train-pose

Train/evaluate WiFi pose models honestly — camera-supervised (MediaPipe + CSI) and camera-free (WiFlow), always checked against the mean-pose baseline before any PCK is quoted.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./harness/ruview/.claude/skills/train-pose/SKILL.md

Quality

Content

78%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 lean and well-structured with a clear validation-gated workflow, but actionability is held back by the absence of executable commands or invocation details for the referenced tool and ADRs.

Suggestions

Add a concrete invocation example for `ruview_claim_check` (command syntax and expected output) so the validation step is executable.

Make the publish workflow's feedback loop explicit, e.g., 'fix any flagged claim and re-run ruview_claim_check; only quote PCK when it passes'.

Show one concrete command for running the mean-pose baseline on a split so step 1 is copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no padding or explanation of basic concepts; every line earns its place and it assumes Claude's competence.	5 / 5
Actionability	Concrete checklist steps (run baseline, report 'model − baseline' in pp, ruview_claim_check the writeup) but no copy-paste executable commands or invocation syntax for the referenced tool/ADRs, leaving guidance incomplete.	3 / 5
Workflow Clarity	Clear numbered 4-step 'Before you publish' sequence with an explicit validation checkpoint (ruview_claim_check flags claims), but the error-recovery loop is implicit rather than a gated 'only proceed when' step.	4 / 5
Progressive Disclosure	Under 50 lines with no external bundle files needed; well-organized sections (non-negotiable baseline, Paths, Before you publish) make navigation easy, satisfying the simple-skill exception.	5 / 5
	Total	17 / 20 Passed

Description

67%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 specific and clearly niche, but it leans on technical jargon for triggers and omits an explicit 'when to use' clause, capping completeness at 3.

Suggestions

Add a 'Use when ...' trigger clause naming natural user phrasings (e.g., 'Use when training or evaluating WiFi CSI pose models, or when reporting PCK numbers').

Soften pure jargon triggers with natural synonyms users would say (e.g., 'pose estimation', 'train a pose model') alongside MediaPipe/WiFlow/PCK.

Dimension	Reasoning	Score
Specificity	Names the domain (WiFi pose models) and multiple concrete actions — 'camera-supervised (MediaPipe + CSI)' and 'camera-free (WiFlow)' — plus the baseline-check discipline, giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Clearly states what the skill does but lacks any 'Use when...' trigger clause; per rubric guidance a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant but mostly technical keywords ('WiFi pose models', 'MediaPipe', 'WiFlow', 'PCK') rather than natural user phrases; missing common variations or synonyms a user would actually say.	3 / 5
Distinctiveness Conflict Risk	Highly niche (WiFi CSI pose modeling with a mean-pose baseline discipline) with distinct, specific triggers, giving minimal overlap with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/RuView
Path: harness/ruview/.claude/skills/train-pose/SKILL.md
Commit: a76adc3

Reviewed: about 4 hours 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.