The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions for text transformation and platform-specific content adaptation. It does not include any scripts, executable code, or remote dependencies.
[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow to ingest user-provided content (e.g., articles, launch notes) and transform it for redistribution via platforms like X or LinkedIn. While it processes untrusted user input and references publishing tools like x-api, the instructions focus on stylistic adaptation and voice preservation. There are no patterns suggesting a risk beyond the inherent behavior of an LLM processing user text.

crosspost