cut a release", or "create version tag".

Smoke-test affected pages in a real browser via the agent-browser CLI by mapping changed files to routes. Use when the user says "test in the browser", "smoke test the PR", "verify the UI works", or before merging UI-affecting changes.

Vitest mocking patterns and test double strategies. Use when writing tests that need mocks, spies, stubs, or fakes. Triggers include: mocking modules, stubbing globals (fetch, Date, timers), testing composables, mocking imports (default/named), creating test doubles, replacing dependencies, verifying mock calls, cleaning up mocks, or any question about "how do I mock X in Vitest". Also use when reviewing tests for proper mocking practices.

Test Vue 3 composables with Vitest following best practices. Use when writing tests for composables, creating test helpers for Vue reactivity, or when asked to "test a composable", "write tests for use*", or "help test Vue composition functions". Covers independent composables (direct testing) and dependent composables (lifecycle/inject testing with helpers).

Write high-quality Vue 3 composables following established patterns and best practices. Use when creating new composables, refactoring existing ones, or reviewing composable code. Triggers include requests to "create a composable", "write a use* function", "extract logic into a composable", or any Vue Composition API reusable logic task.

Write Vue 3 integration tests using Vitest Browser Mode and Page Objects. Use proactively whenever adding tests for views, components with routing, user flows, or features that span multiple components. Triggers include "add tests", "write tests", "test this", "needs tests", "integration tests", "test the feature", "test user flow", or any task involving testing UI interactions, navigation, dialogs, forms, or multi-step workflows.

Vue 3 patterns and best practices for this workout tracker: feature module architecture, createGlobalState() singleton state (not Pinia), defineModel two-way binding, and component gotchas. Use when creating/refactoring components, features, composables, managing shared state, or debugging reactivity issues. Triggers include "add component", "create feature", "refactor", "composable", "v-model", "defineModel", "global state", "createGlobalState", "singleton", "reactive", "two-way binding", "feature structure", "reka-ui", "shadcn-vue".

Workout block model, types, and operations. Use when building workouts, managing block kinds (strength/AMRAP/EMOM/Tabata/ForTime/cardio), handling sets/reps, or working with workout persistence and benchmarks. Triggers: "workout", "block", "strength", "cardio", "AMRAP", "EMOM", "Tabata", "ForTime", "exercise", "set", "reps", "weight", "RIR", "timed block", "create workout", "build workout", "block kind", "discriminated union", "block result", "round", "interval", "benchmark", "template", "persist workout", "complete workout".

Fetch CodeRabbit review comments on the current PR, validate each against project conventions, implement valid fixes, and reply to resolve each conversation. Use proactively when CodeRabbit leaves review comments, or when the user says "review coderabbit", "address coderabbit feedback", or "fix coderabbit comments".

Smoke-test affected pages in a real browser via the agent-browser CLI by mapping changed files to routes. Use when the user says "test in the browser", "smoke test the PR", "verify the UI works", or before merging UI-affecting changes.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.