Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces.

**Judgement:** A strong, general-purpose task-decomposition and skill-orchestration skill that is well-aligned with the skills.sh ecosystem and well-suited for complex workflow design and automation planning. **What it does well:** - Systematically decomposes complex requests into atomic, verifiable subtasks with dependencies. - Maps tasks to a clear capability taxonomy, then formulates concrete `npx skills find` queries. - Distinguishes built-in capabilities (LLM, simple code, scheduling) from steps that truly require external skills. - Produces a structured “Task Decomposition Report” and an actionable execution plan, including skills to install and skills to create. - Provides a solid template and process for creating new, reusable skills when gaps are identified. **Main risks / limitations:** - Quality of decomposition and capability mapping is LLM-driven, so subtasks may be over/under-granular or misclassified, impacting reliability. - Skill search may miss relevant skills due to imperfect keyword selection or ambiguous task descriptions. - Encourages installation of third-party skills (`npx skills add`) which may introduce security or quality risks if not reviewed by the user. - Non-expert users may find the multi-phase process and CLI-oriented workflow somewhat complex. **Recommended scenarios:** - Users with complex, multi-step goals who want help turning them into concrete, automatable workflows. - Developers or power users planning new automations and wanting to leverage existing skills before building custom ones. - Situations where clear execution plans (with prerequisites, verification steps, and skill mapping) are needed before implementation. - Early design of new skills that should be reusable and well-documented within the skills.sh ecosystem.