Use when launching anything that runs longer than a minute, anything that streams logs, anything you want to keep running while doing other work — or when terminal_exec auto-backgrounded on you and returned a job_id. Teaches the start→poll→wait pattern with terminal_job_logs offset bookkeeping, bounded blocking polls, platform-specific process control via terminal_job_manage capabilities, and the hard rule that jobs die when the terminal-tools server restarts. Read before calling terminal_job_start, or right after terminal_exec auto-backgrounded.
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 required workflow involves reading logs and output from terminal background jobs via terminal_job_logs, which can process arbitrary process output and logs generated by outsider-influenced or user-executed programs.
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.