OpenAgentSkill Registry Manifest
Skill: on-device-verification
Slug: google-ai-edge-on-device-verification
Category: research
Description: Prove a converted or quantized LiteRT model on the actual device via the CompiledModel API - confirm GPU residency, compare device output against the source model, and diagnose device-only failures such as silent CPU fallback, whole-graph compile ceilings, and fp16 range breaks. Use after conversion or quantization, when device output is wrong or NaN, when a clean graph fails to compile only on device, or when GPU and CPU outputs are suspiciously identical.

Agent fit:
- Decision: 72/100 Strong shortlist
- Primary fit: Research agents
- Role: Companion skill

Supply profile:
- Track: Research and knowledge work
- Scenario: Research agents
- Applicable agents: Claude Code, CLI, Codex, Cursor
- Maintenance: 3d since push
- Risk: Needs review

Trust:
- Trust score: 76/100 Strong shortlist
- Audit: 81/100 Needs review

Attribution:
- Status: Registry indexed
- Source: recursive skill source sync
- Creator: google-ai-edge
- Claim URL: https://www.openagentskill.com/skills/google-ai-edge-on-device-verification#claim-this-skill

Install:
npx skills add google-ai-edge/litert-samples --skill on-device-verification

URLs:
- Web: https://www.openagentskill.com/skills/google-ai-edge-on-device-verification
- API: https://www.openagentskill.com/api/agent/skills/google-ai-edge-on-device-verification
- Install API: https://www.openagentskill.com/api/skills/google-ai-edge-on-device-verification/install
- Repository: https://github.com/google-ai-edge/litert-samples/tree/main/skills/on-device-verification