pstack-author-skill
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for organizing, writing, and testing AI agent skills across different platforms (Claude Code, Codex, Grok, Cursor).
- [SAFE]: It references project-specific scripts like
scripts/roles.pyandscripts/build.py, which are used for standard testing and build processes within the 'pstack' ecosystem. - [SAFE]: Command execution recommendations (e.g.,
ln -sfn,python3,readlink) are limited to development environment setup and local verification tasks. - [SAFE]: The use of
delegate_taskis documented for the purpose of 'fresh-child' testing to ensure newly created skills work as intended without residual session memory.
Audit Metadata