The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes source code files (Swift, JavaScript, TypeScript) and project metadata (package.json, expo-module.config.json) to inventory module members. This untrusted content could potentially contain instructions aimed at influencing the agent's behavior during the migration process.
Ingestion points: Reads project source code, configuration files, and dependency locks to establish the migration contract and check compatibility.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' warnings for the data being processed.
Capability inventory: The skill uses file modification and system commands including find, grep, gh, and npx.
Sanitization: No explicit sanitization or validation of the content of the files being read is mentioned.
[COMMAND_EXECUTION]: The skill uses several command-line tools for discovery and reporting.
Discovery: Uses find and grep to locate Swift macro declarations and core hooks within the project's dependencies.
Issue Reporting: Uses gh issue create to log limitations or bugs directly to the vendor repository when authorized by the user.
Feedback: Uses npx submit-expo-feedback to send structured feedback about the skill's performance to the vendor.
[EXTERNAL_DOWNLOADS]: The skill references a remote utility for feedback submission.
Vendor Utility: The command npx --yes submit-expo-feedback@latest is used to download and execute the vendor's feedback tool at runtime.

expo-migrate-module