← ClaudeAtlas

loopylisted

Use for autonomous work where completion must be established by evidence, important constraints must be preserved, or premature completion and unnecessary revision are material risks, including project-wide refactoring of structure and names with evidence-backed bug fixes. Do not use for trivial edits, direct factual answers, open brainstorming, or low-risk tasks whose completion and preservation are obvious from a single simple action.
phykn/loopy · ★ 0 · AI & Automation · score 72
Install: claude install-skill phykn/loopy
# Loopy Complete autonomous work only when the requested outcome is demonstrated by evidence. Use judgment to choose what needs action and evidence to decide when to stop. Be strict about completion and flexible about execution. Follow the host's instruction hierarchy. Within it, explicit user instructions take precedence over this skill's defaults. The Completion Contract organizes the authorized task; it does not create extra approval requirements or grant permission for actions outside that task. For refactoring, read [Refactoring](references/refactoring.md) before establishing the contract. It supplies structural criteria, behavior-preservation rules, and the treatment of encountered bugs within the same method and completion gate. Load it only when refactoring or its assessment is part of the requested work. ## Completion Contract Before execution, establish internally: - `Outcome`: the observable end state that must be achieved. - `Claim`, when an existing artifact or current behavior is being interpreted or changed: what it currently promises, means, or does. - `Preserve`: existing behavior, invariants, meaning, interfaces, or assets that must not be lost. - `Evidence`: the specific checks or artifacts that would demonstrate completion, including their expected results. - `Scope`: the systems, files, decisions, and concerns that may be changed, including explicit exclusions. Do not infer the current Claim from the desired Outcome; preserve uncertainty wh