Conciseness

The body is lean and assumes competence — terse bullets, no teaching of concepts Claude already knows. Minor redundancy keeps it from anchor 5: the opening paragraph restates the frontmatter description, and "Guardrails" vs "Pitfalls" overlap (e.g., the team-billing-from-marketing caution appears in both).

Actionability

Concrete guidance throughout: explicit classification checklists ("duplicate checkout / real team intent / broken self-serve controls"), named code paths to inspect ("checkout, pricing page, entitlement calculation, seat or quota handling"), and a copy-paste Output Format template. It stops short of fully executable anchors (5) because no concrete data-access commands or code examples are given (e.g., how to pull Stripe sales or refunds).

Workflow Clarity

A clearly sequenced 4-step workflow (evidence → classify → inspect code → decide) with a final Verification checklist. Validation is end-of-run rather than an in-loop checkpoint, which is a minor gap versus anchor 5's explicit validate-fix-retry loops; the refund decision step is not a batch/destructive automated operation, so no cap applies.

Progressive Disclosure

Well-organized single-file structure with clear sections and no inlined bulk content that belongs in separate files; no bundle files exist (references/, scripts/, assets/ are absent) and none are needed. It does not meet anchor 5's well-signaled one-level-deep references (there are no references at all), and the under-50-line simple-skill exception does not strictly apply to this ~129-line file, so anchor 4 is the best fit.

Specificity

The description names several concrete capabilities ("sales snapshot, pricing comparison, duplicate-charge diagnosis, or code-backed billing reality") rather than generic language, but "billing-model truth workflow" is somewhat abstract and coverage has minor gaps (e.g., disputes/MRR are absent). Fits anchor 4 — several specific actions with minor gaps — better than anchor 5's comprehensive coverage, and clearly above anchor 3's 1-2 actions.

Completeness

Both parts are explicit: the what ("Evidence-first revenue, pricing, refunds, team-billing, and billing-model truth workflow for ECC") and a concrete when clause ("Use when the user wants a sales snapshot, pricing comparison, duplicate-charge diagnosis, or code-backed billing reality"). This matches anchor 5; anchor 4 would require a weaker or less specific 'when', which is not the case here.

Trigger Term Quality

Natural user phrasing is well covered: "revenue", "pricing", "refunds", "team-billing", "pricing comparison", "duplicate-charge diagnosis". A few common variations are missing (MRR, chargebacks, subscription billing, "overcharged"), so it sits at anchor 4 rather than anchor 5's comprehensive synonym/extension coverage.

Distinctiveness Conflict Risk

The niche is fairly distinct (evidence-first operator billing truth vs. customer remediation), and "instead of generic payments advice" signals the boundary, but the description does not explicitly contrast with the closely related `customer-billing-ops` skill (that contrast only appears in the body), leaving minor overlap risk with sibling billing skills. Anchor 4 fits; not anchor 5's minimal-conflict clear niche.