The Agent Skills Directory

[SAFE]: The skill implements a standard development workflow intended to reduce code duplication. It instructs the agent to search the local filesystem using glob and grep patterns focused on UI component directories (e.g., **/components/**, **/ui/**). These searches are appropriately scoped to the project environment and do not target sensitive system paths like .ssh or .env.
[SAFE]: No network operations, such as the use of curl or wget, are present in the instructions. The skill does not attempt to exfiltrate data or connect to external servers.
[SAFE]: There are no signs of obfuscation, credential harvesting, or attempts to override agent safety guidelines. The instructions are clear, transparent, and aligned with the stated purpose of component reuse.
[SAFE]: Although the skill processes external content (project source code and package.json), which technically presents a surface for indirect prompt injection, it lacks the dangerous capabilities (such as network access or privilege escalation) required to exploit such an injection. This behavior is consistent with the primary purpose of a code-focused assistant skill.

component-reuse-first