The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze untrusted external data in the form of project source code and configuration files.
Ingestion points: The skill reads tsconfig.json and general project code via the Check and Code Review instructions in SKILL.md.
Boundary markers: No specific delimiters or instructions are provided to differentiate between data and instructions within the audited project files.
Capability inventory: The skill uses file system read operations for auditing and file system write operations to modify tsconfig.json.
Sanitization: No sanitization or validation of the ingested content is specified.
[COMMAND_EXECUTION]: The skill recommends the execution of shell commands to verify project type safety.
Evidence: references/rule.md contains instructions for the agent or user to execute pnpm exec tsc --noEmit within the project environment.

typescript-strict-mode