The Agent Skills Directory

[SAFE]: The skill is purely instructional and defines writing principles and formatting rules for producing clear and accessible prose. It does not contain any executable code or sensitive operations.
[NO_CODE]: No scripts, executables, or code files are included with this skill.
[PROMPT_INJECTION]: The skill accepts user-provided text through the target argument, creating a surface for indirect prompt injection. However, the risk is negligible as the skill lacks any dangerous capabilities like network or file access. * Ingestion points: target argument in SKILL.md. * Boundary markers: Not explicitly defined. * Capability inventory: None. * Sanitization: Not present.

govuk-style