The Agent Skills Directory

[SAFE]: The skill consists entirely of behavioral instructions and checklists designed to improve the accuracy and reliability of an agent's work. It does not include executable code, script execution, or network requests.
[SAFE]: The instructions mandate the use of standard development tools (like test runners and linters) that are expected to be present in the user's environment. It does not attempt to install new or untrusted dependencies.
[SAFE]: The verification process includes checking version control diffs and re-running critical commands personally rather than trusting reports from other sub-agents, which acts as a safeguard against potential errors or malicious inputs from external sources.

verifying-completion