The Agent Skills Directory

[SAFE]: The skill consists of a single markdown file containing documentation and pseudo-code. No actual executable scripts, binaries, or automated tasks are included.\n- [PROMPT_INJECTION]: The text provides structural guidance for retrieval patterns and does not contain any attempts to override safety filters, bypass system prompts, or induce restricted behavior.\n- [DATA_EXPOSURE]: The pattern describes standard codebase exploration techniques (e.g., searching for file patterns like 'src/**/*.ts'). There is no evidence of hardcoded credentials, sensitive file path targeting, or unauthorized data exfiltration mechanisms.\n- [EXTERNAL_DOWNLOADS]: The skill does not perform any network operations or download external dependencies. The only external link is to an informational guide on social media.

iterative-retrieval