The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands to automate documentation tasks. Specifically, it uses find in conjunction with sed -i to perform bulk text replacements for version synchronization across the docs/ directory. It also utilizes grep for pattern matching and git log to extract commit history for changelog generation.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted external data to generate documentation.
Ingestion points: The skill reads project configuration files (e.g., package.json, pyproject.toml), source code files (via glob_patterns for route discovery), and git commit history.
Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the processed files.
Capability inventory: The skill has the capability to read files, execute shell commands (find, sed, grep, git), and modify the local filesystem.
Sanitization: The skill does not implement sanitization or validation for the content extracted from code comments or git logs before using them in documentation templates.

documentation-specialist