The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run yarn prettier --write <file-path> to ensure consistent formatting across documentation files. This is a standard development practice using a well-known tool.
[INDIRECT_PROMPT_INJECTION]: The skill processes existing documentation files as part of its editing and writing workflow.
Ingestion points: Uses Read, Grep, and Glob tools to ingest content from project files.
Boundary markers: None explicitly defined for untrusted data input.
Capability inventory: Includes Write and Bash capabilities for modifying files and running formatting commands.
Sanitization: No explicit sanitization or filtering of input content is mentioned.
Risk Assessment: As the skill's primary purpose is documentation editing, the exposure to untrusted data is inherent to the task and managed by the AI's internal safety guidelines.

docs-write