Asks a few questions, writes a one-page brief, builds a playable browser game as one HTML folder it plays and screenshots; with an engine set, a throwaway engine or paper prototype. Ends on proceed, pivot or kill. Use when the user says make me a game, wants to try a game idea or mechanic, needs a quick spike, asks to change a game it made, or says they love or hate it.
86%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The skill's only concerning content is hidden spending-limit information kept from the user and an instruction to run a browser install outside the sandbox. Both are concealment or protection-weakening, not malicious intent toward the user.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The only outsider-authored text is a third-party game the person selects and brings in via `door-in.sh`, whose code and on-page words the agent reads and screenshots, so it is low because the attacker can publish a poisoned game but cannot force delivery.
Donchitos/Claude-Code-Game-Studios
abc0de7
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.