Deck Review Rubric Skill

Deck reviews default to taste: font opinions, color takes, and "I'd reorder this" — the reviewer's aesthetic imposed at slide grain while the deck's actual failure (no argument, no ask, dishonest chart) sails through unexamined. The rubric reviews what decks fail at: argument (do the headlines make a case — deck-outline-first skim test), evidence (does each slide prove its claim — evidence-grading weight), density (billboard or wall — slide-density-rules), arc (does tension carry the room — deck-narrative-arc), and honesty (axes, claims, caveats — citation-hygiene). Findings sort by severity — broken beats suboptimal beats taste — and the review ends with the only sentence presenters can act on: the two fixes that matter most.

What This Skill Produces

• The rubric scores — the five dimensions, each with the evidence for its score (cited slides, not vibes)
• The severity-sorted findings — 🔴 broken (would fail in the room) / 🟡 suboptimal (costs force) / ⚪ taste (offered, labeled)
• The two-fixes call — the highest-leverage changes, because forty comments produce paralysis and two produce a better deck
• The reviewer discipline — the review-comments-resolver contract honored from the giving side

Required Inputs

Ask for these if not provided:

• The deck and its job — audience, ask, time slot; a deck can't be reviewed against an unknown mission (the most common finding is that the mission itself is undefined — that's a 🔴, not a formatting note)
• The review's timing — outline stage (structure feedback is cheap — the ideal), draft (full rubric), night-before (triage: 🔴 only, kindly)
• The presenter's stakes and experience — a first-time board presenter needs the confidence-preserving version: same findings, framed as upgrades
• What the presenter wants checked — their stated worry gets explicit attention (and the review says what it found there)