The Agent Skills Directory

[SAFE]: The skill's functionality is limited to reading local files (spec.md, plan.md, tasks.md, and FRAMEWORK.md) to generate a consistency report. It does not ingest data from untrusted network sources or use external tools.
[SAFE]: Explicit guardrails are present in the instructions, specifying that the skill is read-only and must never modify any files.
[SAFE]: No suspicious patterns such as prompt injection, obfuscation, or persistence mechanisms were detected. The skill uses standard markdown instructions to guide the agent's reasoning process.

spec-kit-analyse