Ruview Configure logo

Ruview Configure

CommunityPopular
ruvnet
ruview-configure

Configure RuView — ESP32 sdkconfig variants, NVS provisioning, WiFi channel / MAC filter overrides (ADR-060), edge intelligence modules (ADR-041), sensing-server flags, multi-node mesh, and Cognitum Seed integration. Use when adjusting how a deployed RuView system behaves without changing code.

Overview

Publisherruvnet
RepositoryRuView
Skill nameruview-configure
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 Configure 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-configure .claude/skills/ruview-configure
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ruview Configure 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 Configure 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 Configure 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 Configuration

Everything you can tune in a RuView deployment, from a one-line provision flag to a full mesh + Cognitum Seed setup.

1. Firmware build-time config (sdkconfig)

VariantFileWhen
8MB (default)firmware/esp32-csi-node/sdkconfig.defaults.templateESP32-S3 8MB, full feature set, real WiFi CSI
4MBfirmware/esp32-csi-node/sdkconfig.defaults.4mbESP32-S3 SuperMini 4MB — display disabled, dual OTA slots (partitions_4mb.csv, ~1.856 MB each)
Heltec N16R2firmware/esp32-csi-node/sdkconfig.defaults.heltec_n16r2Heltec boards

Switch: cp firmware/esp32-csi-node/sdkconfig.defaults.<variant> firmware/esp32-csi-node/sdkconfig.defaults, then rebuild (see ruview-hardware-setup). Never test in mock mode — the Kconfig fall-threshold bug only showed up with real CSI.

2. Runtime device config (NVS via provision.py)

provision.py writes the csi_cfg NVS namespace over the serial port. Run python firmware/esp32-csi-node/provision.py --help for the authoritative flag list (on Windows force PYTHONUTF8=1 PYTHONIOENCODING=utf-8 — the help text contains non-ASCII and crashes under cp1252).

bash
python firmware/esp32-csi-node/provision.py --port COM8 \
  --ssid "WiFi" --password "secret" \
  --target-ip 192.168.1.20 --target-port 5005 \   # aggregator UDP sink (port default 5005)
  --node-id 1 \                                   # 0-255
  --channel 6 --filter-mac AA:BB:CC:DD:EE:FF       # ADR-060: pin channel + filter transmitter
Flag groupFlagsNotes
WiFi / sink--ssid --password --target-ip --target-port (5005) --node-id--node-id 0-255
TDM mesh--tdm-slot --tdm-total0-based slot index + total node count — this is how multi-node mesh is slotted
Edge processing--edge-tier {0,1,2}0=off, 1=stats, 2=vitals (ADR-041)
Detection thresholds--pres-thresh (50) --fall-thresh (15000 → 15.0 rad/s²)raise --fall-thresh to cut false falls in high-traffic areas (issue #263)
Vitals--vital-win (300 frames) --vital-int (1000 ms) --subk-count (32, top-K subcarriers)
Channel / hopping--channel (1-14 / 36-177, overrides AP auto-detect) --filter-mac --hop-channels (1,6,11) --hop-dwell (200 ms)omit --channel + set --hop-channels for ADR-061 multi-freq hopping; omit --filter-mac to capture all transmitters
Cognitum Seed--seed-url (http://10.1.10.236) --seed-token (Bearer, from pairing) --zone (lobby)
Swarm--swarm-hb (30 s) --swarm-ingest (5 s)heartbeat + vector ingest intervals
Mode--dry-run (build NVS bin, don't flash) --baud (460800) --force-partial

⚠️ NVS namespace is replaced wholesale (issue #391). Flashing rewrites the entire csi_cfg namespace — any key you don't pass on the CLI is erased. Always pass the full set you want, or use --force-partial knowingly. Read the device's current values off the serial boot log first (adaptive_ctrl / csi_collector lines) if you're unsure.

  • NVS partition images for fleet provisioning: scripts/generate_nvs_matrix.py (subprocess-first — the esp_idf_nvs_partition_gen API changed across versions).

3. Sensing server flags

bash
cd v2
cargo run -p wifi-densepose-sensing-server -- --help

# Common modes:
cargo run -p wifi-densepose-sensing-server                                  # live sink, default port
cargo run -p wifi-densepose-sensing-server -- --pretrain --dataset data/csi/ --pretrain-epochs 50
cargo run -p wifi-densepose-sensing-server -- --train --dataset data/mmfi/ --epochs 100 --save-rvf model.rvf
cargo run -p wifi-densepose-sensing-server -- --model model.rvf --embed
cargo run -p wifi-densepose-sensing-server -- --model model.rvf --build-index env

wifiscan server (multi-BSSID, ADR-022): cargo run -p wifi-densepose-sensing-server consumes wifi-densepose-wifiscan output; use neighbour APs as free radar illuminators.

4. Edge intelligence modules (ADR-041)

Small Rust/WASM programs that run on the ESP32 itself — no internet, instant response. See docs/edge-modules/ and docs/adr/ADR-041-*. Each module declares its CSI feature inputs (8-dim feature vectors) and an RVF store target (Cognitum Seed). Configure which modules ship in a build via the firmware component config; configure their thresholds via NVS keys.

Helper scripts that mirror edge-module logic on the host (useful for tuning before flashing): scripts/apnea-detector.js, gait-analyzer.js, material-classifier.js, passive-radar.js, mincut-person-counter.js, device-fingerprint.js, mesh-graph-transformer.js, material-detector.js.

5. Multi-node mesh

  • 2+ nodes give real spatial resolution. Each node provisioned to the same --target-ip sink.
  • TDM protocol + channel hopping coordinated by wifi-densepose-hardware (v2/crates/wifi-densepose-hardware/src/esp32/).
  • Cross-viewpoint fusion combines nodes — see ruview-advanced-sensing.

6. Cognitum Seed integration ($140 total BOM)

ESP32 streams CSI → bridge forwards to a Cognitum Seed for persistent RVF memory, kNN over environments, and an Ed25519 witness chain.

bash
node scripts/rf-scan.js --port 5006              # live RF room scan → Seed
node scripts/snn-csi-processor.js --port 5006    # SNN real-time learning on-Seed

See docs/tutorials/cognitum-seed-pretraining.md and ADR-028 (capability audit + witness verification).

7. App-level config

  • API: wifi-densepose-api (Axum) — config via wifi-densepose-config crate; see example.env / pyproject.toml for the v1 Python service.
  • Docker: docker run -p 3000:3000 ruvnet/wifi-densepose:latest (env-var overrides documented in README.md / docker/).
  • Dashboard: served on :3000; nvsim dashboard (ADR-092) is separate.

Reference

  • docs/adr/ (96 ADRs) — esp. ADR-022 (wifiscan), ADR-028 (capability audit), ADR-041 (edge modules), ADR-060 (channel/MAC override), ADR-061 (QEMU + mesh), ADR-081 (adaptive CSI mesh kernel)
  • CLAUDE.md / CLAUDE.local.md — crate map, build env, QEMU CI fixes
  • example.env, Makefile, firmware/esp32-csi-node/

Frequently asked questions

What does the Ruview Configure AI skill do?

Configure RuView — ESP32 sdkconfig variants, NVS provisioning, WiFi channel / MAC filter overrides (ADR-060), edge intelligence modules (ADR-041), sensing-server flags, multi-node mesh, and Cognitum Seed integration. Use when adjusting how a deployed RuView system behaves without changing code.

Why use Ruview Configure on TypingMind?

Because you install it once and use it with any model. Ruview Configure 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 Configure in TypingMind?

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

Which AI models can use Ruview Configure?

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 Configure?

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

Is the Ruview Configure 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 👇