The Agent Skills Directory

[SAFE]: The skill is purely instructional and defines a manual review process for Markdown formatting. It does not include any executable code, scripts, or automated tools.
[DATA_EXFILTRATION]: No network operations or sensitive data access patterns were identified. The skill only processes the Markdown content provided by the user within the agent's context.
[PROMPT_INJECTION]: There are no instructions that attempt to bypass AI safety guidelines or override the agent's core behavior. The examples provided are consistent with the skill's stated purpose of linting document formatting.
[EXTERNAL_DOWNLOADS]: The skill references external documentation for attribution (Markdown Guide and Google Style Guide) but does not download or execute any remote content.
[COMMAND_EXECUTION]: The skill does not invoke shell commands, subprocesses, or external binaries. It relies entirely on the agent's native capabilities to read and edit text with user approval.

markdown-style