← All skills

accuracy-safe-quantization

85 / 100 · Low risk

Fine to try.

By google-ai-edge/litert-samples (GitHub) · other · 489 stars · scanned at commit 163222b

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.

Works with any agent that supports SKILL.md skills.

What this skill can do

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'accuracy-safe-quantization' ] || [ -L ~/.agents/skills/'accuracy-safe-quantization' ]; then echo 'A skill folder named accuracy-safe-quantization already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/google-ai-edge/litert-samples' "$d" && git -C "$d" checkout --quiet '163222b0a76d2e80f959c1fc1f1918420e3b1e4d' -- 'skills/accuracy-safe-quantization' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/accuracy-safe-quantization' ~/.agents/skills/'accuracy-safe-quantization' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'accuracy-safe-quantization' ~/.claude/skills/'accuracy-safe-quantization' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for google-ai-edge/litert-samples shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/google-ai-edge/litert-samples.svg)](https://zalavijaysinh.github.io/skilltrust/repos/google-ai-edge/litert-samples/)

Score history