Lean, table-driven structure that assumes Claude's competence — it never explains what IRR, MOIC, or private equity are, and every section earns its place. Not the level below because there is no unnecessary concept explanation or padding.

Gives concrete attribution formulas and a clear MOIC definition, but the IRR computation is hand-wavy ('adjust for interim cash flows') and the sensitivity tables are empty templates with no executable method to populate them. Not score 3 because key computational details are missing; not score 1 because several formulas and a precise input list are provided.

A clear Step 1–5 sequence is present, but there are no validation or sanity-check checkpoints (e.g., confirming the equity bridge balances or that IRR/MOIC are consistent). Not score 3 because explicit validation steps and error-feedback loops are absent; not score 1 because the steps are well sequenced.

Self-contained with well-organized sections (Workflow, Key Formulas, Important Notes) and no nested references, which is appropriate for a focused single-file skill. Not score 2 because content is clearly sectioned rather than a monolithic wall, and there are no deep reference chains.

Lists multiple concrete actions — 'Build quick IRR/MOIC sensitivity tables' and 'Models returns across entry multiple, leverage, exit multiple, growth, and hold period scenarios' — matching the score-3 anchor for several specific actions.

Explicitly answers both 'what' (build IRR/MOIC sensitivity tables, model returns across scenarios) and 'when' via an explicit 'Use when…' clause, satisfying the score-3 anchor.

Provides natural phrases a user would actually say — 'returns analysis', 'IRR sensitivity', 'MOIC table', 'what's the return at', 'model the returns', 'back of the envelope' — giving good coverage of common variations.

Occupies a clear niche (PE deal returns analysis) with distinct, domain-specific triggers unlikely to fire for unrelated skills.