Conciseness

The body is command-driven and mostly lean, with only minor over-explanation: the opening paragraph explaining what Chargify is ('a subscription billing and recurring revenue management platform... used by SaaS and subscription-based businesses'), the entity-taxonomy 'Chargify Overview' bullet list, and slightly padded best-practices prose. This matches anchor 4 ('efficient; minor instances of over-explanation that could be trimmed') — the padding is real but a small fraction of the document, so it is above anchor 3.

Actionability

Every section gives copy-paste-ready commands with concrete flags: 'npm install -g @membranehq/cli@latest', 'membrane connection ensure "https://chargify.com" --json', 'membrane action run <actionId> --connectionId=CONNECTION_ID --input {...} --json', plus a proxy options table. This matches anchor 5 ('fully executable; copy-paste ready commands; specific examples cover the common cases') — even edge cases like headless auth ('membrane login complete <code>') and polling with '--wait' are handled.

Workflow Clarity

There is a clear sequence (install → login → connection ensure → poll states → search actions → run → proxy fallback) with state-based checkpoints ('READY', 'CLIENT_ACTION_REQUIRED', 'CONFIGURATION_ERROR') and a polling loop, which would merit 4–5. However, the skill supports destructive operations (Cancel Subscription, Delete Customer in the actions table) and contains no validation or confirmation guidance before running them, so per the rubric's cap ('missing validation/verification steps in workflows involving destructive or batch operations should cap workflow clarity at 3'), the score is capped at 3.

Progressive Disclosure

The document is well-sectioned (Install, Authentication, Connecting, Searching, Popular actions, Running, Proxy, Best practices) and entirely self-contained — no bundle files exist, so there are no buried or nested references. This matches anchor 4 ('good structure; most content is appropriately placed; minor organization gaps'), falling short of 5 because the 20-row Popular actions table is inline reference material that would be more discoverable in a separate file in this ~160-line skill.

Specificity

The description names the domain ('Chargify integration') but the actions are generic — 'Manage data, records, and automate workflows' could describe almost any integration skill, with no concrete Chargify operations (subscriptions, billing, invoices, customers) mentioned. It fits anchor 2 ('names the domain but actions are minimal or generic') better than anchor 3, which requires at least one concrete action like 'extracts content'.

Completeness

Both parts are present: the 'what' ('Chargify integration. Manage data, records, and automate workflows') and an explicit 'when' clause ('Use when the user wants to interact with Chargify data'). It falls short of anchor 5 because the 'what' lacks concrete trigger phrases and the 'when' is somewhat redundant with the domain name rather than adding specific trigger scenarios.

Trigger Term Quality

'Chargify' is the relevant keyword and appears naturally, but there is no coverage of common variations or synonyms users would say — 'billing', 'subscriptions', 'invoicing', 'customer management' — matching anchor 3 ('some relevant keywords but missing common variations'). It is above anchor 2 because the domain keyword is specific and natural, not generic filler.

Distinctiveness Conflict Risk

'Chargify' is a specific platform, giving a clear niche with minimal generic overlap, but the description risks confusion with other billing/subscription skills (Stripe, Chargebee) since no Chargify-specific capabilities are named. This matches anchor 4 ('mostly distinct; minor overlap risk with closely related skills').