The Agent Skills Directory

[COMMAND_EXECUTION]: The skill automates repository maintenance by executing shell commands including pnpm lint, pnpm build:sdk, pnpm test:sdk, and git diff. These actions are scoped to the project workspaces and represent standard CI-like workflows executed locally for development consistency.
[INDIRECT_PROMPT_INJECTION]: The skill analyzes local file content and git diffs, which introduces a potential surface for indirect prompt injection if source code or documentation contains adversarial instructions designed to influence the reviewing agent.
Ingestion points: The skill reads output from git diff and git status, as well as the content of repository files like CODING_GUIDELINES.md and source code.
Boundary markers: There are no explicit delimiters or safety instructions provided to the agent to isolate potentially untrusted content from its analysis instructions.
Capability inventory: The skill possesses the ability to execute shell commands (pnpm, git) and read local files within the monorepo scope.
Sanitization: No sanitization or filtering of the ingested file content is specified before the agent processes it for review.

tomtom-maps-sdk-js-preflight