The Agent Skills Directory

[SAFE]: The skill follows a structured analysis framework to understand objectives, validate assumptions, and research codebase patterns. It operates within expected development tool scopes (git, node, and filesystem access) to provide implementation roadmaps.
[INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided input through the $ARGUMENTS variable which is processed by a sub-agent. This ingestion point lacks explicit boundary markers or instruction-ignoring delimiters, creating a standard surface for indirect prompt injection common to LLM-based analysis tools. However, the risk is inherent to its primary purpose of analyzing user proposals.

deep-analyze