The Agent Skills Directory

[SAFE]: The skill implements a secure and modular design for guiding users through the creation of new AI agent skills. It uses a structured workflow (Discovery, Architecture, Craft, Validate, Deliver) that prioritizes understanding requirements before generating content, reducing the risk of accidental or inconsistent behavior.
[SAFE]: The provided validation script (scripts/validate_skill.py) performs localized structural and metadata checks on generated skill folders. The script utilizes safe parsing methods, including yaml.safe_load(), and standard Python libraries without initiating network connections or accessing sensitive system files.
[SAFE]: No malicious patterns such as prompt injection, data exfiltration, obfuscation, or persistence mechanisms were detected in the skill instructions or supporting documentation.

skill-architect