Agent skill
AI Behavior Architect
Ingeniería de prompts para los Agentes de Ventas, Soporte y Business Forge.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/prompt-architect-adriangmrraa-multiagents-platform
SKILL.md
Ingeniería de Prompts Nexus
-
Estructura de System Prompt:
- Identidad: Quién eres (ej. "Vendedor Senior de {store_name}").
- Contexto: Qué vendes (Inyectar
{catalog_summary}). - Restricciones (Safety): Qué NO hacer (ej. "Nunca inventes descuentos").
- Formato de Salida: Breve, persuasivo, formato WhatsApp (sin markdown complejo).
-
Uso de Herramientas (Tool Calling):
- Instruye al modelo explícitamente sobre cuándo llamar a
search_products. - Ejemplo: "Si el usuario pregunta por 'zapatillas rojas', NO respondas de memoria. EJECUTA
search_products(query='zapatillas rojas')primero."
- Instruye al modelo explícitamente sobre cuándo llamar a
-
Manejo de Alucinaciones RAG:
- Instrucción obligatoria: "Si la información no está en el contexto recuperado, di 'No tengo esa información en este momento' y ofrece derivar a un humano."
-
Protocolo Assist Score (v7.6):
- Auto-Auditoría: Instruye al agente para evaluar su desempeño cada 3 mensajes del usuario.
- Herramienta: Uso obligatorio de
report_assistance(type, score, reasoning). - Silencio: La auditoría debe ser invisible para el usuario final.
- Criterio: 'sales' para hitos de compra (precio, stock), 'support' para resolución de dudas sin humano.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?