The Agent Skills Directory

[SAFE]: The skill uses official GitHub CLI commands (gh run list, gh run view, gh run watch) and Git commands to resolve the current state of CI workflows.
[SAFE]: The configuration limits tool access to a safe subset (gh, git, Read, Monitor).
[SAFE]: No external network calls are made outside of standard GitHub API interactions through the gh CLI.
[SAFE]: No evidence of prompt injection, data exfiltration, or persistence mechanisms was detected.
[SAFE]: The skill includes clear operational guardrails, such as prohibiting unauthorized commands and enforcing timeouts via built-in platform tools.

watch-ci