Stats
Actions
Tags
From Unity MCP
Safety model for AI-driven Unity changes: read-only first, batch-first, dry-run, confirmation, rollback, and audit-friendly reporting.
How this skill is triggered — by the user, by Claude, or both
Slash command
/unity-mcp:unity-safety-risk-guideThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use whenever a task may modify scenes, assets, project settings, packages, prefabs, or build targets.
Use whenever a task may modify scenes, assets, project settings, packages, prefabs, or build targets.
dryRun and confirmationToken where supported.unity_mcp_safety_manifest or unity_mcp_safety_describe to inspect risk and confirmation token details.confirmationToken only after explaining the risk.npx claudepluginhub karnelian/unity-mcp --plugin unity-mcpProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.