The Agent Skills Directory

[COMMAND_EXECUTION]: The workflow involves running npx @ui5/linter, npm test, and mvn verify. These are standard development commands used for linting and executing local test suites during the modernization verification phases.
[PROMPT_INJECTION]: The skill processes project source code and linter output which presents a surface for indirect prompt injection.
Ingestion points: The skill reads project files (JavaScript, XML, JSON) and linter output logs from the local file system.
Boundary markers: The skill relies on specific structural instructions to sub-agents rather than explicit data delimiters or 'ignore' warnings for the ingested content.
Capability inventory: The skill has the capability to modify files, perform git commits, and execute shell commands (npm and Maven).
Sanitization: No explicit sanitization or escaping of the ingested project code is performed before it is processed by the agent.
[SAFE]: The skill demonstrates security awareness by instructing the agent to update .gitignore to prevent the accidental commitment of local test artifacts and temporary configuration files like headless-chrome.json.

modernize-ui5-app