Conciseness

The body is mostly command-first and efficient, but has noticeable redundancy: Membrane's auth/credential handling is explained three times ("Working with Bridge", "Proxy requests", "Best practices"), and the "Popular actions" section merely repeats the `action list` command already shown in "Searching for actions" without listing any actions. This sits at 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the level-4 'minor instances' anchor.

Actionability

Concrete, copy-paste-ready CLI commands throughout (`npm install -g @membranehq/cli@latest`, `membrane connection ensure ... --json`, `membrane action run ... --input '{...}'`) plus a flags table for proxy requests — matches 'mostly executable guidance; concrete code or commands with minor gaps'. Not a 5 because the "Popular actions" heading lists zero actions, the CLI is invoked inconsistently (`membrane` vs `npx @membranehq/cli`), and the official-docs link points at a Trello API group rather than Bridge's API, weakening the self-serve lookup path.

Workflow Clarity

The connect-then-poll flow is a genuine sequenced workflow with a feedback loop: connection states (READY, CLIENT_ACTION_REQUIRED, CONFIGURATION_ERROR/SETUP_FAILED) each map to an explicit next action including re-polling after user action. Minor gaps keep it below 5: the text says "skip to Step 2" but no Step 2 heading exists (and there is a "1b" with no "1a"/numbered steps), and no guidance on handling failures from `action run`.

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), so everything lives in a single SKILL.md; it is organized into clear headed sections (Install, Authentication, Connecting, Searching, Running, Proxy, Best practices) of appropriate length for an overview, matching 'good structure; most content is appropriately placed; minor organization gaps'. It is not a 5 because the entity-overview list and the proxy flags table are natural candidates for one-level-deep reference files in a larger bundle.

Specificity

"Bridge integration. Manage data, records, and automate workflows" names the domain but the actions are entirely generic — "manage data, records" and "automate workflows" name no concrete operations (no meetings, transcriptions, summaries, or records operations). This matches the anchor 'Names the domain but actions are minimal or generic' and falls short of level 3, which requires 1-2 concrete actions.

Completeness

Both parts are technically present — what: "Manage data, records, and automate workflows"; when: "Use when the user wants to interact with Bridge data" — but the 'what' is vague (no concrete capability) and the 'when' is circular, restating the product name rather than giving trigger phrases. This is weaker than anchor 4 ('both present, when could be more explicit') because the what itself lacks substance, so it lands at 3.

Trigger Term Quality

The only real keyword is the proper noun "Bridge"; the remaining terms ("data", "records", "workflows", "interact with Bridge data") are generic and miss the natural phrases a user would say (e.g., meetings, transcriptions, summaries, action items). It sits between 'one or two generic keywords' (2) and 'some relevant keywords but missing variations' (3), and since the keyword set is essentially one proper noun plus filler, 2 is the better fit.

Distinctiveness Conflict Risk

"Bridge integration" and "interact with Bridge data" give a clear niche trigger (the proper noun), so it is mostly distinct with only minor overlap risk against other SaaS-integration skills that follow the identical 'X integration. Manage data, records, and automate workflows' template. It does not reach 5 because the generic tail could still collide with sibling integration skills.