The Agent Skills Directory

[COMMAND_EXECUTION]: The render-graphs.js script uses execSync to invoke the system's dot command (from Graphviz) to render diagrams. The implementation is secure as it passes input via stdin and uses a static command string, minimizing the risk of shell injection.
[EXTERNAL_DOWNLOADS]: The documentation references standard technical resources and libraries, including pdfplumber, pypdf, and docx-js. It also includes links to images hosted on Anthropic's official documentation CDN. These references are informative and originate from trusted or well-known technology sources.
[PROMPT_INJECTION]: The skill instructions use directive and authoritative language (e.g., 'YOU MUST', 'No exceptions'). In the context of this skill, these are meta-instructions designed to guide the author in creating more reliable and compliant agent documentation, rather than attempts to bypass AI safety filters or exfiltrate data.

writing-skills