Conciseness

The CLI guidance itself is tight, but the body pads with content Claude already knows: "Citrix provides virtualization, networking, and cloud computing services. It's used by IT professionals..." plus a ~20-line bullet list of entity names followed by the empty instruction "Use action names and parameters as needed" and a "Popular actions" section that lists no actions. Fits anchor 3 ("Mostly efficient but includes some unnecessary explanation or could be tightened"); not 2 because the majority of the document is lean, executable command guidance rather than sustained over-explanation.

Actionability

Commands are copy-paste ready throughout — `npm install -g @membranehq/cli@latest`, `membrane connection ensure "https://citrix.com" --json`, `membrane action run <actionId> --connectionId=... --input '{"key": "value"}'`, and a concrete proxy flag table. Fits anchor 4 ("Mostly executable guidance; concrete code or commands with minor gaps"); not 5 because the "Popular actions" section contains no actual actions or example IDs, and the entity overview provides zero parameters, leaving the discovery-to-execution step underspecified.

Workflow Clarity

The sequence (install → login → connection ensure → poll state → discover actions → run → proxy fallback) is present with explicit connection-state checkpoints and a re-poll loop after client actions, but it contains a dangling reference — "skip to **Step 2**" points to a step that is never labeled — and offers no validation or error handling after running actions (e.g., checking output or error fields on run failures). Fits anchor 3 ("Steps listed but validation gaps; sequence present but checkpoints missing or implicit"); not 4 because the broken step reference and absent post-execution validation are more than minor gaps.

Progressive Disclosure

The single body file is well organized into clearly headed sections (Install, Authentication, Connecting, Searching, Running, Proxy, Best practices) with an external official-docs link, and dynamic detail is delegated to CLI discovery (`membrane action list --intent`) rather than inlined API reference. Fits anchor 4 ("Good structure; most content is appropriately placed; minor organization gaps"); not 5 because at ~156 lines some material (the entity catalog and proxy flag table) could live in a reference file, and the empty "Popular actions" section plus the unlabeled step numbering leave minor navigation gaps.

Specificity

The domain is named ("Citrix integration") but the actions are generic — "Manage data, records, and automate workflows" could describe almost any integration and names no concrete Citrix capability (e.g., sessions, delivery groups, catalogs). This matches anchor 2 ("Names the domain but actions are minimal or generic"); it is not 3 because no specific concrete action is listed, and not 1 because the domain is explicitly identified.

Completeness

Both parts are present: "what" ("Citrix integration. Manage data, records, and automate workflows") and an explicit "when" ("Use when the user wants to interact with Citrix data"), so the missing-trigger cap of 3 does not apply. Matches anchor 4 ("Has both 'what' and 'when'; 'when' could be more explicit or specific") — not 5 because the 'what' is vague and the 'when' lacks concrete trigger phrases; not 3 because the 'when' clause is explicit, not merely implied.

Trigger Term Quality

"Use when the user wants to interact with Citrix data" supplies the natural keyword "Citrix", but coverage stops there — missing common variations and synonyms users would say such as XenApp, XenDesktop, DaaS, VDI, remote desktops, sessions, or delivery groups. Fits anchor 3 ("Some relevant keywords but missing common variations or synonyms"); not 4 because keyword coverage beyond the brand name is thin.

Distinctiveness Conflict Risk

The description is anchored to a clear niche (Citrix virtualization/remote app management) with the trigger explicitly naming Citrix, making it unlikely to fire for unrelated skills. Fits anchor 5 ("Clear niche with distinct triggers; minimal conflict risk"); not 4 because no closely related skill overlap is apparent — the brand name itself disambiguates.