The Agent Skills Directory

[SAFE]: The skill operates on local repository files to establish development standards. It does not attempt to exfiltrate data, access sensitive credentials, or perform obfuscated operations.
[COMMAND_EXECUTION]: The skill instructs the agent to run standard development commands such as pnpm install, pnpm test, and pnpm build. These are necessary to verify that the quality-gate setup is functional and are conducted within the local project context.
[INDIRECT_PROMPT_INJECTION]: The skill reads and interprets content from various local files to determine the project's configuration.
Ingestion points: Reads package.json, CLAUDE.md, README.md, and other project-specific documentation or configuration files.
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used when processing these files.
Capability inventory: Includes the ability to write/modify local files and execute shell commands via pnpm.
Sanitization: There is no explicit sanitization or validation of the content read from the project files before it influences agent actions.

setup-quality