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.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

76%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 lean, well-indexed overview that respects the token budget and gives real commands and paths for exploration and validation. Its weakness is process: it describes where each subsystem lives but offers no sequenced workflow or feedback loop for actually deploying or using the advanced sensing features.

Suggestions

Add a short numbered workflow for a representative task (e.g., enable multistatic mode → verify coherence gate decisions → check adversarial rejects), ending in the existing cargo test validation as an explicit checkpoint with a fix-and-retry step.

Show one concrete usage example per headline feature (a node script invocation with expected output, or a snippet that reads the field-model residual) so the main capabilities are actionable, not just located.

Dimension	Reasoning	Score
Conciseness	Every token earns its place: terse module tables ("Welford stats, biomechanics drift detection"), one-sentence architecture facts Claude cannot know ("Treat every WiFi link in range — including neighbours' APs — as a bistatic radar pair, then fuse them"; "the residual is the perturbation"), and zero textbook explanation or padding.	5 / 5
Actionability	Provides executable, copy-paste commands (`node scripts/mesh-graph-transformer.js`, the `cargo test --workspace --no-default-features` / `verify.py` block) and specific real paths, but how to actually operate multistatic mode or produce a tomogram is never demonstrated — the core features are described via module names rather than usage examples.	4 / 5
Workflow Clarity	The body indexes subsystems rather than prescribing a process: the validation command block and the "run a security review when touching the hardware/network boundary" checkpoint exist, but there is no sequenced deploy/use workflow and no fix-and-retry feedback loop, matching "sequence present but checkpoints missing or implicit".	3 / 5
Progressive Disclosure	Clear section headers, module tables acting as an index, and a Reference section pointing one level deep to ADRs (014/029/030/031/032/081/083/095/096), docs/research/, and a named security-audit doc, with no nested references and nothing inlined that belongs in a separate file. Not 5 because the ADR pointers are bare numbers without titles or paths, and the referenced scripts are not part of this skill's bundle.	4 / 5
	Total	16 / 20 Passed

Description

75%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 dense, jargon-appropriate capability inventory with an explicit but terse trigger clause. It is highly concrete and distinctive for its domain, falling just short of top marks because the capabilities are listed as feature nouns without actions, and the "when" guidance names deployment contexts rather than natural user triggers.

Suggestions

Rewrite capability nouns as concrete actions (e.g., "Fuse multistatic WiFi links", "Reconstruct voxel occupancy grids via ISTA") and mention the gesture classifier so the what-coverage matches the body.

Extend the trigger clause with user-utterable phrases, e.g., "Use when the user mentions multistatic sensing, RF tomography, cross-node fusion, or mesh security hardening."

Dimension	Reasoning	Score
Specificity	The description enumerates many concrete capabilities ("attention-weighted fusion, geometric diversity, persistent field model", "RF tomography (ISTA L1 solver, voxel grids)", "longitudinal biomechanics drift", "adversarial signal detection") with no vague language, but they are capability nouns rather than concrete actions and the gesture classifier covered in the body is omitted, leaving minor gaps in coverage.	4 / 5
Completeness	A clear and comprehensive "what" is paired with an explicit trigger clause ("Use for research-grade or multi-node deployments"), so it is not capped at 3; however the "when" names deployment contexts rather than concrete user-utterable trigger phrases, matching the anchor where "when" could be more explicit.	4 / 5
Trigger Term Quality	Strong domain keywords a specialist would naturally say ("multistatic", "RF tomography", "cross-viewpoint fusion", "mesh security hardening", "multi-node deployments"), but no synonyms, variations, or concrete artifact/command names, which the 5 anchor requires.	4 / 5
Distinctiveness Conflict Risk	Terms like "RuvSense multistatic sensing", "RuView", and "ISTA L1 solver" occupy a clear niche with minimal conflict risk, though the "Advanced" framing implies sibling RuView skills sharing overlapping trigger space, leaving minor overlap risk.	4 / 5
	Total	16 / 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: 3 missing	Warning

	Total	15 / 16 Passed

Repository: ruvnet/RuView
Path: plugins/ruview/skills/ruview-advanced-sensing/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.