The Agent Skills Directory

[SAFE]: The skill provides utility functions for robustly parsing and validating JSON output from LLM responses. The logic focuses on standard string manipulation and JSON parsing techniques.
[EXTERNAL_DOWNLOADS]: The skill references the partial-json Node.js package. This is a well-known utility used for parsing incomplete JSON streams in interactive applications.
[INDIRECT_PROMPT_INJECTION]: The skill addresses the processing of untrusted data from LLM outputs by recommending defensive patterns such as schema validation and strict JSON parsing to ensure data integrity.

response-parser