subagent-prompt-construction

SKILL.md

λ(usecase, complexity) → subagentprompt | ∧ require(needorchestration(usecase) ∨ needmcpintegration(usecase)) ∧ complexity ∈ {simple, moderate, complex} ∧ linetarget = {simple: 30-60, moderate: 60-120, complex: 120-150} ∧ template = read(templates/subagent-template.md) ∧ patterns = read(reference/patterns.md)

∧ integration = read(reference/integration-patterns.md) ∧ apply(template, usecase, patterns, integration) → draft ∧ validate(|draft| ≤ 150 ∧ integrationscore ≥ 0.50 ∧ clarity ≥ 0.80) ∧ examples/{phase-planner-executor.md} demonstrates orchestration ∧ reference/case-studies/ provides detailed analysis ∧ scripts/ provide validation and metrics automation

Usage: See templates/subagent-template.md for structure. Apply integration patterns for Claude Code features. Validate compactness (≤150 lines), integration (≥1 feature), clarity. Reference examples/ for compact demonstrations and case-studies/ for detailed analysis.

Metodología sistemática para construir indicaciones de subagente compactas (<150 líneas), expresivas e integradas en Claude Code utilizando contratos lambda y lógica simbólica. Úselo al crear nuevos subagentes especializados para Claude Code con composición de agentes, integración de herramientas MCP o referencias de habilidades. Validado con fase-planificador-ejecutor (V_instance=0.895). Fuente: zpankz/mcp-skillset.

Ver original