The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted external data from migration artifacts to generate source code, creating a surface for indirect prompt injection.
Ingestion points: Reads configuration and schema data from source-schema.json, mapping-plan.md, and setup-requirements.md files.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided for these ingested files.
Capability inventory: Generates and writes executable JavaScript files (readers, transforms, and writers) to the local file system designed to interact with Wix APIs.
Sanitization: No explicit sanitization or validation of the input artifact content is mentioned before it is used in the code generation process.
[COMMAND_EXECUTION]: Provides instructions for running system-level commands such as ngrok http and configuring local network tunnels.
[EXTERNAL_DOWNLOADS]: Recommends the installation of external tools like ngrok via the brew package manager and describes a process for copying library code from sibling skills into the project workspace.

rp-import-codegen