The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes the mthds-agent command-line tool to perform bundle validation and debugging. This tool is a verified resource from the author 'mthds-ai', and its execution is required for the skill's primary purpose of fixing method bundles.
[PROMPT_INJECTION]: The skill has a surface area for indirect prompt injection as it processes and acts upon external file data. 1. Ingestion points: Reads .mthds files and interprets the output of the validation command. 2. Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from obeying instructions that might be embedded within the files being repaired. 3. Capability inventory: The skill can execute CLI commands and modify files on the system. 4. Sanitization: There is no explicit sanitization step for the content of the .mthds files before the agent interprets them to determine necessary fixes.

fix