The Agent Skills Directory

[SAFE]: The skill instructions define a purely conversational workflow for information gathering and decision mapping, with no signs of prompt injection or malicious overrides.
[SAFE]: No external code, third-party dependencies, or remote network operations are present within the skill configuration.
[SAFE]: Tool usage is explicitly limited to read-only fact-finding to avoid unintended side effects or data exposure.
[SAFE]: The skill follows security best practices by requiring a final summary of decisions and explicit user confirmation before any subsequent execution begins.

grilling