The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the npx package runner and shell commands (e.g., npx tsc, npm test) to validate project code and check tool versions. It also includes scripts/ts_diagnostic.py, which utilizes subprocess.run(shell=True) to execute diagnostic commands such as grep and npx. These are standard activities for a developer tool.
[INDIRECT_PROMPT_INJECTION]: The skill analyzes external project configuration files and source code.
Ingestion points: Reads package.json, tsconfig.json, and searches the src/ directory via grep.
Boundary markers: The instructions do not define specific delimiters for separating project data from agent instructions.
Capability inventory: The skill has the ability to execute shell commands and modify code via tools like ts-migrate.
Sanitization: Project configuration data is processed directly without explicit filtering for malicious payloads embedded in file contents.
[DYNAMIC_EXECUTION]: SKILL.md contains a node -e one-liner that programmatically parses package.json to identify installed tooling. This is a localized dynamic execution pattern used for project environment discovery.

typescript-expert