The Agent Skills Directory

[SAFE]: The skill consists solely of natural language instructions and examples for linguistic tasks. It contains no executable scripts, shell commands, or external dependencies.\n- [PROMPT_INJECTION]: No attempts to override system prompts, bypass safety guidelines, or extract internal instructions were detected. The language is focused entirely on the stated task of text compression.\n- [DATA_EXFILTRATION]: The skill does not contain any network operations, sensitive file access, or hardcoded credentials.\n- [REMOTE_CODE_EXECUTION]: No package installations, remote script downloads, or dynamic execution patterns were found.\n- [OBFUSCATION]: The content is provided in plain text with no encoded sections, zero-width characters, or homoglyphs.

semantic-compression