ruview-mmwave

Set up and run RuView mmWave / FMCW radar sensing — ESP32-C6 + Seeed MR60BHA2 (60 GHz, heart rate / breathing rate / presence) and HLK-LD2410 (24 GHz, presence + distance), plus mmWave↔WiFi-CSI sensor fusion (48-byte fused vitals, MR60BHA2/LD2410 auto-detect, v0.5.0+). Use when the deployment includes a millimetre-wave radar alongside or instead of WiFi CSI.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, token-efficient reference skill: dense hardware table, executable provisioning command, and a genuinely useful decision table for mmWave vs. WiFi CSI. It falls short of top marks on inline version-sensitive details, bare host-side script invocations, and the absence of a no-radar-detected recovery path.

Suggestions

Add an error-recovery branch to the firmware workflow (e.g., 'if the serial monitor reports no radar detected, check wiring/UART pins and re-provision'), turning the confirm step into a validate → fix → retry loop.

Give the host-side commands a complete common-case invocation: expected arguments for scripts/mmwave_fusion_bridge.py and scripts/passive-radar.js (output topic, serial port, CSI source) so they are copy-paste ready like the provision.py command.

Move version-sensitive specifics (v0.5.0+ binary-size delta, firmware tag recommendations) into the already-referenced docs/user-guide.md release table and keep only the pointer in SKILL.md.

Dimension	Reasoning	Score
Conciseness	Lean and dense — the hardware table and terse pointers ('ESP-IDF v5.4 ≠ Git Bash') assume competence and skip known concepts. However, version-sensitive details ('Binary is ~12 KB larger', 'v0.5.0+', '~22 ms pipeline, 19K+ pts/frame') sit inline instead of behind the referenced release table.	4 / 5
Actionability	The provision.py command is copy-paste ready with args and an expected-outcome comment, but the host-side invocations (mmwave_fusion_bridge.py, passive-radar.js) are given bare with no arguments, prerequisites, or expected output — mostly executable with minor gaps.	4 / 5
Workflow Clarity	Sections 1-4 form a coherent firmware → bridge → standalone → selection sequence with an explicit checkpoint ('Confirm: serial monitor should report which radar was detected') and a closing validation pointer (ruview-verify, QEMU helpers). It lacks an error-recovery branch (e.g., what to do if no radar is detected).	4 / 5
Progressive Disclosure	No bundle files exist; the body organizes content into clear sections with a dedicated, well-signaled 'Reference' section pointing one level deep to repo paths and a cross-skill pointer (ruview-hardware-setup). Minor gaps: 'ADR-094' is cited without a path, and referenced files are not part of a verifiable bundle.	4 / 5
	Total	16 / 20 Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person, dense with concrete hardware and capability terms, with an explicit and well-scoped 'Use when' clause. The only soft spot is that the action list ('set up and run') is thinner than the capability enumeration around it.

Dimension	Reasoning	Score
Specificity	Names concrete devices, bands, and capabilities (heart rate / breathing rate / presence / distance, 48-byte fused vitals, auto-detect) but offers only 2-3 distinct action verbs ('Set up and run', fusion), leaving minor coverage gaps versus the comprehensive multi-action anchor.	4 / 5
Completeness	Explicitly answers both 'what' (devices, capabilities, fusion output) and 'when' via a concrete 'Use when the deployment includes a millimetre-wave radar alongside or instead of WiFi CSI' trigger clause.	5 / 5
Trigger Term Quality	Comprehensive natural terms with synonyms — 'mmWave', 'FMCW radar', 'millimetre-wave radar', 'presence', 'heart rate', 'breathing rate', 'distance', 'sensor fusion', 'WiFi CSI' — plus exact model names (MR60BHA2, LD2410, ESP32-C6) a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (mmWave/FMCW radar sensing with named hardware) and it explicitly draws the boundary against the WiFi-CSI skill, so it is unlikely to trigger for the wrong skill.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 5 missing	Warning

	Total	15 / 16 Passed

Repository: ruvnet/RuView
Path: plugins/ruview/skills/ruview-mmwave/SKILL.md
Commit: 5ef001b

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.