The Agent Skills Directory

[SAFE]: The skill instructions in SKILL.md define standard educational writing principles such as plain language, cognitive load theory, and worked examples. These are purely linguistic and pedagogical guidelines with no technical risk.
[COMMAND_EXECUTION]: The skill includes a Python script eval/contract_check.py and a shell script eval/run-eval.sh. These are used for validation purposes (checking if required phrases exist in SKILL.md). The scripts are local, do not take external input, and perform only safe file reading operations within the skill's own directory.
[EXTERNAL_DOWNLOADS]: No external network calls, downloads, or remote code execution patterns were detected in the instructions or the evaluation scripts.
[DATA_EXFILTRATION]: The skill does not access sensitive files, environment variables, or credentials. All file access is restricted to the skill's own directory for validation.
[PROMPT_INJECTION]: No prompt injection markers or attempts to bypass safety filters were found. The instructions are focused on educational quality and readability formulas.

05-educational-clarity-writing