The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute local CLI commands including bun test, qlty check, and tldr. These commands are used to validate code generated during the migration process.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it processes untrusted external data.
Ingestion points: The skill reads existing code from the user-provided source_path and pattern reference files in Steps 1 and 2 to guide the migration.
Boundary markers: The instructions do not specify any delimiters or warnings to the sub-agents to ignore potentially malicious instructions embedded in the source code comments or strings.
Capability inventory: The orchestration environment has access to the Bash tool (used in Steps 2, 3, and 5) for running tests and the Write tool for creating files.
Sanitization: There is no evidence of sanitization or filtering of the content read from source files before it is used to generate implementation code and unit tests.

tdd-migrate