The Agent Skills Directory

[NO_CODE]: The skill consists entirely of markdown instructions and documentation. There are no scripts, executables, or code blocks that perform actions on the system.
[SAFE]: The skill focuses on talent acquisition workflows (bias reduction, legal compliance in interviews). It includes a robust 'Cannot Assess Without' section and explicit disclaimers regarding legal and HR advice, following best practices for high-stakes AI assistants.
[METADATA_POISONING]: No deceptive or malicious metadata was found. The author and versioning information are clear and consistent with the stated purpose.
[PROMPT_INJECTION]: No attempts to override system prompts or bypass safety guidelines were detected. The instructions use 'IMPORTANT' and 'MUST' in a benign, instructional context to ensure the quality of the generated output (e.g., ensuring jurisdiction is provided).
[INDIRECT_PROMPT_INJECTION]: While the skill ingests untrusted data (user-supplied job descriptions), its capabilities are limited to text generation with strictly defined boundary markers (Disclaimer blocks, Reviewer Checklists). It does not have access to file-write or network-send tools that could be abused via malicious JD content.

interview-guide