Conciseness

Most of the body is lean executable commands, but the opening "Canvas is a learning management system used by educational institutions..." explains a concept Claude already knows, and the 20-row "Popular actions" table repeats "No description" twenty times — both are tightening candidates. This matches the score-3 anchor 'Mostly efficient but includes some unnecessary explanation or could be tightened'; not a 4 due to these specific padded spots, not a 2 because the bulk is command-driven and useful.

Actionability

The body provides copy-paste-ready commands throughout — `npm install -g @membranehq/cli@latest`, `membrane connection ensure "..." --json`, `membrane action run <actionId> --input '{...}'`, plus a documented proxy flag table — covering install, auth, connection, search, run, and proxy. This matches the score-5 anchor 'Fully executable; copy-paste ready code or commands; specific examples cover the common cases'; not a 4 because the common cases are concretely covered with explained parameters.

Workflow Clarity

The connect-to-Canvas flow is well sequenced with a state machine (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and polling feedback loops, but the skill facilitates destructive operations (create-course, update-user, DELETE via proxy) with no validation or verification step taught. Per the rubric guideline, a destructive/batch workflow missing validation is capped at 3; it is not a 2 because the sequence and checkpoints for connection setup are clearly present, and not a 4 because the cap applies.

Progressive Disclosure

The body is a single well-organized file with clear section headers (Overview, Working with Canvas, Install, Authentication, Connecting, Searching, Popular actions, Running actions, Proxy, Best practices) and no nested/2+-level references — bundle directories do not exist. This matches the score-4 anchor 'Good structure; most content is appropriately placed; references mostly clear; minor organization gaps'; not a 5 because the inlined 20-row action table and clientAction detail could arguably live in a separate reference file, not a 3 because organization is clean and one level deep.

Specificity

Quotes "Canvas integration. Manage Canvases." name the domain but the actions are minimal and generic ("Manage"), matching the score-2 anchor 'Names the domain but actions are minimal or generic'. It is not a 1 because a concrete domain is named, and not a 3 because no concrete operations (list courses, submit assignments, etc.) are listed.

Completeness

It states a (vague) what ("Canvas integration. Manage Canvases.") and an explicit when ("Use when the user wants to interact with Canvas data."), fitting the score-4 anchor 'Has both what and when; when could be more explicit'. It is not a 5 because the what is generic and lacks concrete trigger phrases, and not a 3 because an explicit 'Use when' clause is present (which the guideline says avoids the cap at 3).

Trigger Term Quality

The phrase "Use when the user wants to interact with Canvas data" supplies the natural keyword "Canvas", but it misses common variations and synonyms users would say (courses, assignments, grades, submissions). This matches the score-3 anchor 'Some relevant keywords but missing common variations or synonyms'; not a 4 because coverage is thin, not a 2 because "Canvas" is a genuine natural term rather than pure jargon.

Distinctiveness Conflict Risk

"Canvas" is a specific product niche with a distinct trigger ("interact with Canvas data"), so conflict risk with other skills is low, matching the score-4 anchor 'Mostly distinct; minor overlap risk'. It is not a 5 because the trigger phrasing is somewhat generic ("Canvas data") rather than crisply scoped to LMS tasks.