.claude/skills/evaluations-framework/SKILL.md
Evaluations Framework
npx skillsauth add gonzalezpazmonica/pm-workspace evaluations-frameworkInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Framework sistemático para evaluar la calidad de outputs de agentes, asegurando estándares de excelencia en la entrega de software.
Evalúa la calidad de la descomposición de historias de usuario:
Rubric:
Evalúa la calidad de especificaciones técnicas generadas:
Rubric:
Evalúa la precisión de estimaciones tras finalizar sprints:
Rubric:
Evalúa la calidad de revisiones de código/requisitos:
Rubric:
Evalúa si las tareas se asignaron a personas idóneas:
Rubric:
Evaluaciones se guardan en:
data/evals/{eval-name}/
├── config.json (definición y rubric)
├── results/
│ └── {timestamp}.json (scores, feedback)
└── trends/
└── {eval-name}-trends.json (análisis histórico)
Las evaluaciones se integran con el workflow de sprints, refinamiento y planning para mejora continua basada en datos.
testing
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
tools
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
tools
Sistema proactivo de bienestar individual
development
Search the web to resolve context gaps — documentation, versions, CVEs, best practices. Auto-starts SearxNG Docker if available, falls back to WebSearch.