Ruview Hardware Setup logo

Ruview Hardware Setup

CommunityPopular
ruvnet
ruview-hardware-setup

ESP32-S3 / ESP32-C6 firmware build, flash, WiFi provisioning, and serial monitoring for RuView CSI sensing nodes. Use when setting up physical hardware, reflashing a node, or debugging a device that isn't streaming CSI.

Overview

Publisherruvnet
RepositoryRuView
Skill nameruview-hardware-setup
Stars
94.3K
Forks
12.5K
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by ruvnet on GitHub. Read the source before you install it.

Installation

Install the Ruview Hardware Setup AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ruvnet/RuView.git /tmp/RuView
mkdir -p .claude/skills
cp -r /tmp/RuView/plugins/ruview/skills/ruview-hardware-setup .claude/skills/ruview-hardware-setup
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ruview Hardware Setup in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ruview Hardware Setup on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ruview Hardware Setup is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

RuView Hardware Setup

Bring a RuView sensing node online: build firmware → flash → provision WiFi → confirm CSI stream.

Supported devices

DeviceFlashChipRole
ESP32-S3 (8MB)8 MBXtensa dual-coreWiFi CSI sensing node (default)
ESP32-S3 SuperMini4 MBXtensa dual-coreCompact CSI node — use sdkconfig.defaults.4mb
ESP32-C6 + Seeed MR60BHA2RISC-V + 60 GHz FMCWmmWave HR/BR/presence

Not supported: original ESP32, ESP32-C3 (single-core).

⚠️ Ask about board form factor before flashing. If the user's board is a coin-sized clone (ESP32-S3-Zero, SuperMini, or similar — not a full DevKitC/XIAO-style board with a real USB connector and visible regulator), warn them before they walk away from it: this firmware runs the WiFi radio continuously (WIFI_PS_NONE) plus a full DSP pipeline (edge_tier=2), which is sustained high current draw that full-size dev boards handle fine but tiny clones with minimal copper/budget regulators may not. At least one field report: boards ran hot during a normal session and failed to power on again afterward (regulator damage suspected). Tell them to give the board airflow (don't stack/enclose it) and check it by touch during the first several minutes of any new deployment.

1. Build firmware (Windows — Python subprocess, NOT bash directly)

ESP-IDF v5.4 does not support MSYS2/Git Bash. Use the Espressif Python venv as a subprocess with MSYSTEM* env vars stripped. The proven command lives in CLAUDE.local.md — reproduce it:

bash
/c/Espressif/tools/python/v5.4/venv/Scripts/python.exe -c "
import subprocess, os
env = os.environ.copy()
for k in ['MSYSTEM','MSYSTEM_CHOST','MSYSTEM_PREFIX','MINGW_PREFIX','CHERE_INVOKING']:
    env.pop(k, None)
env['IDF_PATH'] = r'C:\Users\ruv\esp\v5.4\esp-idf'
env['IDF_PYTHON_ENV_PATH'] = r'C:\Espressif\tools\python\v5.4\venv'
env['IDF_TOOLS_PATH'] = r'C:\Espressif'
env['PATH'] = (
    r'C:\Espressif\tools\xtensa-esp-elf\esp-14.2.0_20241119\xtensa-esp-elf\bin;'
    r'C:\Espressif\tools\cmake\3.30.2\cmake-3.30.2-windows-x86_64\bin;'
    r'C:\Espressif\tools\ninja\1.12.1;'
    r'C:\Espressif\tools\idf-exe\1.0.3;'
    r'C:\Espressif\tools\ccache\4.10.2\ccache-4.10.2-windows-x86_64;'
    r'C:\Espressif\tools\python\v5.4\venv\Scripts;'
    + env['PATH']
)
python = r'C:\Espressif\tools\python\v5.4\venv\Scripts\python.exe'
idf_py = os.path.join(env['IDF_PATH'], 'tools', 'idf.py')
r = subprocess.run([python, idf_py, 'build'],   # flash: [python, idf_py, '-p', 'COM8', 'flash']
    cwd=r'C:\Users\ruv\Projects\wifi-densepose\firmware\esp32-csi-node',
    env=env, capture_output=True, text=True, timeout=300)
print(r.stdout[-3000:]); print(r.stderr[-2000:]); print('RC:', r.returncode)
"
  • 8MB build: uses sdkconfig.defaults.template (no mock — real WiFi CSI).
  • 4MB build: cp firmware/esp32-csi-node/sdkconfig.defaults.4mb firmware/esp32-csi-node/sdkconfig.defaults first, then build.
  • Build outputs: firmware/esp32-csi-node/build/{bootloader/bootloader.bin, partition_table/partition-table.bin, esp32-csi-node.bin, ota_data_initial.bin}.

