visual-ralph
visual-ralph is a Design-to-code & prototyping skill for AI agents, published by Yeachan-Heo in the oh-my-codex repository on GitHub. Skillspace rates visual-ralph D (64/100) and it passed the safety scan; a judge model has also reviewed it.
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
- Grade
- D
- Quality
- 64 / 100
- Safety
- Passed
- GitHub stars
- 33,124
Placed #1 of 2 when judged against its near-duplicates in Design-to-code & prototyping.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 99 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- Low-risk patterns
- License
- Not declared. Check the repository before reusing it.
Judge review
Placed #1 of 2 when judged against its near-duplicates in Design-to-code & prototyping.
- Trigger
85 85 - Instructions
93 93 - Specificity
92 92 - Safety
85 85 - Disclosure
90 90 - Maintenance
90 90
More complete and DRY: delegates shared invariants to templates/AGENTS.md and defines a measurable score>=90 verdict schema plus explicit stop conditions and a handoff template.
What the scanner flagged
- mentions secrets in text
Not checked yet
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- 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.