The Agent Skills Directory

[COMMAND_EXECUTION]: The render-graphs.js utility script uses execSync to run system commands (dot, which) to render Graphviz diagrams from markdown files.
[DYNAMIC_EXECUTION]: The skill includes a Node.js utility script (render-graphs.js) shipped as part of the skill to process and render visual artifacts.
[PROMPT_INJECTION]: The persuasion-principles.md and testing-skills-with-subagents.md files provide advanced instructions on using behavioral pressure (e.g., 'Authority', 'Scarcity') to ensure agent compliance with documentation rules.
[INDIRECT_PROMPT_INJECTION]: The skill contains an attack surface where render-graphs.js ingests data from SKILL.md. 1. Ingestion Point: render-graphs.js reading SKILL.md. 2. Boundary Markers: Regex markers for dot blocks. 3. Capability Inventory: execSync for shell command execution. 4. Sanitization: Content is passed to the binary via stdin.
[EXTERNAL_DOWNLOADS]: Documentation references official Python packages like pdfplumber and pypdf for example use cases.

writing-skills