Conciseness

Nearly every line delivers rc-specific facts Claude cannot already know — "`rc schema apps:create` silently returns the root schema", the exit-code table, the `data.items[]` vs `data.names[]` envelope caveat. No padding, no explanation of general CLI concepts; every token earns its place — anchor 5.

Actionability

Commands are copy-paste ready throughout (`npx @revenuecat/cli <command>`, `brew install RevenueCat/tap/rc`, `rc commands --schemas --json`) and the skill documents a reliable self-discovery mechanism. The "Common operations" section, however, uses abbreviated noun forms ("rc projects list|create|use", "rc products ...") rather than a fully worked example invocation with expected output — a minor gap against anchor 5.

Workflow Clarity

The install → authenticate → discover → operate sequence is clear, with an explicit discovery workflow ("Don't guess a command or flag, ask the binary") and error-recovery signals via exit codes (4 = auth, 5 = not found) and `--no-input` failing rather than hanging. Not 5 because no explicit validation/verification checkpoint is built into the workflow; the exit-code table documents failure modes but the skill does not direct the reader to check them at any step.

Progressive Disclosure

The skill is under 50 lines, needs no external reference files (none exist in the bundle), and is organized into clear, scannable sections. Cross-references to sibling skills (`revenuecat-paywall-design`, `revenuecat-dashboard-links`) are clearly signaled and one level deep — anchor 5 under the simple-skill guideline.

Specificity

The description lists several concrete capability areas — "Covers install, authentication, command discovery, and output conventions" — but stops at category level rather than naming concrete operations (e.g., listing products or managing offerings). Anchor 4 (several specific actions, minor gaps) fits; not 5 because coverage is enumerated at a summary level only.

Completeness

The "what" is clear (drive RevenueCat from the terminal via the rc CLI), but the "when" is only weakly implied through "an alternative to the RevenueCat MCP server for humans, CI, and agents" and the trailing sentence about other skills referencing it. There is no explicit "Use when..." clause, which caps completeness at 3 per the judging guidelines; not 4 because the usage context is inferential rather than stated.

Trigger Term Quality

Natural trigger terms are present: "RevenueCat", "terminal", "rc CLI", "MCP server", "install", "authentication". A user needing this skill would plausibly say "RevenueCat CLI" or "rc command", though common variations like "command line" are absent. Good coverage with a few natural terms missing — anchor 4.

Distinctiveness Conflict Risk

The description explicitly carves a clear niche — "an alternative to the RevenueCat MCP server" — with a specific named tool (`rc`), making confusion with other skills unlikely. Clear niche with distinct triggers; anchor 5.