ulw-loop
ulw-loop is an Execution & autonomous loops skill for AI agents, published by code-yeongyu in the oh-my-openagent repository on GitHub. Skillspace rates ulw-loop C (71/100) and it passed the safety scan; a judge model has also reviewed it.
Goal-like loop that uses ultrawork mode to decompose work into systematic, evidence-bound steps.
- Grade
- C
- Quality
- 71 / 100
- Safety
- Passed
- GitHub stars
- 65,891
Placed #6 of 6 in the judged category final for Execution & autonomous loops.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 94 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
- Scope
- Portable: works in any project. Generic evidence-bound goal loop workflow, no repo or product specifics
Judge review
Placed #6 of 6 in the judged category final for Execution & autonomous loops.
- Trigger
55 55 - Instructions
70 70 - Specificity
80 80 - Safety
70 70 - Disclosure
78 78 - Maintenance
68 68
Correctly defers detail to a reference file, but what remains is dense, jargon-bound to one specific multi-agent tool surface, and triggered by an undefined 'ultrawork mode' phrase.
Not checked yet
- No blind task eval yet
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.