The Agent Skills Directory

[SAFE]: The skill contains no malicious patterns, obfuscation, or attempts to bypass AI safety guidelines. It focuses purely on guiding the agent to generate integration test code.
[NO_CODE]: The skill is composed entirely of Markdown and instructions; it does not include any scripts, binaries, or configuration files that could be executed.
[CREDENTIALS_UNSAFE]: No secrets or hardcoded credentials were found. Mentions of external services like Stripe and Supabase are restricted to instructions for mocking these services during tests.
[PROMPT_INJECTION]: The instructions do not contain any 'ignore previous instructions' or jailbreak-style commands. The persona adoption ('top-tier software engineer') is standard for task-oriented prompting.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a minimal attack surface by accepting external input via the $ARGUMENTS placeholder.
Ingestion points: The $ARGUMENTS variable in the main instruction block.
Boundary markers: None present.
Capability inventory: None. The skill generates text/code output but does not possess the ability to write to the filesystem or execute commands autonomously.
Sanitization: None present.

integration-tests