The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions for an AI agent to perform text editing tasks. It does not use any external tools, scripts, or network resources.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user-provided article content (untrusted data), the risk is minimal due to the lack of exploitable capabilities. \n * Ingestion points: User-provided article text processed according to instructions in SKILL.md. \n * Boundary markers: Absent; the instructions do not specify delimiters to isolate user content. \n * Capability inventory: None; the skill does not request tool access, file system writes, or network operations. \n * Sanitization: Absent; input is used directly for rewriting tasks.

edit-article