Conciseness

The body is mostly efficient executable commands, but contains padded conceptual passages: "It's used by businesses and developers to automate data entry and streamline document processing workflows. Think of it as a way to programmatically pull information out of unstructured documents", "so you can focus on the integration logic rather than auth plumbing", and the mechanics of "The URL is normalized to a domain and matched against known apps". Mostly efficient with some unnecessary explanation; not 4 because there are several trimmable explanatory passages.

Actionability

Concrete, executable commands throughout: `npm install -g @membranehq/cli@latest`, `membrane connection ensure "https://airparser.com/" --json`, `membrane action run <actionId> --connectionId=CONNECTION_ID --input '{"key": "value"}' --json`, plus a proxy flags table and a popular-actions table. Mostly executable with a minor gap: the table lists action `Key` values while the run command takes `<actionId>` without stating they are the same; not 5 because examples require user-specific values and that mapping is unstated.

Workflow Clarity

The connection workflow is well sequenced with real checkpoints (poll with `--wait`, branch on `CLIENT_ACTION_REQUIRED`/`CONFIGURATION_ERROR`, check the `error` field), but the skill surfaces destructive and batch operations — "Delete Inbox", "Upload Document", "List Documents" — with no verification or confirmation guidance before running them. Per the rubric's cap, destructive/batch operations without validation steps cap workflow clarity at 3; not 2 because the connect-and-run sequence itself is clearly defined with state-based branching.

Progressive Disclosure

No bundle files exist and the body is self-contained with well-organized sections (Install, Authentication, Connecting, Searching, Popular actions, Running, Proxy, Best practices) and no dangling or buried references. Good structure with content appropriately placed; not 5 because at ~145 lines it exceeds the simple-skill threshold and some detail (proxy flag table, clientAction state handling) could be split into a reference file.

Specificity

"Manage data, records, and automate workflows" names the domain (Airparser) but the actions are entirely generic — no concrete capabilities like document parsing, data extraction, or inbox management are stated. Not 3 because that anchor requires 1-2 concrete actions; not 1 because the domain is named.

Completeness

"Use when the user wants to interact with Airparser data" is an explicit when-clause and a what is present ("Manage data, records, and automate workflows"), but the what is vague. It sits between anchor 3 (clear what, weak when) and anchor 4 (both present, when could be more specific) — the explicit trigger clause places it noticeably above the midpoint; not 5 since neither the what nor the triggers are concrete.

Trigger Term Quality

The only natural keyword is "Airparser"; "data", "records", and "automate workflows" are generic and lack the natural phrases a user would say ("parse documents", "extract data from PDFs or emails", "document parsing", "inbox"). Fits the anchor for one or two generic keywords while missing the natural phrases users say.

Distinctiveness Conflict Risk

"Airparser" names a clear niche with minimal conflict risk, but the generic tail "Manage data, records, and automate workflows" overlaps with broad data-management and automation skills. Mostly distinct with minor overlap risk; not 5 because the non-brand terms alone would collide with many similar skills.