Ulw Loop — Productivity skill for Claude Code
Self-referential loop that runs a task until Oracle-verified completion (cap 100 iterations).
How to install Ulw Loop
Installs to ~/.claude/skills/oocheol-lazyclaude-ulw-loop/SKILL.md
mkdir -p ~/.claude/skills/oocheol-lazyclaude-ulw-loop && curl -fsSL https://raw.githubusercontent.com/oocheol/lazyclaude/HEAD/commands/ulw-loop.md -o ~/.claude/skills/oocheol-lazyclaude-ulw-loop/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Ulw Loop does
description: Self-referential loop that runs a task until Oracle-verified completion (cap 100 iterations). argument-hint: "\"task\" [--completion-promise=TEXT] [--strategy=reset|continue]"
/ulw-loop
Run a task in a self-referential loop until Oracle-verified completion.
Usage
/ulw-loop "task description" [--completion-promise=TEXT] [--strategy=reset|continue]
Arguments
task— what to accomplish (required)--completion-promise— explicit condition that proves
Alternatives in Productivity
- Browser Harness JS — Self-healing browser harness that enables LLMs to complete any task 480 ★
- Chief — CLI that wraps Claude Code in a loop 396 ★
- Workflow Orchestration — A Claude Code skill for disciplined task execution with planning, verification, and self-improvement loops 113 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Slm Loop
Run a task as a bounded, gate-verified loop backed by SuperLocalMemory — iterate until an independent gate pas
Donnyclaude
Verified workflow engine for Claude Code: durable project memory, phase planning, subagents, and deterministic
Loop Task
Run a task through a maker/checker loop until done (triage → implement → verify → gate)
Dabke
Loop a task until every gate is met, acting only at high confidence
Verify Loop Skill
A Claude skill that runs a supervised, self-verifying loop on a coding task. The loop is the easy part — verif
Dev Overnight
Autonomous overnight development loop - continuously explores codebase, finds issues, fixes them, and repeats
Related Agents
Plan Coordinator
Iteratively polish a plan by launching plan-polisher in a loop until critique passes or max iterations reached
Coverage Closer
Extend tests until GNATcov reports full coverage. Use for the Coverage task of the feature workflow — adds/ext
Stp Refiner
Iteratively refine an STP document by running review, fixing findings, and re-reviewing until approved. Autono