What is tflite-micro-integration?

An integration guide for TensorFlow Lite Micro, Google's runtime for running machine-learning models on microcontrollers. It covers registering model operations, reserving memory, loading inputs, and running the model.

Use it to run a .tflite model on an MCU with the correct operations, memory arena, tensor allocation, and int8 input format.

It helps resolve missing-operation errors, insufficient memory, incorrect integer input scaling, and empty or drifting results during inference.

tflite-micro-integration — Skill for Claude Code and Codex by easyzoom

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add easyzoom/aix-skills --skill tflite-micro-integration

Clone the repo

git clone --depth 1 https://github.com/easyzoom/aix-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/easyzoom/aix-skills/tflite-micro-integration/github.svg)](https://agentmods.dev/skills/easyzoom/aix-skills/tflite-micro-integration)

Your own site

<a href="https://agentmods.dev/skills/easyzoom/aix-skills/tflite-micro-integration"><img src="https://agentmods.dev/badge/skills/easyzoom/aix-skills/tflite-micro-integration/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/easyzoom/aix-skills/tflite-micro-integration"><img src="https://agentmods.dev/badge/skills/easyzoom/aix-skills/tflite-micro-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,338 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00047	$0.01338
Opus 5	$0.00023	$0.00669
Sonnet 5	$0.00009	$0.00268
Haiku 4.5	$0.00005	$0.00134

Measured 6d ago against content hash 71589ff9bfd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tflite-micro-integration scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/tflite-micro-integration/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TensorFlow Lite Micro Integration

Overview

Use this skill to bring up TensorFlow Lite for Microcontrollers (TFLM / LiteRT for Microcontrollers) on an MCU: register exactly the ops the model uses, size the tensor_arena correctly, and quantize inputs so Invoke() returns valid output. Most failures are missing ops, an undersized arena, or unquantized input, not model logic. TFLM is Google's official microcontroller runtime and is integrated by several vendor toolchains — Espressif esp-tflite-micro (with ESP-NN kernels), NXP eIQ, and ST X-CUBE-AI, where TFLM is available as an optional runtime alongside ST's own proprietary Cube.AI runtime. Use tinymaix-integration instead when you want a lighter, dependency-free runtime.

When To Use

Use this skill when:

The user runs tensorflow/tflite-micro and works with tflite::MicroInterpreter, tflite::MicroMutableOpResolver, AllocateTensors(), or Invoke().
The build or runtime hits Didn't find op for builtin opcode 'CONV_2D', 'QUANTIZE', arena/AllocateTensors failures, or output that is all zeros or drifting.
The project embeds a .tflite model as a C array (xxd -i) and needs int8 scale/zero_point handling.

Do not use this skill when the model is not yet converted and quantized to .tflite; run the TFLite converter and validate on the host first.

First Questions

Ask for:

Target core, RAM/flash, and toolchain; whether CMSIS-NN / ESP-NN / vendor kernels are used.
The .tflite model, its op list (from Netron or flatc), and its input/output dtype (int8, uint8, or float32).
Current kTensorArenaSize and whether AllocateTensors() returns kTfLiteOk.
Input scale/zero_point and expected output; a known golden input/output pair.
Exact symptom: link error, missing-op error, allocation failure, or wrong output.

Integration Checklist

Convert and embed the model. Produce a quantized .tflite, then xxd -i model.tflite > model.cc. Reference it via tflite::GetModel(g_model) and check model->version() != TFLITE_SCHEMA_VERSION.

Read the full file on GitHub · 83 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

6d ago First seen · 83 lines · 47 tokens per session scan A 71589ff9bfd6

Subscribe to this mod's changes

tflite-micro-integration is a skill published in the GitHub repository easyzoom/aix-skills (31 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 1,338 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Data and AI Hardware and IoT agent-skills ai-agents ai-workflows automation claude-skills cortex-m

json-parser

Parse and validate JSON data from construction APIs, IoT sensors, and BIM exports. Transform nested JSON to flat DataFrames.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 28 tokens

container-home

Answer questions, assist with planning, and help with design decisions for Mick's off-grid shipping container lake home project. Trigger when the user mentions the container home, lake home, Stewart County, LBL, the expansion, solar system, septic permitting, or retirement property.

mickpletcher/AI-Skills · 57 tokens

tflite-micro-integration