What problem does it solve? Creating well-formed Agent Skills that follow the Agent Skills specification is error-prone: frontmatter rules, naming conventions, directory structure, and prompt-injection risks are easy to get wrong. This Skill automates the generation, validation, and security scanning of complete skill packages. ## Core Features & Use Cases - Skill Generation: Interactively creates complete skill packages (SKILL.md, references, scripts, templates) following the Agent Skills open standard, with four skill types: basic, task, visual, and research. - Learn Mode: Fetches and studies documentation URLs, synthesizes the knowledge, and generates a skill grounded in the source material with source attribution. - Two-Level Security Scanning: Combines a regex/static-analysis Python scanner with LLM semantic review to detect prompt injection, data exfiltration, and destructive commands before installing external skills. - Use Case: A developer wants a reusable slash command for API conventions. They invoke the generator, answer a few questions, and receive a validated, security-scanned skill package ready to commit to .cursor/skills/. ## Quick Start Ask the agent to generate a new skill named api-conventions that documents your REST API design guidelines.
