ui-screenshots
ui-screenshots is a UI design craft & review skill for AI agents, published by TobiasLaross in the IntelliNest repository on GitHub. Skillspace rates ui-screenshots F (15/100) and the safety scan rated it unsafe; the rating is based on static analysis only.
Unsafe. This skill has patterns associated with malicious or dangerous behaviour. We do not recommend running it.
Capture screenshots of an IntelliNest SwiftUI UI change under several data variations (empty / loading / full / long-text / grouped / error), so the user can eyeball the result instead of trusting a green build. Use this WHENEVER you add or modify anything a user can see in the app — a new view or sheet, a restyle, a layout or spacing tweak, a Swedish copy change, an empty/error/ loading state, a list row, a dashboard button — even if the user only said "make X look like Y" and never mentioned screenshots. Build/test green is not enough: the type-checker can't see padding, ordering, truncation, contrast, or theme regressions. Primary mechanism is rendering the real SwiftUI views to PNG with sample data via ImageRenderer (no Home Assistant needed); an optional live-simulator path captures real HA data when local secrets exist. Do NOT use it for service-layer-only, test-only, refactor, or doc changes with no visible result.
- Grade
- F
- Quality
- 15 / 100
- Safety
- Unsafe
- GitHub stars
- 23
Unproven: rated by static analysis only, not yet compared head-to-head.
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.
Our review
- Architecture
- 84 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- Critical-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- destructive rm -rf on home/root
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- 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.