Conciseness

The body is two lines with a single heading and one sentence giving the exact invocation command; there is no padding or over-explanation, matching the score-5 'lean and efficient; every token earns its place' anchor.

Actionability

It provides one concrete, executable command ('/skill:disable-model-invocation') but gives no task guidance beyond the invocation path, fitting the score-3 'some concrete guidance but incomplete' anchor rather than fully executable task instruction.

Workflow Clarity

This is a single-purpose skill whose sole action (manual invocation via the named slash command) is unambiguous; per the simple-skill exception it scores 5, and no destructive or batch operation is present to invoke the validation cap.

Progressive Disclosure

The skill is under 50 lines, needs no external references, and is organized with a clear heading and a single factual line; per the under-50-line simple-skill exception this matches the score-5 anchor.

Specificity

The description ('A skill that cannot be invoked by the model.') states only a negative constraint and names no concrete action the skill performs, matching the score-1 anchor of pure abstract language with no actions.

Completeness

Neither 'what does this do' nor 'when should Claude use it' is answered; the description only says the skill cannot be model-invoked, fitting the score-1 anchor of missing both what and when.

Trigger Term Quality

There are no natural keywords a user would say when needing this skill; the text contains only a meta statement about invocation, with no trigger phrases, matching the score-1 anchor of no natural keywords.

Distinctiveness Conflict Risk

The description clearly marks the skill as manual-only, which operationally lowers auto-trigger conflict risk, but it conveys no domain niche or triggers, so it lands at the score-3 'somewhat specific but no clear niche' anchor rather than the fully-distinct 5.