Conciseness

The CLI guide is mostly efficient, but the "Apollo Overview" section ("Query — Represents a data request", "Schema — Defines the structure of the data", "Use action names and parameters as needed") is filler explaining concepts Claude already knows and adds nothing, the "Popular actions" heading duplicates the search command from "Searching for actions", and phrases like "This is the fastest way to get a connection" are padding. It matches anchor 3 ('mostly efficient but includes some unnecessary explanation') rather than 4 because the filler overview section is a whole wasted block, not a minor trim.

Actionability

Concrete, executable commands throughout: `npm install -g @membranehq/cli@latest`, `membrane login complete <code>`, `membrane connection ensure "https://www.apollographql.com/" --json`, `npx @membranehq/cli connection get <id> --wait --json`, `membrane action run <actionId> --connectionId=... --input '{...}' --json`, and a full proxy flag table. It fits anchor 4 ('mostly executable with minor gaps') and not 5 because the "Popular actions" section promises popular actions but lists none, and there are no worked end-to-end examples with real parameter values.

Workflow Clarity

A clear sequence exists (install → login → connection ensure → poll → search actions → run/proxy) with a genuine feedback loop for the connection lifecycle (poll while BUILDING, handle CLIENT_ACTION_REQUIRED with its clientAction fields, check the error field on CONFIGURATION_ERROR/SETUP_FAILED). It is not 5 because the text says "skip to Step 2" but no Step 2 exists, "1b" appears with no "1a", and there is no verification guidance after running an action or proxy request.

Progressive Disclosure

No bundle files exist, and the single ~140-line file is organized under clear section headers with all content appropriately inline at this scale; there are no buried or nested references. It matches anchor 4 ('good structure, most content appropriately placed, minor organization gaps') rather than 5 because of the redundant overlap between the "Searching for actions" and "Popular actions" sections and the inconsistent step numbering.

Specificity

The description names the domain ("Apollo integration") but the actions are generic: "Manage data, records, and automate workflows" lists no concrete capability specific to Apollo (no lead search, contact enrichment, or outreach actions). It matches anchor 2 ('names the domain but actions are minimal or generic') and not anchor 3 because no concrete, specific action is articulated.

Completeness

Both elements are explicitly present — what ("Manage data, records, and automate workflows") and when ("Use when the user wants to interact with Apollo data") — but the 'what' is vague and the 'when' merely restates the domain circularly. It falls between anchor 3 (clear what, weak when) and anchor 4 (both present, when could be more specific), closer to the middle, so 3 rather than 4 because neither element is concrete.

Trigger Term Quality

The only meaningful trigger keyword is "Apollo"; "data", "records", and "workflows" are generic and omit the natural phrases a user of this platform would say (leads, prospects, outreach, sales intelligence, sequences). It sits at anchor 2 rather than 3 because the non-domain keywords carry no real trigger value.

Distinctiveness Conflict Risk

"Apollo" anchors a specific product, but "Manage data, records, and automate workflows" is broad enough to overlap with any data-management or automation skill, and "Apollo" itself is ambiguous (Apollo.io sales intelligence vs. Apollo GraphQL). It matches anchor 3 ('somewhat specific but could still overlap with similar skills'); not 4 because the generic action list and the name ambiguity create real overlap risk.