The Agent Skills Directory

[COMMAND_EXECUTION]: The skill initiates its workflow by executing a Python module using the command python3 -m skills.codebase_analysis.analyze. This script orchestrates the exploration and synthesis phases.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and understand external codebases, creating a vulnerability surface for indirect prompt injection from the files being analyzed.
Ingestion points: Codebase files, tech stack patterns, and repository structure (referenced in README.md and SKILL.md).
Boundary markers: No specific delimiters or instructions to ignore embedded content are defined in the provided markdown.
Capability inventory: The skill performs deep analysis, documents findings with file references, and synthesizes recommendations via the analyze script.
Sanitization: The provided instructions do not specify any filtering or sanitization of content extracted from the analyzed codebase.

codebase-analysis