The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by reading repository documentation and source code to identify design patterns. * Ingestion points: Project files searched via grep and read for analysis. * Boundary markers: No specific delimiters are provided to isolate processed file content. * Capability inventory: The skill can modify local files and execute development tools (linting, testing). * Sanitization: No sanitization is mentioned for the content read from the codebase.
[DYNAMIC_EXECUTION]: The skill's instructions include running quality assurance tools like linters and test suites. This involves the execution of local scripts and binaries within the project's development environment.

normalize