From lumina
Enter Play mode in Unity, capture a screenshot and runtime logs via the engine MCP, and summarize whether the scene matches intent. Use as the final verification step and whenever the user asks "does it work / show me".
How this skill is triggered — by the user, by Claude, or both
Slash command
/lumina:playtestThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Confirm the game actually runs and looks right. "Compiles" is not "works" — you must observe the
Confirm the game actually runs and looks right. "Compiles" is not "works" — you must observe the running scene.
What to check (from the GDD/plan, or $ARGUMENTS): the core loop is reachable and the scene
contains what was promised.
mcp__unity).Debug.Log from systems like the
win/lose manager).PLAYTEST: ok | issues
Observed: <what the screenshot shows>
Runtime log: <0 errors / list errors>
Matches plan: <yes / what's missing or wrong>
For the user to judge: <"fun"/feel questions you cannot answer automatically>
Update are the classic silent failure.npx claudepluginhub tapascodespace/claude-plugin --plugin luminaProvides 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.