The Agent Skills Directory

[PROMPT_INJECTION] (LOW): The skill uses aggressive imperative language to override the agent's autonomous behavior and bypass standard operational guidelines. Evidence: 'IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT. This is not negotiable. This is not optional. You cannot rationalize your way out of this.'
[PROMPT_INJECTION] (LOW): It explicitly instructs the agent to suppress its own reasoning and context-gathering steps, labeling them as 'Red Flags'. Evidence: The skill instructs the agent to stop thinking 'I need more context first' or 'I can check git/files quickly' and instead force a tool invocation.
[PROMPT_INJECTION] (LOW): It establishes a dangerously low threshold for tool invocation, which forces the agent to load and potentially execute content from external files with minimal relevance. Evidence: 'Even a 1% chance a skill might apply means that you should invoke the skill to check.'

using-superpowers