The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a bundled Python script (scripts/scan_docs.py) which in turn invokes standard Git commands (git diff, git status, git describe) to identify documentation drift. This is a primary functional requirement for tracking repository changes.
[PROMPT_INJECTION]: The skill is designed to read and process documentation files from an external repository, creating a surface for potential indirect prompt injection.
Ingestion points: The skill reads content from various documentation files identified by the scanner, including files with extensions like .md, .rst, .adoc, and specific files like AGENTS.md or CLAUDE.md.
Boundary markers: No specific boundary markers or explicit warnings to ignore embedded instructions are used when the agent processes the content of these files.
Capability inventory: The skill possesses file-writing capabilities, the ability to run Git commands through the provided script, and instructions to execute repository-specific documentation build tools (e.g., mkdocs, docusaurus, sphinx).
Sanitization: No content sanitization or validation is performed on the ingested documentation files before they are processed by the agent.

docs-update-expert