CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

66

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 concise, well-structured body that assumes Claude's competence and leads with executable commands plus a clear mmWave-vs-CSI decision table. The main weaknesses are delegated (not shown) build/flash steps, a light validation checkpoint on provisioning, and references that point to external files rather than a present local bundle.

Suggestions

Inline the firmware build/flash command sequence instead of deferring to 'ruview-hardware-setup', so the provisioning workflow is fully executable from this skill alone.

Add an explicit validate→fix→retry loop for the provision/flash step (e.g., check the serial monitor for a detected-radar line and re-run if detection fails) to strengthen workflow clarity.

Either bundle the referenced scripts/docs (scripts/mmwave_fusion_bridge.py, examples/medical/README.md, docs/user-guide.md) under references/scripts/assets, or mark them clearly as cross-skill references so progressive disclosure is verifiable.

DimensionReasoningScore

Conciseness

Lean and efficient throughout: a tight hardware table, brief command blocks, and a decision table, with no padding explaining concepts Claude already knows. Every section earns its tokens; minor parentheticals like '~$15 hardware, no wearable' carry useful information.

5 / 5

Actionability

Provides concrete, executable commands ('python firmware/esp32-csi-node/provision.py --port COM8 --ssid "WiFi" ...', 'python scripts/mmwave_fusion_bridge.py', 'node scripts/passive-radar.js') and a situation→choice decision table. Below 5 because firmware build/flash is delegated ('Build/flash as in ruview-hardware-setup') rather than shown, and the referenced scripts are not present as bundle files.

4 / 5

Workflow Clarity

Numbered sections sequence the work (firmware/fusion → host bridge → standalone use → decision table) with one confirmation checkpoint ('Confirm: serial monitor should report which radar was detected'). It is noticeably above 3's 'checkpoints missing' anchor, but lacks an explicit validate→fix→retry loop for the fragile provision/flash step, keeping it below 5.

4 / 5

Progressive Disclosure

Well-organized overview with one-level-deep references clearly signaled in a Reference section (README.md, docs/user-guide.md, scripts/..., examples/medical/README.md, ADR-094) and appropriately inline tables. Below 5 because no bundle files exist in references/scripts/assets, so the referenced paths are external/other-skill material rather than a verifiable local bundle.

4 / 5

Total

17

/

20

Passed

Description

78%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 specific, well-triggered description that names concrete hardware, capabilities, and fusion behavior with an explicit 'Use when' clause. It is comprehensive on distinctiveness and completeness, with only minor gaps in action variety and trigger-term synonyms.

Suggestions

Add a couple more concrete action verbs (e.g., 'provision', 'flash', 'bridge', 'fuse') so the capability list reads as multiple distinct actions rather than one 'set up and run' cluster.

Broaden trigger terms with natural synonyms a user might say ('occupancy', 'vitals', 'presence sensing', 'radar') to lift trigger-term coverage toward comprehensive.

Consider adding a second concrete trigger phrase (e.g., 'Use when the user asks for contactless heart-rate or breathing-rate sensing') to strengthen the 'when' guidance beyond a single deployment condition.

DimensionReasoningScore

Specificity

Names concrete devices, bands, and capabilities ('Set up and run', '48-byte fused vitals', 'MR60BHA2/LD2410 auto-detect', 'heart rate / breathing rate / presence'), covering two sensors plus fusion. Not a 5 because the verbs collapse to a single 'set up and run' action cluster rather than multiple distinct concrete actions.

4 / 5

Completeness

Explicitly answers both what (set up/run radar sensing + fusion on named hardware) and when (the 'Use when the deployment includes a millimetre-wave radar alongside or instead of WiFi CSI' clause). The 'when' is a single deployment-condition clause rather than several concrete trigger phrases, so it sits above 4's anchor but short of the multi-trigger 5.

4 / 5

Trigger Term Quality

Includes natural terms users would say ('mmWave', 'FMCW radar', 'millimetre-wave radar', 'WiFi CSI', 'heart rate', 'breathing rate', 'presence') with an explicit 'Use when the deployment includes a millimetre-wave radar alongside or instead of WiFi CSI' trigger. A few common variations (e.g., 'occupancy', 'vitals') are absent, keeping it below 5.

4 / 5

Distinctiveness Conflict Risk

Highly specific niche with named hardware (ESP32-C6, MR60BHA2, LD2410), explicit band/frequencies, and a clear 'Use when a millimetre-wave radar is present' trigger; minimal overlap risk with a generic CSI skill.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 5 missing

Warning

Total

15

/

16

Passed

Repository
ruvnet/RuView
Reviewed

Table of Contents

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.