Conciseness

The body is mostly efficient — concrete commands with brief explanations for auth, connections, actions, and proxying — but contains unnecessary padding: the marketing-style intro ("Chift is a platform that simplifies integrations... used by developers and IT professionals"), the vague "Chift Overview" bullet tree followed by the filler line "Use action names and parameters as needed", and a "Popular actions" section that only repeats the discovery command already shown. This matches the anchor 'Mostly efficient but includes some unnecessary explanation or could be tightened'; it is not a 4 because several sections add tokens without adding guidance.

Actionability

Nearly every section provides copy-paste-ready CLI commands: install (`npm install -g @membranehq/cli@latest`), login (including the headless `login complete <code>` fallback), connection ensure with polling, action list/run with `--input` JSON, and a proxy flag table. This matches the anchor 'Mostly executable guidance; concrete code or commands with minor gaps'. It is not a 5 because placeholders (CONNECTION_ID, <actionId>) are never demonstrated in a realistic worked example, and the "Popular actions" heading promises example actions but delivers none.

Workflow Clarity

The sequence — install, login, connection ensure, poll to READY, handle client actions, search actions, run, proxy fallback — is clear and includes real checkpoints: the connection state machine (READY / BUILDING / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR) with a poll loop and re-check after the user acts. This matches the anchor 'Clear sequence with most checkpoints present; minor validation gaps'. It is not a 5 because "skip to Step 2" references a labeled step that does not exist anywhere in the document, leaving the intended step ordering implicit.

Progressive Disclosure

The ~140-line single-file body has real sections but navigation is unreliable: a dangling "skip to Step 2" cross-reference, inconsistent heading hierarchy ("### Searching for actions" sits under "## Working with Chift", while "## Popular actions" is a sibling that contains "### Running actions" as a subsection), and a duplicated "Popular actions" section. This matches the anchor 'Some structure but could be better organized'; it is not a 4 because the defects impede navigation rather than being minor placement gaps, and not a 2 because the content is genuinely sectioned and there are no buried or nested references.

Specificity

The description names the domain ("Chift integration") but its actions are generic — "Manage data, records, and automate workflows" describes virtually any integration skill, with no concrete Chift-specific capabilities (e.g., sync accounting records, manage connections or webhooks). This matches the anchor 'Names the domain but actions are minimal or generic'; it is not a 3 because none of the listed actions is concrete enough to count as a specific capability.

Completeness

It has both a 'what' ("Chift integration. Manage data, records, and automate workflows") and an explicit 'when' ("Use when the user wants to interact with Chift data"), which matches the anchor 'Has both what and when; when could be more explicit or specific'. It is not a 3 because the when-clause is explicit rather than merely implied, and not a 5 because the 'what' is vague and the 'when' is circular — it triggers only on the word Chift rather than on concrete task phrases.

Trigger Term Quality

The natural keyword "Chift" appears both as the lead and in the trigger clause ("interact with Chift data"), but coverage stops there — no variations or synonyms users would naturally say ("Chift API", "Chift integrations", "connect apps via Chift", "sync data through Chift"). This matches the anchor 'Some relevant keywords but missing common variations or synonyms'; it is not a 4 because the surrounding terms ("data", "records", "workflows") are generic rather than natural trigger phrases.

Distinctiveness Conflict Risk

"Chift" is a distinctive brand name and the only trigger is Chift-specific ("Use when the user wants to interact with Chift data"), giving it a clear niche with minimal risk of firing for unrelated skills. This matches the anchor 'Clear niche with distinct triggers; minimal conflict risk'; the generic middle sentence does not create meaningful conflict risk because it is not the trigger.