Conciseness

The command blocks are lean, but there is measurable padding: a two-sentence product intro ("It's used by developers, analysts, and researchers..."), a near-empty placeholder "Bitquery Overview" section ("- **GraphQL Query** / - **Response**"), and duplication — `membrane action list` with the same intent/flags appears in both "Searching for actions" and "Popular actions". This matches 'Mostly efficient but includes some unnecessary explanation or could be tightened' rather than the minor-trim level of 4.

Actionability

Concrete, executable commands throughout: `npm install -g @membranehq/cli@latest`, `membrane login complete <code>`, `membrane connection ensure "https://bitquery.io/" --json`, `action run` with `--input '{"key": "value"}'`, and a full proxy flag table. Matches 'Mostly executable guidance; concrete code or commands with minor gaps' — not a 5 because "Popular actions" promises examples but delivers only the generic discovery command, with no concrete Bitquery action id or input example.

Workflow Clarity

A clear install → login → connect → poll → discover → run → proxy sequence with explicit checkpoints: `--wait` long-polling, per-state handling (READY, CLIENT_ACTION_REQUIRED with a re-poll loop, CONFIGURATION_ERROR/SETUP_FAILED → check the error field). Matches 'Clear sequence with most checkpoints present; minor validation gaps' — the gaps are the dangling "skip to **Step 2**" reference (no step is ever labeled Step 2, and "1b" has no "1a") and no error-recovery guidance for failed action runs, which keep it below 5.

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), so the score rests on the ~140-line body: sections are well-organized, appropriately sized for a single-file integration skill, and the only external pointer (the official docs URL) is one level deep. Matches 'Good structure; most content is appropriately placed; references mostly clear; minor organization gaps' — the placeholder "Bitquery Overview" and duplicated discovery section are the minor gaps keeping it from 5.

Specificity

"Bitquery integration. Manage data, records, and automate workflows" names the domain but every stated action is generic integration filler — no concrete Bitquery capability (e.g., run GraphQL queries, fetch blockchain transactions) is mentioned, matching the anchor 'Names the domain but actions are minimal or generic'. It is not a 3 because that anchor requires 1-2 concrete actions, and nothing here is concrete.

Completeness

Both parts are present: what ("Manage data, records, and automate workflows") and an explicit when ("Use when the user wants to interact with Bitquery data"), but the 'when' merely restates the product name rather than giving concrete trigger phrases, matching 'Has both what and when; when could be more explicit or specific'. Not a 5 because the trigger clause is tautological rather than concrete; not a 3 because an explicit 'Use when' clause exists.

Trigger Term Quality

"Bitquery" and "data" are relevant keywords a user might say, but common variations and synonyms — "blockchain data", "crypto", "on-chain", "GraphQL", "Web3" — are entirely missing, matching 'Some relevant keywords but missing common variations or synonyms'. Not a 2 because 'Bitquery' is a specific, non-generic product keyword rather than purely generic language.

Distinctiveness Conflict Risk

Bitquery is a distinct named product with a narrow niche, so wrong-skill triggering is unlikely; the only overlap risk comes from the generic "manage data / automate workflows" phrasing shared with many data-integration skills, matching 'Mostly distinct; minor overlap risk'. Not a 5 because the triggers lack concrete phrases beyond the product name itself.