The Agent Skills Directory

[SAFE]: The skill is composed exclusively of Markdown documentation and instructions. It contains no executable code, binaries, or scripts, ensuring that it cannot perform unauthorized actions on the host system or network.
[SAFE]: All external resources referenced in the bibliography (references/sources.md) are well-known, reputable sources within the software engineering and academic communities. These include publications from USENIX, arXiv, and official repositories of established technology companies like JetBrains and SonarSource, as well as authoritative blogs from industry experts like Martin Fowler and Robert C. Martin.
[SAFE]: The skill actively promotes security and robustness by instructing the agent to detect and prevent dangerous patterns such as package hallucinations, hardcoded fixtures in production code, and the suppression of critical exceptions. This provides a hardening layer for the code generated by the agent.
[SAFE]: No sensitive data access, credential harvesting, or exfiltration patterns were detected. The skill specifically defines its scope as portable and requires no MCP servers, network access, or API keys.

clean-code-guard