The body lists discrete checklist items ("Quality of earnings (QoE) — revenue and EBITDA adjustments", "Working capital analysis — normalized vs. actual") without explaining what those concepts are, so it is lean and assumes Claude's competence; it stays above score 2 because there is no padded concept explanation, only actionable line items.

Concrete guidance is given throughout — explicit Step 1 intake questions, a status table with defined columns, a status state-machine ("Not Started → Requested → ... → Red Flag"), red-flag fields, and output formats; as an instruction-only skill with actionable guidance, the absence of code is not penalized per the scoring notes.

A clear 5-step sequence (Scope → Generate → Status Tracking → Red Flag → Output) with a built-in living-document update loop and escalation path; the validation-checkpoint cap does not apply because this is a non-fragile generative task, so it reaches the score-3 anchor rather than being capped at 2.

It is a well-organized single file with clear sections, but at ~118 lines the exhaustive per-workstream item lists and sector-specific additions are inline where they could be split into one-level-deep reference files, and no references exist at all; this matches the score-2 anchor ("content that should be separate is inline") rather than the score-3 split-with-navigation pattern, and the under-50-line exemption does not apply.

"Generate and track comprehensive due diligence checklists" plus "request lists, status tracking, and red flag escalation" lists multiple concrete actions, matching the score-3 anchor rather than the single-action score-2 example.

It explicitly states what ("Generate and track comprehensive due diligence checklists... Covers all major workstreams...") and when ("Use when kicking off diligence, organizing a data room review, or tracking outstanding items"), satisfying the score-3 anchor for both what AND when with explicit triggers.

"Triggers on 'dd checklist', 'due diligence tracker', 'diligence request list', 'what do we still need', or 'data room review'" gives good coverage of natural phrases a user would say, matching the score-3 anchor; it is above score 2 because it includes common variations rather than a single keyword.

Due diligence is a clear niche with distinct triggers ("dd checklist", "data room review") unlikely to fire for unrelated skills, matching the score-3 anchor; it is not score 2 because the domain is specific rather than broadly overlapping.