Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

ULW Loop (durable goal execution)

An execution loop skill that decomposes long-running work into goals, evidence-bound steps, and delegated background subagents.

AutomationAdvanced★ 67,531⑂ 5,507AI score 7/10Last updated: Aug 9, 2026

What it does

  • Registers large work as goals, mirrors every atomic action into a live checklist with exactly one step in progress at a time.
  • Requires observable evidence (terminal/TUI, HTTP, browser, CLI stdout, DB diff) for every success criterion, bound to the current git tree hash; passing tests alone never count as done.
  • Delegates code edits, test writing, and QA to right-sized background subagents via the native task tool, tracking WORKING: / BLOCKED: signals instead of polling.
  • Gives an explicit decision rule for when to stand up a team (per-member worktrees, per-unit merges, lead-owned conflicts) versus simply fanning out parallel workers.
  • Commits each verified unit atomically in the repository's observed message style, never in an omnibus commit.

Who it's for

  • Users of the oh-my-openagent / omo-senpi stack running multi-hour or multi-day agent work.
  • Teams that need a reliable resume procedure after context compaction.
  • Anyone who wants completion judged by real-surface evidence rather than green tests.

Examples

  1. "Run ulw-loop to refactor the billing module" → goals registered, granular checklist created, evidence recorded per step.
  2. Batch-spawn background workers for three independent features, then merge and commit each unit as its gates go green.
  3. After a context loss, re-read the brief, goals, ledger and ulw-loop status --json, then resume mid-plan instead of re-planning.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/HEAD/packages/omo-senpi/skills/ulw-loop/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the packages/omo-senpi/skills/ulw-loop folder from the GitHub repo code-yeongyu/oh-my-openagent into my ~/.claude/skills/code-yeongyu-ulw-loop/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/code-yeongyu/oh-my-openagent.git /tmp/oh-my-openagent && mkdir -p ~/.claude/skills && cp -r /tmp/oh-my-openagent/packages/omo-senpi/skills/ulw-loop ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/code-yeongyu/oh-my-openagent.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r oh-my-openagent/packages/omo-senpi/skills/ulw-loop ~/.claude/skills/
  5. Verify that references/full-workflow.md came along — the skill depends on it for the full procedure.
  6. Install the omo-agent-toolkit CLI and the omo-senpi environment per the repository README; without them the ULW state commands will fail.
  7. Restart Claude Code and ask something like "use ulw-loop to deliver X" to trigger the skill.
View source on GitHub ↗License: NOASSERTION