ULW Loop

by code-yeongyu

ULW Loop is an AI Engineering skill for Claude Code, published by code-yeongyu in lazycodex.

3.2K stars201 forkson code-yeongyu/lazycodexAdded 2026/08/17+1% in starsRepository updated 2026/08/09

View source on GitHub Download repo ZIP

aiai-agentsclaudeclaude-codeclicodexdeveloper-toolslazylazycodexoh-my-openagentomoopenaiorchestrationtypescript

Install in seconds

Install ULW Loop

Copy ULW Loop into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/code-yeongyu/lazycodex/tree/main/plugins/omo/skills/ulw-loop ~/.claude/skills/ulw-loop

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/code-yeongyu/lazycodex.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: plugins/omo/skills/ulw-loop/SKILL.md in code-yeongyu/lazycodex
Installs to: ~/.claude/skills/ulw-loop
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What ULW Loop does

ULW Loop decomposes work into systematic, evidence-bound steps using ultrawork mode and manual QA. Use it for durable goal execution, checkpointed long-running delivery, or when evidence-led work and subagent delegation are required.

ULW Loop is cataloged under AI Engineering on DirSkills. ULW Loop comes from a repository tagged ai, ai-agents, claude, claude-code and cli.

Documentation

README

Excerpt

ulw-loop

Use this skill when the user asks for ulw-loop, ulw, durable goal execution, evidence-led work, manual QA, or checkpointed long-running delivery.

This skill is intentionally compact. The full workflow lives in references/full-workflow.md. Read only the sections needed for the current phase, then execute them exactly.

Required First Steps

Open references/full-workflow.md.
Read through Bootstrap (including its tier triage), Execution Loop, the Manual-QA channels table, and the Stop Rules before running any ULW command or recording evidence.
If the task has code edits, tests, QA, or commit work, follow the full workflow's delegation and evidence rules. Tests alone never prove done.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about ULW Loop

What else does code-yeongyu publish alongside ULW Loop?
ULW Loop is one of 25 skills that DirSkills catalogs from code-yeongyu/lazycodex, the repository it ships in. Its siblings there include Ast-Grep, Bug Fix Contribution and Codex Rules. Each one is a separate skill with its own page in this directory, installs the same way ULW Loop does, and is maintained by code-yeongyu in that same repository. The rest of the collection is listed on the code-yeongyu/lazycodex page.
How does ULW Loop compare to other AI Engineering skills?
ULW Loop ranks #641 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of ULW Loop against them. Open each page to compare what they document and how they install.