Turn a workflow you just performed into a pre-filled loop blueprint. Use when the user says "turn what I just did into a loop", "distill my recent work", "make a loop out of this session", or otherwise wants to automate a multi-step task they already did by hand. Reads the current session transcript, judges whether it fills the loop blueprint, drafts the seven answers from evidence (never fabricating), and hands off to loop-builder to run the interview and scaffold. It never scaffolds loops itself.
Capture, review, and file a bug report or feedback as a GitHub issue under the user's OWN account. Use whenever the user wants to report a bug, give feedback, file an issue, or review collected feedback about loop-builder or a loop it generated. Sanitizes private content and requires explicit consent before any public issue is filed.
Use when doing alpha things on a schedule.
Use when doing beta work across multiple lines that fold together.
Use for X | Y | Z choices.
Design and scaffold an agent "loop" — an unattended, scheduled, self-verifying agent workflow. Use this whenever the user wants to automate a recurring task, schedule an agent, run an agent unattended or overnight, set up monitoring, triage, or alerting, poll something on a cadence, or turn a manual repeated workflow into a self-running one — even if they never say the word "loop." If a request implies "do this every day / on a schedule / until some condition holds, without me typing each time," reach for this skill. It walks the seven-question blueprint, picks the simplest loop pattern, and scaffolds the six building blocks (schedule, isolation, skill, connectors, verifier, state) with a human-gate list and a budget.