# Planning Design

> Planning Design is an Agent Skill for productivity published in the a5c-ai/babysitter repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Design technical architecture, select technology stack, and define implementation strategy from specifications and constitution constraints.

- Skill name: `planning-design`
- Category: [Productivity](https://www.openparable.com/skill/productivity/1)
- Source: https://github.com/a5c-ai/babysitter/blob/HEAD/library/methodologies/spec-kit/skills/planning-design/SKILL.md
- Repository: a5c-ai/babysitter (1,548 GitHub stars when collected)

## SKILL.md

- When evaluating technology stack options for a feature
- When designing system architecture for new components
- When assessing implementation risks and defining mitigations

## Key Principle

Architecture decisions must be traceable to specification requirements. Technology choices must comply with constitution constraints. Trade-offs must be documented for every significant decision.

## Process

1. **Assess technology stack** - Evaluate options against constitution requirements
2. **Design architecture** - Components, interfaces, data model, integration points
3. **Define strategy** - Phases, milestones, testing strategy, deployment approach
4. **Assess risks** - Identify risks and define mitigations
5. **Human review** - Approve architecture and strategy before task breakdown

## Tool Use

Invoke via babysitter process: `methodologies/spec-kit/spec-kit-planning`
Full pipeline: `methodologies/spec-kit/spec-kit-orchestrator`

---

Source: https://www.openparable.com/skill/productivity/planning-design (OpenParable). Cite the canonical URL above.
