OpenAgentSkill Registry Manifest
Skill: OmniTokenizer
Slug: foundationvision-omnitokenizer
Category: media-automation
Description: [NeurIPS 2024]OmniTokenizer: one model and one weight for image-video joint tokenization.

Agent fit:
- Decision: 41/100 Needs manual review
- Primary fit: Multimodal media
- Role: Needs validation

Supply profile:
- Track: Design and creative production
- Scenario: Multimodal media
- Applicable agents: Claude Code, CLI, Codex, Cursor, Python
- Maintenance: 2y since push
- Risk: Needs review

Trust:
- Trust score: 74/100 Strong shortlist
- Audit: 67/100 Needs review

Attribution:
- Status: Community indexed
- Source: GitHub star discovery
- Creator: FoundationVision
- Claim URL: https://www.openagentskill.com/skills/foundationvision-omnitokenizer#claim-this-skill

Install:
npx skills add FoundationVision/OmniTokenizer

URLs:
- Web: https://www.openagentskill.com/skills/foundationvision-omnitokenizer
- API: https://www.openagentskill.com/api/agent/skills/foundationvision-omnitokenizer
- Install API: https://www.openagentskill.com/api/skills/foundationvision-omnitokenizer/install
- Repository: https://github.com/FoundationVision/OmniTokenizer