The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes several local utility scripts (check-ai-patterns.js, check-degeneration.js, normalize-punctuation.js, and author_memory_commit.py) to perform stylistic analysis and manage a local state of author preferences. These scripts are executed within the agent's environment to process data locally.
[DATA_EXPOSURE]: The skill includes instructions to check for the presence of platform-specific configuration directories (e.g., .claude/agents/, .opencode/agents/) to verify compatibility and determine the appropriate execution mode for subagents. This activity is focused on environment detection for functional purposes.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided novel text, which represents an attack surface for indirect prompt injection. The skill mitigates this by using deterministic, regex-based local scripts for its primary detection and cleanup tasks, ensuring that user data is treated primarily as a target for stylistic transformation rather than a source of commands.

story-deslop