agent-development

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • Agent Architecture Guidance: The skill provides detailed instructions on creating agent configurations using YAML frontmatter and Markdown. It emphasizes the principle of least privilege by recommending restricted tool access for agents.
  • System Prompt Design Patterns: Multiple files define structured approaches to writing system prompts, focusing on core responsibilities, process steps, and output formatting. These patterns are designed to improve agent autonomy and reliability.
  • Validation Utility: The inclusion of scripts/validate-agent.sh provides a local mechanism for developers to verify the integrity and structure of their agent files. The script uses standard Unix utilities (grep, sed, awk) for static analysis of local files and does not perform any network operations or access sensitive system directories.
  • Educational Resource: The skill serves as an educational repository with various examples (Code Reviewer, Test Generator, Security Analyzer) that demonstrate how to implement domain-specific experts securely and effectively.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 11:08 AM