The Agent Skills Directory

[SAFE]: The skill's primary purpose is to simplify code without altering its behavior. The instructions are transparent and focused on developer productivity and code quality.- [PROMPT_INJECTION]: The skill provides instructions to read project-specific documentation such as AGENTS.md and CLAUDE.md to align with repository conventions. This ingestion of untrusted local data represents a surface for indirect prompt injection if those files were to contain malicious instructions targeting the agent's behavior.
Ingestion points: AGENTS.md, CLAUDE.md, and project source code files.
Boundary markers: Absent; the skill does not define specific delimiters to isolate external project instructions from its core logic.
Capability inventory: SKILL.md (specifies code refinement via file writing and execution of validation checks via subprocess tools).
Sanitization: Absent; the skill does not specify any validation or filtering of the content read from documentation files.

simplify