davidcastagnetoa/skills

document_edge_detection

Detectar bordes del documento para validar captura correcta y aplicar corrección de perspectiva

First seen Mar 2, 2026

Installation

$ npx skills add davidcastagnetoa/skills --skill document_edge_detection

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from davidcastagnetoa/skills · top by installs.

npx skills add davidcastagnetoa/skills

Browse all from davidcastagnetoa/skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 1
Default branch main
Open issues 0
Status Active

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,141 B
  • docs SUMMARY.md 127 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 12 installs

SKILL.md

documentedgedetection

Detecta el contorno del documento de identidad para validar que está correctamente encuadrado y extraer sus coordenadas para corrección de perspectiva posterior.

When to use

Usar en la captura del documento, antes de pasarlo al documentprocessoragent.

Instructions

  1. Escala de grises + blur gaussiano: blur = cv2.GaussianBlur(gray, (5,5), 0)
  2. Canny: edges = cv2.Canny(blur, 75, 200)
  3. Contornos: contours, = cv2.findContours(edges, cv2.RETRLIST, cv2.CHAINAPPROXSIMPLE)
  4. Ordenar por área descendente y tomar los 5 primeros.
  5. Aproximar polígono: approx = cv2.approxPolyDP(c, 0.02*peri, True)
  6. Buscar contorno de 4 vértices (cuadrilátero) de mayor área → es el documento.
  7. Devolver los 4 puntos esquina ordenados.

Notes

  • Overlay en tiempo real mostrando el contorno detectado guía al usuario.
  • Complementar con YOLOv8 para clasificación del tipo de documento.