Conciseness

The CLI sections are mostly lean, command-driven prose, but the ~50-item bare bullet inventory of resources (Story, Comment, Roadmap, ... Webhook) followed by the filler line 'Use action names and parameters as needed' is a padded section that adds no instructional value, fitting 'Mostly efficient but includes some unnecessary explanation or could be tightened'. It is above score 2 because the rest of the document is efficient rather than having several padded sections, and below score 4 because the resource dump alone wastes a large fraction of the file's tokens on content discoverable via 'membrane action list'.

Actionability

Concrete, executable commands appear throughout — 'npm install -g @membranehq/cli@latest', 'membrane connection ensure "https://bigpicture.io/" --json', 'membrane action run <actionId> --connectionId=CONNECTION_ID --input ...' — plus a flag table for proxy requests, matching 'Mostly executable guidance; concrete code or commands with minor gaps'. It is above score 3 because the guidance is real CLI syntax rather than pseudocode, and below score 5 because placeholders (CONNECTION_ID, QUERY, <actionId>) are never resolved in a worked end-to-end example, 'membrane login --tenant' shows no value for --tenant, and line 128 inconsistently uses 'npx @membranehq/cli' where the rest uses 'membrane'.

Workflow Clarity

A sequence is present (install → login → connection ensure → poll for READY → search actions → run → proxy fallback) with state checkpoints (BUILDING/READY/CLIENT_ACTION_REQUIRED), fitting 'Steps listed but validation gaps; sequence present but checkpoints missing or implicit'. It is above score 2 because the connection state machine and re-poll loop are coherently described, but below score 4 because the document twice says 'skip to Step 2' (lines 121 and 135) yet no Step 2 — or any numbered step headings besides '1b' — exists, and failure handling for CONFIGURATION_ERROR is just 'Check the error field'.

Progressive Disclosure

The body has real section structure (Overview, Working with Bigpicture.io, Popular actions, Best practices) and no nested or buried references, but the entire ~195-line skill is one file with no bundle files at all, and the 50-entry API resource inventory is inline content that should be trimmed or split into a reference file — matching 'Some structure but could be better organized; content that should be separate is inline'. It is above score 2 because headers make it navigable and it is not a monolithic wall of text, and below score 4 because at nearly 200 lines it exceeds a lean overview and inlines catalog material (the resource list and the popular-actions table) that belongs behind a clearly signaled one-level-deep reference.

Specificity

"Bigpicture.io integration" names the domain, but the stated actions — "Manage data, records, and automate workflows" — are minimal and generic, matching the anchor 'Names the domain but actions are minimal or generic'. It is above score 1 because a domain and a Use-when clause are present, but below score 3 because no concrete action (e.g., stories, roadmaps, risks, iterations) is ever named.

Completeness

Both parts are explicitly present: a what ("Manage data, records, and automate workflows") and a when ("Use when the user wants to interact with Bigpicture.io data"), matching 'Has both what and when; when could be more explicit or specific'. It is above score 3 because the when clause is explicit rather than missing or weakly implied, and below score 5 because the what is vague and the when lacks concrete trigger phrases beyond the domain name.

Trigger Term Quality

"Bigpicture.io" (repeated in "Use when the user wants to interact with Bigpicture.io data") is a relevant, natural keyword, but there are no synonyms or variations (BigPicture, project planning, roadmaps, portfolio management), fitting 'Some relevant keywords but missing common variations or synonyms'. It is above score 2 because the domain term is specific rather than generic, and below score 4 because coverage consists of essentially one keyword plus generic words like 'data' and 'records'.

Distinctiveness Conflict Risk

The named SaaS domain ("Bigpicture.io") gives a clear niche trigger unlikely to fire for unrelated skills, matching 'Mostly distinct; minor overlap risk with closely related skills'. It is above score 3 because the trigger is anchored to one specific product rather than a broad category, and below score 5 because the generic phrases 'Manage data, records, and automate workflows' could overlap with any data-management or automation skill.