The Agent Skills Directory

[SAFE]: The skill provides a structured framework for generating Claude Code agents using clear YAML frontmatter standards and markdown templates.
[SAFE]: The included agent_generator.py script is a utility for formatting and validating agent configuration data. It uses standard libraries (typing, re) and performs safe string interpolation without the use of dangerous functions like eval() or exec().
[SAFE]: No suspicious network operations, credential exposures, or data exfiltration patterns were detected. All external tool references (e.g., mcp__github, mcp__playwright) are standard platform integrations for Claude Code.
[SAFE]: The skill provides constructive safety guidance, such as advising users to run quality-focused agents sequentially to prevent system resource exhaustion.
[SAFE]: Documentation and instruction files contain no hidden commands, prompt injections, or obfuscated content.

agent-factory