The Agent Skills Directory

[SAFE]: The skill is a legitimate technical reference tool. It grounds AI responses in the established 'Command Line Interface Guidelines' (clig.dev).
[EXTERNAL_DOWNLOADS]: The skill fetches machine-readable documentation from https://clig.dev/llms.txt. This is used to ensure the agent's advice remains current with upstream changes to the guidelines. The destination is a well-known technical resource and does not involve executable code.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from an external source (clig.dev). While this represents an attack surface for indirect prompt injection, the risk is negligible because the skill does not have access to sensitive tools or the ability to perform dangerous operations. The ingested data is used strictly as a reference for generating human-readable design advice.

cli-development