ulw-loop
Installation
SKILL.md
Loop
This is a Hermes-native loop workflow skill.
Why This Exists
loop exists for goals whose correct implementation cannot be known upfront but can be discovered through bounded cycles of definition, action, verification, and revision without confusing planned cycles with observed progress.
Do Not Use When
- The user asks for one bounded delivery cycle; use
ulw-work's delivery-boundary capability instead. - Scope and milestones are already known and only durable checkpoint/resume tracking is needed; use
ulw-work's durable-checkpoint capability. - The user gives only a north-star outcome such as revenue, stars, or adoption and declines the bounded first loop goal you proposed; stop at the proposed arena, problem and verification and wait.
- The goal is too vague to name an observable problem, next artifact, verification signal, or stop condition.
- The goal depends mainly on external waiting, adoption, revenue, or community response without observable local next actions.
- The permission profile does not allow repeated research, handoff, queue, or feedback cycles.
- The request is a check repeated on a timer inside this session, such as polling CI, a deploy, or a queue every few minutes until it changes; that is Hermes' native
/loop(an interval plus--untilor--times), which only the user can start, so name the command instead of opening a goal loop. - The work must run unattended on a schedule that outlives this session, such as hourly or nightly; use
omh-automation-blueprint, which settles overlap, missed runs, retries, and failure pauses before a Hermes cron job is created. - The request is one objective with a stated done condition that needs no interviewer, planner, researcher, or reviewer cycles; native
/goalkeeps the session on it (/goal draftwrites its completion contract), and this skill keeps the long-horizon loop engineering.