CtrlK
BlogDocsLog inGet started
Tessl Logo

ruview-advanced-sensing

Advanced RuView capabilities — RuvSense multistatic sensing (attention-weighted fusion, geometric diversity, persistent field model), cross-viewpoint fusion across multiple nodes, RF tomography (ISTA L1 solver, voxel grids), longitudinal biomechanics drift, pre-movement intention signals, adversarial signal detection, and multistatic mesh security hardening. Use for research-grade or multi-node deployments.

56

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./plugins/ruview/skills/ruview-advanced-sensing/SKILL.md
SKILL.md
Quality
Evals
Security

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.

The body is a dense, well-structured reference that respects Claude's intelligence and points precisely into a large codebase via module tables, ADR numbers, and runnable scripts. It is highly actionable and concise; the main room for improvement is adding an explicit error-recovery feedback loop in the validation workflow.

Suggestions

Add an explicit feedback loop to the validation block (e.g., 'If cargo test fails, fix the failing module and re-run before proceeding to verify.py').

Consider extracting the long module tables into a references/ file (e.g. MODULES.md) and pointing to it from the overview, which would tighten the main body and improve progressive disclosure toward a 5.

Tighten or remove conversational openers like "The deep end:" and "more nodes, more independent looks, tighter localization" to nudge conciseness toward a 5.

DimensionReasoningScore

Conciseness

Lean and assumes Claude's competence — terse module tables and ADR citations with no padding or re-explanation of basics (e.g. what a WiFi link is); only mild chattiness like "The deep end:" keeps it just below a 5.

4 / 5

Actionability

Provides concrete executable guidance: real module paths, named functions, runnable host scripts ("node scripts/mesh-graph-transformer.js"), and a copy-paste-ready validation bash block; module-table entries are descriptive rather than executable, so it sits just under fully copy-paste-ready.

4 / 5

Workflow Clarity

The "Validate advanced changes" section is a clearly ordered, real-command validation sequence with a checkpoint (python verify.py) and the security section flags when to run a review; minor gap is the absence of an explicit validate->fix->retry feedback loop.

4 / 5

Progressive Disclosure

Well-organized single-file skill with clear section headers and tight module tables; no bundle files exist to reference, so structure is judged on organization alone, which is good with only minor gaps versus the ideal split-file overview.

4 / 5

Total

16

/

20

Passed

Description

55%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.

The description is comprehensive and highly distinctive, naming many concrete advanced capabilities, but it leans heavily on technical jargon and offers only a vague, non-trigger-rich "Use for" clause. Strengthening the natural-language trigger phrases would lift the weakest dimensions.

Suggestions

Add concrete, user-facing trigger phrases to the "Use for" clause (e.g., 'Use when the user asks about multistatic/multi-node WiFi sensing, RF tomography, or advanced RuView deployments').

Introduce a few natural synonyms users would actually say (e.g., 'through-wall sensing', 'WiFi pose tracking', 'mesh sensing') alongside the technical terms to improve trigger-term coverage.

Reframe a couple of capability names as actions Claude performs (e.g., 'fuse cross-viewpoint CSI', 'reconstruct voxel occupancy grids') to convert capability lists into actionable verbs.

DimensionReasoningScore

Specificity

Lists many concrete capabilities ("attention-weighted fusion, geometric diversity, persistent field model", "RF tomography (ISTA L1 solver, voxel grids)", "pre-movement intention signals") with comprehensive coverage, though they are capability names rather than actions Claude takes — fitting the "lists several specific actions; minor gaps" anchor better than the 5.

4 / 5

Completeness

The "what" is clearly enumerated and there is a "Use for research-grade or multi-node deployments" clause, but the "when" is only weakly specified and not tied to concrete trigger phrases, matching the "clear what but when weakly implied" anchor rather than the 4.

3 / 5

Trigger Term Quality

Dominated by technical jargon ("RuvSense multistatic sensing", "ISTA L1 solver", "multistatic mesh"); the only natural user-facing phrase is "research-grade or multi-node deployments", missing the common phrases and synonyms a user would actually say.

2 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (RuView advanced sensing) with highly specific terminology, making it unlikely to trigger for the wrong skill and minimizing conflict risk.

5 / 5

Total

14

/

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: 3 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.