The Agent Skills Directory

[SAFE]: No malicious patterns, prompt injections, or obfuscation techniques were detected in the skill instructions or supporting files.
[SAFE]: The skill uses local file system tools (Read, Write, Edit, Bash) to manage project-specific marketing artifacts. All file paths are scoped to the expected project directories (.agents/mkt/, brand/, research/).
[SAFE]: The multi-agent architecture is well-defined and serves the legitimate purpose of decomposing a complex creative task into manageable steps with validation gates.
[SAFE]: External communication is limited to instructions for human designers or well-known third-party tools (Claude.ai, Figma) as part of a standard hand-off workflow.
[SAFE]: The author context (hungv47) and the complexity of the provided rubrics (4-U, PAS, CP-01-13) indicate a high-quality, professional tool for marketing optimization.

lp-brief