The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill analyzes the content of local codebases to generate a .ai-style-rules.md file, which then serves as a behavioral constraint for future agent actions. This creates an indirect prompt injection surface if the scanned project files contain malicious instructions disguised as code or comments.
Ingestion points: Project source files are accessed using Read, Glob, and Grep tools.
Boundary markers: No delimiters or explicit instructions to ignore embedded prompts are mentioned for the scanning phase.
Capability inventory: The skill utilizes Bash, Write, and Edit tools.
Sanitization: No sanitization or filtering of the scanned codebase content is defined.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute git commands, including ls-files, diff, and log, for the purpose of analyzing project scale and recent changes.

inherit-legacy-style