2. Flash to the device

Same subprocess pattern, swap [python, idf_py, 'build'][python, idf_py, '-p', 'COM8', 'flash']. Or with esptool directly:

bash
python -m esptool --chip esp32s3 --port COM8 --baud 460800 \
  write_flash 0x0 firmware/esp32-csi-node/build/bootloader/bootloader.bin \
  0x8000 firmware/esp32-csi-node/build/partition_table/partition-table.bin \
  0xf000 firmware/esp32-csi-node/build/ota_data_initial.bin \
  0x20000 firmware/esp32-csi-node/build/esp32-csi-node.bin

(The default device port in this workspace is COM8. Some docs reference COM9 — confirm with the user.)

3. Provision WiFi + sink address

Runs directly — no ESP-IDF env needed:

bash
python firmware/esp32-csi-node/provision.py --port COM8 \
  --ssid "YourWiFi" --password "secret" --target-ip 192.168.1.20 --target-port 5005 --node-id 1

# Optional ADR-060 overrides:
python firmware/esp32-csi-node/provision.py --port COM8 --channel 6 --filter-mac AA:BB:CC:DD:EE:FF

--help lists the full flag set (TDM mesh slotting, edge tier, detection thresholds, vitals window, hop channels, Cognitum Seed, swarm intervals) — see the ruview-configure skill for the table. Gotcha (issue #391): flashing replaces the entire csi_cfg NVS namespace — any key not on the CLI is erased; pass the full set you want. On Windows, provision.py --help needs PYTHONUTF8=1 to print (non-ASCII in the help text).

4. Confirm CSI stream

bash
# Serial monitor (use pyserial — idf.py monitor hangs in a subprocess)
/c/Espressif/tools/python/v5.4/venv/Scripts/python.exe -c "
import serial, time
ser = serial.Serial('COM8', 115200, timeout=1); start = time.time()
while time.time() - start < 15:
    line = ser.readline()
    if line: print(line.decode('utf-8', errors='replace').strip())
ser.close()
"

Then start the sink and watch frames arrive:

bash
cd v2 && cargo run -p wifi-densepose-sensing-server   # listens for ESP32 UDP CSI

Common issues

SymptomCauseFix
MSys/Mingw is no longer supportedESP-IDF detected Git BashUse the Python-subprocess command above with MSYSTEM* stripped
cmd.exe /C hangsInteractive prompt from Git BashDon't use cmd.exe /C — use the Python subprocess
cmake not foundWrong pathIt's cmake\3.30.2\cmake-3.30.2-windows-x86_64\bin, not cmake\3.30.2\bin
python_env not foundMissing env varSet IDF_PYTHON_ENV_PATH=C:\Espressif\tools\python\v5.4\venv
No CSI frames at the sinkWiFi not provisioned, wrong channel, or MAC filter too tightRe-run provision.py; try --channel matching your AP; drop --filter-mac
False fall alertsOld fall_thresh defaultIssue #263 raised it to 15.0 rad/s² + debounce — reflash latest firmware

Firmware release process (for maintainers)

  1. Build 8MB from sdkconfig.defaults.template (no mock)
  2. Build 4MB from sdkconfig.defaults.4mb (no mock)
  3. Save 6 binaries: esp32-csi-node.bin, bootloader.bin, partition-table.bin, ota_data_initial.bin, esp32-csi-node-4mb.bin, partition-table-4mb.bin
  4. git tag v0.X.Y-esp32 && git push origin v0.X.Y-esp32
  5. gh release create v0.X.Y-esp32 <binaries> --title "..." --notes-file ...
  6. Verify on real hardware (COM8) before publishing — always test with real WiFi CSI, not mock mode (mock missed the Kconfig threshold bug)

Reference

  • CLAUDE.local.md — exact ESP-IDF build env, paths, QEMU CI notes
  • firmware/esp32-csi-node/ — C firmware (channel hopping, NVS config, TDM protocol)
  • docs/adr/ADR-028-esp32-capability-audit.md, docs/build-guide.md, docs/TROUBLESHOOTING.md

Frequently asked questions

What does the Ruview Hardware Setup AI skill do?

ESP32-S3 / ESP32-C6 firmware build, flash, WiFi provisioning, and serial monitoring for RuView CSI sensing nodes. Use when setting up physical hardware, reflashing a node, or debugging a device that isn't streaming CSI.

Why use Ruview Hardware Setup on TypingMind?

Because you install it once and use it with any model. Ruview Hardware Setup is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ruview Hardware Setup in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ruvnet/RuView/tree/main/plugins/ruview/skills/ruview-hardware-setup. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ruview Hardware Setup?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ruview Hardware Setup?

As many as you like. As long as a model supports skills, you can use Ruview Hardware Setup with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ruview Hardware Setup AI skill free?

Yes. It is published on GitHub by ruvnet under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