The Agent Skills Directory

[NO_CODE]: The skill consists entirely of instructional markdown (SKILL.md) and does not contain any executable scripts, binaries, or configuration files that could run code.
[SAFE]: The skill defines clear operational boundaries, explicitly instructing the agent not to perform sensitive actions such as committing code, pushing to repositories, or automatically approving pull requests.
[SAFE]: There are no indicators of data exfiltration, network operations, or sensitive file access. The skill operates solely as a text-processing and formatting assistant.
[SAFE]: The instructions include a specific safety-conscious rule for security findings (CVEs, authentication issues, or secrets), requiring the agent to switch from its terse style to full, clear prose to ensure critical risks are communicated effectively.

unslop-review