Ulw Loop
A goal-like loop that decomposes work into systematic, evidence-bound ultrawork steps.
Install
npx skills add code-yeongyu/oh-my-openagent --skill ulw-loop -g -a claude-code -y- Repository
- code-yeongyu/oh-my-openagent70.6k
- Category
- Engineering
- Updated
- 3d ago
- License
- See repository
- Context cost
- Mediumabout 2,150 tokens
- Runs scripts
- No, instructions only
What it does
A goal-like loop that decomposes work into systematic, evidence-bound ultrawork steps. Use when the user wants a goal loop or durable, checkpointed execution.
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.
- Open
references/define-goal.mdand register the run's goal by it. Goal creation is NEVER skipped: shape the objective and every success criterion by that reference before any implementation. - 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.
