Vasile Razdalovschi
Community@vrazdalovschi · London
Principal Engineer @ PSYKHE AI | Building the Taste Intelligence Layer for Ecommerce, Platforms & Agents
Agent Skills by Vasile Razdalovschi
Showing 24 vetted skills indexed across 1 GitHub repositories.
vrazdalovschicollaborate-codex
Orchestrate the OpenAI Codex CLI for code analysis, refactoring, and automated editing.
vrazdalovschicollaborate-gemini
Run Gemini CLI agents in parallel via tmux sessions.
vrazdalovschiexplore-website-stack
Analyze a website's technology stack and business intelligence via browser automation.
vrazdalovschiconsult-agents
Query Claude, Gemini, and Codex in parallel for validation feedback.
vrazdalovschiusing-git-worktrees
Create isolated Git worktrees with directory selection and baseline testing.
vrazdalovschipython-code-simplifier
Review and simplify Python code by reducing over-engineering and complexity.
vrazdalovschitest-driven-development
Guide the Red-Green-Refactor cycle for Test-Driven Development tasks.
vrazdalovschisystematic-debugging
Guide a four-phase process to identify root causes of software bugs.
vrazdalovschivercel-react-native-skills
Apply React Native and Expo best practices for mobile app performance.
vrazdalovschiweb-design-guidelines
Review UI code for compliance with Web Interface Guidelines and accessibility.
vrazdalovschiusing-superpowers
Invoke relevant skills before generating any response or action.
vrazdalovschidispatching-parallel-agents
Dispatches multiple AI agents concurrently to independently investigate and resolve separate task failures.
vrazdalovschiexecuting-plans
Execute implementation plans in batches with review checkpoints before proceeding.
vrazdalovschifinishing-a-development-branch
Verify tests and present integration options for completing a development branch.
vrazdalovschipython-pro
Build, review, and refactor Python 3.11+ code with type safety and async patterns.
vrazdalovschibrainstorming
Guide user ideas into approved design specifications through structured dialogue.
vrazdalovschiwriting-plans
Generate detailed implementation plans for multi-step software development tasks.
vrazdalovschirequesting-code-review
Dispatch a code-reviewer subagent to analyze code changes against requirements.
vrazdalovschireceiving-code-review
Evaluate code review feedback against codebase realities before implementation.
vrazdalovschiwriting-skills
Apply RED-GREEN-REFACTOR cycles to author and test AI skills.
vrazdalovschivercel-react-best-practices
Optimize React and Next.js applications with 57 performance rules across 8 categories.
vrazdalovschivercel-composition-patterns
Guide React component architecture with composition patterns and React 19 APIs.
vrazdalovschiverification-before-completion
Run fresh verification commands and analyze output before asserting task completion.
vrazdalovschisubagent-driven-development
Executes task plans by delegating each step to separate agentsUTE and reviewing outcomes for compliance and quality.