probar
Skill39 starsChanged 23 days agoMITView on GitHub
Abre el simulador de chat en la terminal y corre el caso contra el cerrador, sin credenciales.
The file
Files
<!-- Copyright (c) 2026 Enrique Rocha (@soyenriquerocha) · tododeia.com · id er-ac7bc61a -->Probar
Leé blueprint/40-pruebas.md y seguilo. El procedimiento vive ahí, no acá.
El simulador escribe como un contacto y muestra qué contesta el agente. Corre con el proveedor
demo, que no es un transporte falso: reproduce entregas grabadas, los mismos bytes crudos y la
misma cabecera de firma. No pide credenciales y lo que pasa acá vale.
Tres cosas que mirar:
pasostrae seis elementos. Si trae cinco, el ciclo se cortó y la salida no valida.- Con el modo en
borrador, los pasos 3, 4 y 5 quedan ensin-confirmary no escriben nada. - Los horarios ofrecidos salen de
disponibilidad. Uno que no esté ahí es fallo.
Cuando el caso pasa, corré /revisar. Un caso en verde no es la compuerta en verde.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

