The Agent Skills Directory

[SAFE]: The skill focuses on providing instructional frameworks for skill creation and testing. It does not contain malicious code, data exfiltration patterns, or safety bypasses.
[COMMAND_EXECUTION]: The provided render-graphs.js script uses the local dot (Graphviz) utility to render diagrams. This is a legitimate development tool functionality and operates on local file content provided within the skill directory.
[PROMPT_INJECTION]: While the skill teaches 'Persuasion Principles' to enforce technical discipline (e.g., using 'Authority' language like 'YOU MUST'), these are meta-instructions for improving agent compliance with the skill's own methodology (like TDD) and do not target system-level safety overrides.

writing-skills