segmentation-sam2
segmentation-sam2 is a Computer vision skill for AI agents, published by SharpAI in the DeepCamera repository on GitHub. Skillspace rates segmentation-sam2 B (87/100) and it passed the safety scan; a judge model has also reviewed it.
Interactive click-to-segment using Segment Anything 2 — AI-assisted labeling for Annotation Studio
- Grade
- B
- Quality
- 87 / 100
- Safety
- Passed
- GitHub stars
- 2,908
Placed #5 of 6 in the judged category final for Computer vision.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 100 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- No issues found
- License
- MIT
- Adoption
- Adopted by 1 other repositories, in 0 collections
- Scope
- Vendor-specific: built around one product. Segmentation via Meta's public SAM2 model
Judge review
Placed #5 of 6 in the judged category final for Computer vision.
- Trigger
55 55 - Instructions
35 35 - Specificity
45 45 - Safety
65 65 - Disclosure
55 55 - Maintenance
40 40
Mostly a JSON-lines protocol spec for a specific host app rather than a self-contained skill, with no real usage guidance beyond running an installer.
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.