The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions designed to improve communication clarity. No malicious patterns, prompt injections, or obfuscated content were detected.- [NO_CODE]: There are no scripts, binaries, or command-line executions associated with this skill.- [SAFE]: The skill configuration includes disable-model-invocation: true, which restricts the agent's ability to call external tools or models, further reducing the security surface area.- [SAFE]: The reference to CONTEXT.md for 'ubiquitous language' is a standard project documentation practice and does not involve accessing sensitive system files or credentials.

wait-what-wx