oxedom

Software testing expertise for writing effective tests. Use when writing tests, reviewing test quality, designing test suites, debugging test failures, or implementing TDD. Covers xUnit patterns, test case selection, mocks/fixtures, parametrization, testing stateful systems, BDD, golden/snapshot testing, and LLM output evaluation.

Sync the claudeResources registry in claude-runner.ts with actual files in .claude folder. Use when adding, removing, or renaming skills/agents/commands, or when claudeResources may be out of sync with the .claude directory structure.

Turn rough MyTraining feature requests into testable PRDs (Mutual Persistent Memory + Backend PRD + Frontend PRD) with explicit API contracts, acceptance criteria mapped to tests, and stable `data-testid` selectors for E2E.

Use when running E2E checks or debugging the web app with Playwright MCP, especially when you need to (1) ensure the demo user exists with superadmin permissions via demo.sql, and (2) login via /demoLogin on localhost.

React performance optimization guidelines. This skill should be used when writing, reviewing, or refactoring React code to ensure optimal performance patterns. Triggers on tasks involving React components, data fetching, bundle optimization, or performance improvements.

Guide for creating effective skills. Use when creating a new skill (or updating an existing one) that extends the assistant with specialized knowledge, workflows, or tool integrations.

Transform vague or informal prompts into structured, precise prompts optimized for the researchCodebase agent. Use when preparing to launch codebase research and the user's request needs refinement for better results.

Expert SQL developer specializing in complex query optimization, database design, and performance tuning across PostgreSQL, MySQL, SQL Server, and Oracle; includes advanced SQL patterns, indexing strategies, and data warehousing techniques.

Prepare a concise daily briefing.

Use when the agent needs current library or framework documentation. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Next.js, Prisma, etc.

Default process for a personal assistant turn.

Use when the agent needs to automate a browser — navigate websites, take screenshots, fill forms, or extract page content.

Use when starting a brand-new project or repository from scratch — triggers like "bootstrap a project", "start a new project", "new repo", "init a repo and put it on GitHub", "spin up a new private repo", "create me a new project". For going from nothing to a named, private GitHub repo with onboarding files.

React performance optimization guidelines. This skill should be used when writing, reviewing, or refactoring React code to ensure optimal performance patterns. Triggers on tasks involving React components, data fetching, bundle optimization, or performance improvements.

Use when building a pinned bottom action bar (submit, next, mark-complete, navigate) that stays docked to the viewport while users scroll long content — common in lessons, challenges, forms, and multi-step wizards. Trigger on phrases like "sticky bar", "docked footer", "floating submit", "pinned action bar", or when primary actions risk being scrolled out of view.

Use when the user wants to consolidate multiple tmux sessions into a single session's windows, or unify many tmux sessions into one tabbed view.

Generate themed input.json files for vite-plugin-injector. Use this skill whenever the user wants to create, customize, or generate content for vite-plugin-injector — including requests like "generate input.json", "create injector content", "make a theme for vite-plugin-injector", "generate jokes/quotes/comments for my build", or any mention of injector themes, build artifact injection content, or the vite-plugin-injector input file. Also trigger when the user provides a topic/theme and wants it turned into developer comments, console logs, variable suffixes, ASCII art, changelog entries, or HTML comments for code injection.