The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is intended to process and audit documentation and code comments which are external, potentially untrusted sources of data. Ingestion points: Markdown files (*.md), JSDoc blocks, and source code comments. Boundary markers: The instructions do not define delimiters or explicit rules to separate analyzed text from agent instructions. Capability inventory: The skill uses git ls-files, wc, and grep for analysis and performs file moves and structural edits. Sanitization: There are no instructions to sanitize or escape documentation content before it is processed by the agent.
[COMMAND_EXECUTION]: The skill provides a specific shell command pipeline for word count analysis: git ls-files '*.md' ':(exclude)vendor/**' | xargs wc -w | sort -rn | head -30. This is a benign read-only operation used to identify documentation outliers relative to word budgets.

doc-standards