fix: correct risk level from 'low' to 'safe' in 3 skills

Fixes validation errors for:
- saas-mvp-launcher/SKILL.md
- llm-prompt-optimizer/SKILL.md
- gemini-api-integration/SKILL.md

Valid risk values are: none, safe, critical, offensive, unknown

skills/gemini-api-integration/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: gemini-api-integration
 description: "Use when integrating Google Gemini API into projects. Covers model selection, multimodal inputs, streaming, function calling, and production best practices."
-risk: low
+risk: safe
 source: community
 date_added: "2026-03-04"
 ---

skills/llm-prompt-optimizer/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: llm-prompt-optimizer
 description: "Use when improving prompts for any LLM. Applies proven prompt engineering techniques to boost output quality, reduce hallucinations, and cut token usage."
-risk: low
+risk: safe
 source: community
 date_added: "2026-03-04"
 ---

skills/saas-mvp-launcher/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: saas-mvp-launcher
 description: "Use when planning or building a SaaS MVP from scratch. Provides a structured roadmap covering tech stack, architecture, auth, payments, and launch checklist."
-risk: low
+risk: safe
 source: community
 date_added: "2026-03-04"
 ---