Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).
94%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The workflow reads output from locally run commands the agent launches (build logs, `kubectl logs -f` from the org's own `commonly-dev` backend deployment), and an outsider could only influence that text indirectly, such as by sending requests whose payloads get logged, so this is at most low rather than a monitored feed outsiders can post into.
Team-Commonly/commonly
86eb6a1
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.