Conciseness

Most content is high-value, non-obvious operational knowledge (payload contracts, error patterns, sorting gotchas) with no filler explaining concepts Claude already knows. However, there is more than minor redundancy: 'Fastest Metric Path' steps 1-3 restate Standard Loop steps 1-4, its step 4 overlaps 'Latest Periods Are Not Row Limits', and 'Before You Start' restates the frontmatter's deepline-gtm skip guidance verbatim. This fits 'mostly efficient but could be tightened' rather than the 4 anchor's 'minor instances'.

Actionability

Fully executable, copy-paste-ready commands throughout: 'deepline auth status', 'deepline tools execute snowflake_get_semantic_layer --payload '{"includeYaml": true}'', a complete runnable semantic-query payload with concrete example names (OPPORTUNITY, total_pipeline_generated, discovery_quarter_label), concrete CLI fallback paths, and explicit good/bad filter payload examples. Specific examples cover the common metric-breakdown case, matching the 5 anchor.

Workflow Clarity

The Standard Loop is a clearly sequenced 6-step process with an explicit validation pilot ('Pilot the smallest useful query... This cheaply catches missing credentials, missing semantic objects, and warehouse schema drift') and SQL inspection, backed by an error-to-response table forming feedback loops ('fix the table/metric/dimension/filter and rerun before claiming an answer') and a Reporting Results checklist. This matches the 5 anchor's explicit validation steps, error-recovery loops, and checklists; queries are read-only so the destructive-operation cap does not apply.

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), so all ~180 lines are inline. Section headers and tables are well organized, but content that clearly belongs in a separate reference is inlined: the 'Deepline Internal Analytics Sources' table plus the ~15-line dashboard source-of-truth list is Deepline-internal operational detail irrelevant to standard customer analytics flows, matching the 3 anchor's 'content that should be separate is inline'. The simple-skill exception (under 50 lines) does not apply.

Specificity

The description names the domain richly ("business analytics, RevOps, GTM metric, pipeline, revenue, funnel, customer, or warehouse questions with Deepline") and cites concrete tool identifiers ("snowflake_get_semantic_layer / snowflake_run_semantic_query"). It lists several specific elements rather than multiple distinct actions, and omits what the skill actually does beyond 'answering questions' (e.g., inspecting the semantic layer, validating payloads), so it fits 'several specific actions with minor gaps' rather than the comprehensive coverage of the 5 anchor. It is clearly above the 3 anchor, which expects only 1-2 concrete actions.

Completeness

The 'when' is explicit and 5-level ("Use this skill when answering..." plus concrete trigger phrases and an explicit skip clause), but the 'what' is a single composite capability — 'answering business analytics... questions with Deepline' — rather than enumerated concrete actions like the 5 anchor's 'Extract text and tables... fill forms, merge documents'. This sits above anchor 4's 'when could be more explicit' but below anchor 5's fully concrete what-and-when pairing.

Trigger Term Quality

Natural user phrases are well covered: "'query Snowflake', 'analyze pipeline', 'total ACV', 'break down by quarter', 'use the semantic layer', 'run a semantic query", plus tool-name triggers. A few common variations a user might say are missing (e.g., 'ARR', 'churn', 'retention', 'revenue by account', 'write/run SQL'), which matches 'good keyword coverage; a few natural terms missing' rather than the comprehensive synonym coverage of the 5 anchor.

Distinctiveness Conflict Risk

The niche (Deepline/Snowflake semantic-layer analytics) and tool-ID triggers are distinct, and the explicit skip clause ("Skip prospecting, enrichment, contact finding, outbound, or personalization workflows; use deepline-gtm for those") actively manages conflict with a closely related sibling skill. Residual minor overlap remains: 'GTM metric' and 'customer' questions sit near deepline-gtm's territory, and generic 'warehouse' questions could also match a general Snowflake skill, so it fits 'mostly distinct; minor overlap risk with closely related skills' rather than the minimal-conflict 5 anchor.