soltar
Skill39 starsChanged 23 days agoMITView on GitHub
Pasa el paso 3 de borrador a automático, después de mostrarte los números que dicen si conviene.
The file
Files
<!-- Copyright (c) 2026 Enrique Rocha (@soyenriquerocha) · tododeia.com · id er-ac7bc61a -->Soltar
Leé blueprint/60-bandeja.md, la parte de la compuerta numérica.
La compuerta informa, no bloquea. Mostrá cada número contra su piso: borradores revisados, cuántos salieron sin corregir, objeciones que aparecieron fuera del playbook y días con la bandeja abierta.
Si cumple, cambiá el modo del paso 3 a automatico y decí en una línea qué cambia: el agente
le escribe a una persona sin preguntarte.
Si no cumple, decí qué falta y ofrecé soltar igual. Es el negocio de quien instala, no el
tuyo. Con esa respuesta lo cambiás y no lo discutís de nuevo.
Los pasos 4 y 5 no se tocan acá. Se sueltan de a uno.
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.

