The Agent Skills Directory

[COMMAND_EXECUTION]: The utility script render-graphs.js executes the dot command (from the Graphviz suite) and the which command using Node.js child_process.execSync. This is used to render process diagrams extracted from SKILL.md into SVG files for visualization.
[SAFE]: The instructional content focuses on improving AI agent discipline and skill reliability through structured testing. While it discusses psychological principles (authority, commitment), these are applied to ensuring the agent follows technical best practices (like TDD) and do not involve bypassing safety filters or security protocols.
[SAFE]: File system operations in render-graphs.js are restricted to reading the skill's own documentation and writing to a local diagrams/ subdirectory. No sensitive system paths are accessed.
[SAFE]: All external references and documented dependencies (such as pdfplumber or Graphviz) are well-known, industry-standard tools for the described tasks.

writing-skills