Skill Spec

Scope: This creates YAML skill specifications for agentic frameworks (custom agent ecosystems). For Claude Code SKILL.md files, use /skill-creator-moat.

Generic, brand-neutral engineering capability; sourced playbooks in references//knowledge/. [DOC]

TL;DR

Generate complete skill.yaml definitions — capability modules for agents in multi-agent ecosystems. Each spec defines inputs/outputs, security, observability, interoperability contracts, and minimum 4 workflows with full step decomposition [EXPLICIT]

When to use

• Use for the skill spec capability. [EXPLICIT]
• NOT for adjacent domains — route to the matching skill. [INFERENCE]

Sub-capabilities (resource map)

Deep, evidence-tagged playbooks — open the one the task needs (ICM Layer 3, on-demand). [INFERENCE]

Procedure

1. Resolve the sub-capability; open the matching references/ playbook. [EXPLICIT]
2. Apply its decision tables; pick the strategy explicitly. [EXPLICIT]
3. Validate against the Quality Criteria and tag every claim. [EXPLICIT]

Quality Criteria

• Sub-capability resolved to one playbook. [INFERENCE]
• Claims evidence-tagged. [EXPLICIT]

Contract

• Aceptación: capability resolved to its reference playbook, applied, validated, evidence-tagged. [EXPLICIT]
• Límites: scoped to this capability; deep procedure in references/. [EXPLICIT]
• Casos borde: - Agent has no security checkpoints: Create simplified securityValidations with input validation and output sanity checks - Skill has only 2-3 workflows: Likely too narrow. [EXPLICIT]
• Supuestos: - Assumes an agentic ecosystem with defined agents, tools, and security checkpoints - Assumes the owning agent's agent.md constitution exists (reads it for grounding) - *. [SUPUESTO]
• Trade-off: depth in references keeps the SKILL.md stage contract lean (ICM). [EXPLICIT]

Packet

Capas del packet, cargables bajo demanda (disciplina ICM: una capa por vez, nunca todas juntas): references/ guías de profundidad (cargar UNA por etapa) · knowledge/ cuerpo de conocimiento · prompts/ prompts listos · examples/ salida de ejemplo · agents/ subagentes del packet · templates/ plantilla de output · scripts/ automatización local · assets/ recursos estáticos.