Conciseness

Mostly efficient command-first sections, but padded spots remain: 'Chartmogul is a subscription analytics platform. It helps SaaS businesses track and analyze key metrics...' explains the vendor's business rather than the task, the bare object-tree Overview ('Customers / Subscriptions / Invoices...') adds little, and editorial asides like 'This is the fastest way to get a connection' and 'This will burn less tokens' could be trimmed. Matches 'Mostly efficient but includes some unnecessary explanation or could be tightened'.

Actionability

Concrete, executable CLI commands throughout: install (`npm install -g @membranehq/cli@latest`), login including the headless completion flow, `membrane connection ensure`, polling with `--wait`, `action run` with a real `--input` JSON example, and a proxy flag table. Not a 5 because the search example uses an unresolved placeholder (`--intent "QUERY"`) with no filled-in real intent example, and there is no complete end-to-end run (search → run with actual parameters → read output) tying the pieces together.

Workflow Clarity

The install → login → connect → poll → search → run sequence is present with explicit state handling (READY, BUILDING, CLIENT_ACTION_REQUIRED, CONFIGURATION_ERROR) and poll-again guidance, which is good. However the body references 'skip to Step 2' and a '#### 1b' heading with no Step 2 ever labeled, and — decisive for the cap — destructive operations (delete-customer, delete-plan) and batch list operations ship with no validation or verification guidance, which per the rubric caps workflow_clarity at 3. It is not a 2 because the sequence and error-state recovery are substantially better defined than a rough outline.

Progressive Disclosure

There is no bundle at all (no references/, scripts/, or assets/), so everything lives inline in a ~160-line SKILL.md. Section headers and tables give it reasonable navigation, but content that belongs in a separate reference — the 20-row Popular actions table and the proxy flag options — is inlined, matching 'Some structure but could be better organized... content that should be separate is inline'. It is not a 2 because the structure is genuinely present and navigable, not a wall of text.

Specificity

The description names the domain ('Chartmogul integration') but the actions are generic — 'Manage data, records, and automate workflows' could apply to almost any business app, matching the anchor 'Names the domain but actions are minimal or generic'. It is not a 3 because it never lists a single concrete Chartmogul capability (e.g. list customers, sync subscriptions, query MRR); it is not a 1 because the domain is explicitly named.

Completeness

A 'when' clause is present ('Use when the user wants to interact with Chartmogul data') but both halves are weak: the 'what' is vague ('Manage data, records, and automate workflows') and the 'when' is a near-tautology ('interact with Chartmogul data'). This sits between anchor 3 (clear what, weak when) and anchor 4 (both present, when could be more specific) — the when is explicit but circular and the what lacks concrete actions, so it falls noticeably below the anchor-4 midpoint.

Trigger Term Quality

The only substantive keyword is 'Chartmogul' itself; 'data' and 'records' are generic filler. Natural phrases a user would say — subscription analytics, MRR, churn, customers, invoices, plans — are all absent, matching 'One or two generic keywords; missing the natural phrases users say'. It is not a 3 because even common synonyms for the domain are missing, not just a few variations.

Distinctiveness Conflict Risk

The trigger is anchored to the distinct product name 'Chartmogul', so it is unlikely to fire for unrelated skills. It is not a 5 because the generic action phrasing ('Manage data, records, and automate workflows') is structurally identical to other app-integration skills, creating minor overlap risk among sibling integrations.