Loop Engineering videos distilled into reusable AI skills
kangarooking/loop-engineering-skill
Skill Claude CodeCodex
A way to track the gap between what an automated agent produces and what a person actually understands. As automation creates more code or content, the person may know less about how it works.
kangarooking/loop-engineering-skill
Skill Claude CodeCodex
A guide for designing goals and completion checks in an automated loop, where an agent repeatedly performs work. It turns a vague objective into a measurable target and a clear test for knowing when the work is done.
kangarooking/loop-engineering-skill
Skill Claude CodeCodex
A blueprint for a complete repeating agent system, covering scheduled starts, isolated workspaces, project rules, connections to outside tools, separate worker and reviewer agents, and stored memory.
kangarooking/loop-engineering-skill
Skill Claude CodeCodex
A four-stage path for turning a manual AI task into a repeatable automated loop. It moves from doing the task by hand, to saving the instructions as a skill, to adding a trigger, and finally to adding verification and stored state.
kangarooking/loop-engineering-skill
Skill Claude CodeCodex
A simple model for any repeating automated process: something starts it, an action happens, and a rule decides when it stops. The start may be a schedule, a new message, or a failed build.
kangarooking/loop-engineering-skill
Skill Claude CodeCodex
A decision checklist for deciding whether a task is worth running as a repeating automated process. It checks how often the task happens, whether results can be checked automatically, whether the usage cost is acceptable, and whether the agent has the tools it needs.
kangarooking/loop-engineering-skill
Skill Claude CodeCodex
A work-and-review pattern in which one agent produces the result and a separate agent checks it. The reviewer is kept independent so it is less likely to overlook the producer's mistakes.
kangarooking/loop-engineering-skill
Skill Claude CodeCodex
A three-stage model for judging how a person or team works with AI coding tools: writing code with suggestions, managing several conversations manually, or running an automated system that starts work itself.