Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →wasabeef/análisis-paralelo-multi-rol-con-reporte-integrado
Análisis paralelo multi-rol con reporte integrado. Se activa con "analizar desde múltiples perspectivas", "análisis multi-rol".
Passed 22 of 22 test cases with the skill, and 12 of 22 without it.
and 10 more in the full report
10 fixed12 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
I want to invoke the multi-role tool to evaluate an authentication service with security and architect roles using sub-agents. A colleague wrote `/multi-role security,architect Check auth microservice --agent`. How should this command be correctly formatted according to positional rules?
| Checked | Without skill | With skill |
|---|---|---|
| The command places the `--agent` flag immediately after the role list. | Missed | Passed |
| The analysis target text appears after the `--agent` flag. | Passed | Passed |
The instructions your model reads when the skill loads.
Un comando que analiza el mismo objetivo en paralelo con múltiples roles y genera un reporte integrado.
/multi-role <rol1>,<rol2> [--agent|-a] [objetivo_análisis]
/multi-role <rol1>,<rol2>,<rol3> [--agent|-a] [objetivo_análisis]
security: Experto en auditoría de seguridadperformance: Experto en optimización de rendimientoanalyzer: Experto en análisis de causa raízfrontend: Experto en frontend y UI/UXmobile: Experto en desarrollo móvilbackend: Experto en backend y servidorreviewer: Experto en revisión de códigoarchitect: Arquitecto de sistemasqa: Ingeniero de pruebasImportante:
--agent inmediatamente después de especificar los roles--agent/multi-role qa,architect --agent Evaluar el plan/multi-role qa,architect Evaluar el plan --agent--agent o -a: Ejecutar cada rol como sub-agente en paralelo (recomendado para análisis a gran escala)
test cases passed, vs 12 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.