The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts (validate_design_system.py and export_tokens.py) to perform its primary functions. These scripts are provided within the skill package and do not perform network operations or access sensitive system paths.
[DYNAMIC_EXECUTION]: The skill utilizes Python scripts to process design token JSON files and generate downstream artifacts like CSS and Tailwind configurations. These scripts include safety measures, such as a depth limit for resolving nested token aliases to prevent resource exhaustion attacks.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and audit existing workspace files (e.g., README.md, package.json, CSS files). It manages this risk through a structured 'Gate' workflow, explicit non-negotiable rules for token architecture, and instructions to verify findings against manual evidence and baseline matrices.
[SAFE_PRACTICE]: The included validation script (validate_design_system.py) actively scans the generated design artifacts for hardcoded secrets, private keys, and API tokens, reporting them as errors if found. This demonstrates a strong security-first approach to artifact generation.

design-system