The Agent Skills Directory

[SAFE]: The skill is primarily instructional documentation focused on improving the quality and reliability of agent skills. It does not exhibit malicious intent or exfiltrate data.
[COMMAND_EXECUTION]: The utility script render-graphs.js uses child_process.execSync to execute the system dot (Graphviz) command. This is used locally to convert Markdown code blocks into SVG diagrams for visualization and is a standard development practice.
[DYNAMIC_CONTEXT_INJECTION]: The documentation in SKILL.md correctly identifies and explains the platform-specific !command`` syntax used for load-time execution in some environments. It provides this information as a reference for developers rather than utilizing it for malicious command injection.
[PROMPT_INJECTION]: The skill discusses techniques like 'Authority' and 'Commitment' to ensure agents follow specific workflows (like TDD). While these are techniques for behavioral modification, they are explicitly framed as methods to ensure adherence to quality standards and do not attempt to bypass core safety or ethical guardrails.

writing-skills