The Agent Skills Directory

[SAFE]: The skill serves as a meta-utility for generating other skills. It includes a comprehensive safety audit checklist requiring generated skills to use disable-model-invocation: true for operations with side effects and mandatory approval gates before irreversible actions.- [SAFE]: No evidence of obfuscation, credential harvesting, or unauthorized data exfiltration was found. The skill promotes the use of environment variables like ${CLAUDE_PROJECT_DIR} over hardcoded absolute paths.- [SAFE]: The instructions and design patterns provided (e.g., cross-repo synchronization, phased workflows) are standard developer tasks and include explicit error handling and status reporting guidelines.- [SAFE]: The skill does not contain any remote code execution or external downloads. It correctly utilizes platform-specific features for argument handling and context management.

command-skill-creator