Skill of Skills
📄 skillActivePromisingmedium

vllm-project/vllm-omni

by vllm-project

A framework for efficient model inference with omni-modality models

Supported Platforms

🤖 Claude Code

Stars

5.2k

Skill Type

📖 Library & API Reference

Quality Score

89/200

License

Apache-2.0

Forks

1.1k

Last Updated

Jul 25, 2026

Discovered

Jun 11, 2026

Validation

Passed

github.com/vllm-project/vllm-omni

Quality Breakdown

89/ 200

Content Signals

○Gotchas/Edge Cases+40
✓Progressive Disclosure+30
○Trigger Description+20
○Verification/Safety+20
○Code Examples+15
✓Composability+15

Repo Health

✓Recent Activity+15
✓Scripts/Automation+10
✓Real Usage (Issues)+10
✓Single Responsibility+10
✓Config/Persistence+10
✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

medium

Requires extended permissions (shell access, subagents). Review before use.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Multiple bootstrap and installation shell scripts in .buildkite directory that could execute arbitrary commands during CI/CD pipeline initialization
  • Persistent .claude directory with custom skills configuration and agent definitions (.claude/skills/*/agents/openai.yaml) that could configure autonomous AI agent behavior
  • Hardware CI scripts (run-amd-test.sh, run-xpu-test.sh, run_npu_test.sh) with potential for system-level command execution
  • Build pipeline YAML files that trigger automated shell scripts without apparent human approval gates in the workflow
  • Pre-commit configuration (.pre-commit-config.yaml) that can execute arbitrary hooks during development workflow

Related guides

Best skills & plugins for Claude Code