# Optimization Policy Designer

> Use when reading or modifying the rule content and editable definition of the exact SmartCMP cost-optimization policy selected by an embedded policy-editor page Context.

- Skill: `cloudchef/optimization-policy-designer` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add cloudchef/optimization-policy-designer`
- Raw SKILL.md: https://api.skillmd.com/api/skills/cloudchef/optimization-policy-designer/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: CloudChef (https://skillmd.com/u/cloudchef)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/cloudchef/optimization-policy-designer

---


# optimization-policy-designer

Read the current saved cost-optimization policy and produce user-directed replacement content.

## Workflow

1. Always call `smartcmp_read_current_optimization_policy` first. Never ask for a policy ID already supplied by page Context.
2. Treat the returned rule, scope, resource types, severity, remediation text, notifications, and task definition as one policy contract.
3. Apply only the requested change. Preserve unrelated fields and the current expression language.
4. Return the complete updated `ruleContent` with no ellipses. If any other editor field changes, return a complete JSON object containing every changed field and its full replacement value.
5. Call out assumptions when the current policy or user request lacks metric, billing, resource-state, or remediation evidence. Never fabricate a metric or Provider field.
6. State that the output is for manual review and copying into CMP. Do not claim that the policy was saved, enabled, executed, or published.

## Safety

- No policy or remediation write APIs.
- No recommendation execution.
- Keep cost-optimization category and resource-type gates intact unless the user explicitly asks to change them.