OpenAgentSkill Registry Manifest
Skill: accuracy-safe-quantization
Slug: google-ai-edge-accuracy-safe-quantization
Category: research
Description: Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task benchmark, or degenerates over long generations, or when deciding between dynamic-range, weight-only, and blockwise variants.

Agent fit:
- Decision: 72/100 Strong shortlist
- Primary fit: Browser automation
- Role: Companion skill

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

Trust:
- Trust score: 65/100 Manual review
- Audit: 76/100 Risky

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

Install:
npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization

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