The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes several shell commands to manage the game development and deployment workflow. This includes project builds (npm run build), environment-specific deployment scripts (publish.sh, gh-pages), and local utility scripts for managing Play.fun credentials (playfun-auth.js). It also uses gh and git to gather repository metadata and curl to verify the availability of the deployed game URL.
[EXTERNAL_DOWNLOADS]: The skill adds a reference to the Play.fun SDK CDN (https://sdk.play.fun/latest) within the game's index.html. This allows the game to load the necessary client-side libraries for monetization and point tracking at runtime.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it parses content from local game project files to automate its tasks.
Ingestion points: Accesses package.json, vite.config.js, src/core/EventBus.js, and .herenow/state.json to extract game metadata, configuration, and deployment states.
Boundary markers: No explicit delimiters are specified for the ingested content when the agent interpolates this data into API requests or generated source code.
Capability inventory: The agent possesses capabilities for shell command execution, file system modification, and making network requests to the Play.fun API.
Sanitization: The instructions do not define sanitization or validation procedures for the data extracted from the project files.

monetize-game