The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the agent to verify material claims in technical documentation by executing relevant commands, as noted in SKILL.md ("Execute the claim when doing so is safe, authorized, and proportionate") and resources/docs-quality.md.
[COMMAND_EXECUTION]: The resources/docs-quality.md file contains specific Git command examples (git log, git show, git blame, etc.) intended for investigating repository history to verify technical behavior described in documentation.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external technical documents which may contain instructions that could influence the agent's behavior.
Ingestion points: The skill is invoked during the drafting, rewriting, or editing of technical documents (SKILL.md).
Boundary markers: No specific delimiters or instructions to ignore embedded prompts within the processed documentation are present.
Capability inventory: The skill allows for command execution (Git and verification commands) and file system interactions related to documentation maintenance.
Sanitization: There is no evidence of content sanitization or validation for the processed document data.

technical-writing