Skip to content
Main menu

Pablo Contreras · Vibe Coding · Lima, Peru · Remote LATAM/US

Vibe Coding

AI-Augmented Full Stack · Claude Code

I have been using Claude Code since launch (May 2025). Before that I was already piping context to Claude web with my own FastStruct extension. I build tools that accelerate that flow and publish real prompts. AI is a tool — I review, test and maintain the code myself.

Track record

Years shipping product
0 +
Companies
0
LATAM countries
0
Certifications
0

01

Experience

Roles where I integrate AI into daily work (current role at Destacame).

  1. Frontend Architect and Microservices Developer

    Destacame

    August 2022 — Present

    Frontend Architect leading the microfrontend migration and orchestrating Destacame fintech products for Chile and Mexico.

    • AWS
    • Arquitectura Frontend
    • Django
    • Microfrontend
    • Microservicios
    • Python
    • TypeScript
    View detail →

02

Projects

FastStruct + CV builder (bypabloc/cv) + Astro monorepo of this portfolio. Tools I use to ship.

MVP template Full Stack

Activo

This open source portfolio is my reference template to bootstrap full stack: Astro 6, AWS serverless backend, Python 3.14 devtools and a standardized Claude Code harness.

  • Claude Code
  • Astro 6
  • TypeScript
  • Python 3.14
  • AWS Lambda
  • DynamoDB
  • +3

FastStruct

Activo

VS Code extension that visualizes and documents a project structure in seconds, optimized for AI workflows.

  • TypeScript
  • VS Code Extension API
  • Node.js
  • Claude Code
  • Cursor
  • GitHub Copilot
  • Prompt Engineering
  • Vibe Coding
  • Vue 3
  • Nuxt.js
  • TypeScript
  • Astro
  • Desarrollo Frontend
  • Desarrollo Frontend
  • Astro
  • TypeScript
  • Nuxt.js
  • Vue 3
  • Vibe Coding
  • Prompt Engineering
  • GitHub Copilot
  • Cursor
  • Claude Code
Vibe Coding · 2026

AI workflow

How I work with Claude Code, Cursor and subagents. No gimmicks: real prompts, transparent output, concrete metrics.

History

Claude web + FastStruct → Claude Code (May 2025)

Before Claude Code I used the Claude web interface to code and piped context with my own FastStruct extension (published on the VS Code Marketplace). When Claude Code launched in May 2025 I was an early adopter from day one.

Enterprise adoption

I rolled out Claude Code at Destacame

I was the one who introduced Claude Code in my current team at Destacame. I built a skills/rules/docs structure to standardize usage across developers, define canonical prompts per task, avoid duplicated discoveries and keep coherence in quality gates.

CLI tooling

Custom CLIs built with Claude Code

I regularly build CLIs (Python 3.14 devtools orchestrator, scan/verify/feature-test scripts, etc.) with Claude Code to centralize repetitive team processes. Each CLI is reviewed, tested and maintainable code — not throwaway scripts.

Current stack

Claude Code · Cursor · Sub-agents

Claude Code as primary driver (91% CSAT, 54 NPS). Cursor for targeted visual refactors. Sub-agents (researcher / Explore / code-reviewer) on long outputs to avoid burning the orchestrator context.

Real prompt

Pattern explore → plan → implement → commit

"Explore these 3 files and tell me which components are refactor candidates due to duplication. Write your report to tmp/explore_X.md, respond a single line." → Cuts 80% of orchestrator token consumption.

Open reference

bypabloc/mvp-template-full-stack

Public repository I use as template and reference for the workflow: .claude/ structure, skills, rules, hooks, devtools CLI, conformance and testing. Serves as blueprint for new projects and to showcase the full vibe coding workflow.

Recent output

bypabloc/cv — MVP in one night (May 12-13, 2026)

CV builder built in a single night with Claude Code. Public repo bypabloc/cv. Demonstrates that the Claude Code + human review combo ships product without sacrificing maintainability.

Metrics

5x faster + 0% AI attribution

Time spent instructing an LLM drops 5x with FastStruct. Zero "Generated with Claude Code" in commits/PRs via prepare-commit-msg hook that scans and strips AI attribution by company policy.

Rules

AI = tool, not author

All code is reviewed, tested (Vitest + Playwright) and maintained by me. Quality gates in pre-commit and pre-push (Biome + tsc + astro check + coverage ≥80% + build). AI attribution forbidden by policy — not in commits, not in PRs, not in docs.

// Disclosure: all code is reviewed, tested (Vitest + Playwright) and maintained by me. AI is a tool, not an author. NEVER in commit attribution.

03

Technical skills

Current stack + domains where I have shipped to production.

Technical

AI Workflows

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Prompt Engineering
  • Vibe Coding
  • Sub-agentes
  • MCP Servers
  • Skill-based agents

Frontend

  • Vue 3
  • Nuxt.js
  • TypeScript
  • Astro
  • Desarrollo Frontend
  • Arquitectura Frontend
  • Microfrontend
  • Desarrollo de E-commerce
  • Aplicación Web
  • jQuery

Soft

Mindset & Personal

  • Adaptabilidad
  • Agilidad de Aprendizaje
  • Auto-motivación
  • Pensamiento Analítico
  • Resolución de Problemas