The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown documentation and configuration files (SKILL.md and references/current-guidance.md). It contains no scripts, binaries, or executable logic.
[SAFE]: All instructions relate to internal reasoning and workflow classification (e.g., determining if a request is clear-scoped vs vague-action). There are no network operations, file system modifications, or sensitive data access patterns. The mention of scripts/workflow.py in the documentation refers to an external tool expected in the environment, not code provided or executed by this skill.

request-triage